- Deterministic hash-based character portraits and reference sheets
- Implemented strict early Renaissance aesthetic controls and role-specific headwear rules
- Added audiobook batch export scripts and progress tooling
- Verified book profiles with a new 'confirmed' state tracking mechanism
- Updated Pillow dependency for robust image handling
- Configured .gitignore for audiobook and audio cache exports
Re-cast all three volumes end to end and compared each against its existing
cast. Book 03 finished at 9 unknown, below the 25-line cast it replaced, and
its fused multi-turn segments — one voice reading both sides of an exchange —
fell from 60 to 6. Speaker counts stayed level with the hand-corrected books
instead of inflating, confirming the phantom-speaker filter and the label
consolidation both hold.
Agreement with the hand-corrected books is 81-82%. The largest remaining
error is systematic ping-pong inversion, where a whole exchange alternates
onto the wrong speaker, followed by epithets that share no tokens with the
canonical name.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Consolidation ran only at cast completion, but recast/repair passes assign
speakers of their own and can re-introduce the variants just removed —
confirmed live: a freshly cast book gained "Alrik" alongside "Alrik von
Blautann" during auto-repair, splitting one character across two voices again.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
One character is referred to by several labels across a book — bare vs full
name, a title on its own, a stray fragment — and each variant became its own
cast entry with its own voice, so the character audibly changed voice
mid-scene. Measured against a hand-corrected book this accounted for more of
the disagreements than genuine misattributions.
Variants are folded together only when one label's words are a strict subset
of another's after stripping articles and titles, so "Weber" and "Alter Weber"
stay separate and unrelated names never merge. Applied to a real cast:
Sharraz -> Sharraz Garthai, Baronin -> Baronin Ira von Seewiesen,
Von -> Oberst Alrik von Blautann (40 lines, 58 -> 54 speakers).
Also moves the quotation-mark toggle into the A- / A+ toolbar row.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
CSS cannot target a character inside a text node, so the marks are now wrapped
in their own .ab-q element at render time and hidden with a single class on
body. Toggling is instant regardless of segment count, and the stored text is
never modified.
Also fixes the toggle looking inert on a freshly cast book: it previously only
added missing marks and never hid the ones the book already carried. Button
moved bottom-right as a larger labelled pill, clear of the search controls.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
German prose never quotes narration, so displaying the guillemets makes a
mislabeled line obvious at a glance. Extraction strips them from ~80% of
segments, so they are rendered rather than stored: dialogue rows display
wrapped in » «, lines that kept their own marks are left as-is, and the saved
text is untouched so synthesis and exports are unaffected. A toolbar button
toggles visibility and the choice persists.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Adjacent segments merge when they share a speaker, but an unattributed line
carries the speaker "Unknown", so two consecutive Unknown lines compared as
equal and were fused into a single block joined by a blank line. Confirmed
against the source text: Lysandra's line and Perdia's interruption — two
separate paragraphs in the book — became one segment, after which no
attribution pass could separate them and one voice would read both sides of
the exchange.
"Unknown" means the speaker is not known, never that two lines share one.
Narration and lines with a real speaker name merge exactly as before.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
A trailing inquit names only the last speaker, so applying it to a block
holding multiple turns silently mis-credited the earlier one — a wrong
attribution is invisible where an Unknown is not. Such blocks are now skipped
by the grammar rules and left for the LLM pass or a manual split.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
"Darrags Stimme klang tonlos." after a quote names who just spoke, but the
voice-announcement rule only looked at the narration before a line, so this
mirror image stayed Unknown. Verified on the book (-> Darrag).
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Driven by unresolved lines in a real German novel:
- AB_SPEECH_VERBS was missing many common inquit verbs (grunzte, versetzte,
unterbrach, drängte, herrschte, keuchte, erklärte, widersprach, warf ein …)
and had no thought verbs at all, so inner monologue ("dachte Lysandra") was
never attributed.
- A trailing inquit naming two people ("unterbrach die blonde Perdia Lysandra")
resolved to the wrong one; the grammatical subject speaks, so articles and
adjectives are skipped and the first name after the verb wins.
- A quote whose own inquit had been mistyped as dialogue could never resolve,
because the rule required the following segment to be narration. A segment
opening with a lower-case speech verb is an inquit whatever its type; it is
now accepted and its type corrected.
Verified on the book: resolves further lines with no LLM call.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Opening a book always restored the localStorage draft and then pushed it to the
server as a backfill, so a tab holding an older copy silently overwrote newer
work saved from anywhere else — confirmed live: a cast improved from 79 Unknown
lines to 25 was destroyed by opening the book in a stale tab. Local and server
drafts are now compared by savedAt, the newest wins and is cached locally, and
the server is only backfilled when the local copy is actually newer.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The Identify/Cast flyouts were hard-anchored to open above their trigger,
which suited the casting panel's bottom footer but clipped them off the top of
the screen in Studio, where the same toolbar sits near the top — the first two
entries were unreachable. They now pick the side with space, prefer opening
downwards, stay clamped inside the viewport and scroll if taller than it.
Also reorders the Identify menu to the sequence the passes should run in, with
the one-click Auto-repair cast first.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Spoken lines that PDF extraction typed as narration were invisible to
"Identify unknown characters" (it only scans type==='dialogue'), so no number
of re-runs could fix them, while the pass that could re-sent all ~1000
narration segments to the LLM. Adds a detector that scores narration for
direct-speech signals and re-checks only those: 36 candidates instead of 1036
on a real novel. Adds "Auto-repair cast" to chain the passes in the right
order automatically after casting.
Also fixes a rollback gap where stopping a run skipped the safety net that
undoes a pass which increased Unknown speakers (confirmed live: 80 -> 159
with no warning), corrects an attribution rule that taught the model the
listener is the speaker, and stops the threshold loop from re-verifying every
narration segment each round.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Fish-Speech clones from the app's own saved WAV library but was missing from
the set of backends populated with those voices, so the UI probed the Fish
server for a voice-listing endpoint it does not have, showed "Fetched 0
voices" and left the engine unusable despite being healthy. It now reports
the full library (218 voices).
Also adds a Fish-only panel listing all 49 documented emotion tags with
click-to-insert and a multi-emotion example, and corrects the backend's
advertised capabilities: it was flagged style_aware with "emotion markers are
honoured per request", but measurement shows a reference clip's in-context
prosody overwhelms inline tags (10x loudness spread across emotions without a
reference, 1.2x with one). It is now described by what it does well:
deterministic, byte-reproducible cloning.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The emotion quick-pickers added in 1.20.5 guarded with
`typeof REH_EMOTIONS === 'undefined'`, but REH_EMOTIONS is a const declared
later in the bundle's single shared scope — `typeof` on a const in its
temporal dead zone throws instead of returning "undefined", which aborted
top-level initialization for every module bundled after tts-preview.js.
The pickers now read window.REH_EMOTIONS on a deferred macrotask.
Also: emotion instructions are now always built in English (spoken text and
the native-accent clause stay in the book's language), which controlled A/B
testing showed produces a far cleaner prosodic gradient from Qwen3-TTS; and
Fish-Speech now receives temperature/top_p/repetition_penalty, which it was
the only backend never to have forwarded.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Fish-Speech emotion tags were silently ignored on non-English books: per-line
emotions are LLM-generated in the book's own language, but Fish-Speech only
recognizes English [tag] markers, and a double-tagging bug was stacking a
broken server-derived tag on top of the client's own. Added a DE->EN
translation table and removed the double-tagging. Also wires the existing
book-profile context and race_species field into character portrait prompts
(previously only used for voice design), adds a recast-until-threshold loop
for casting, and adds backend-aware emotion quick-picks to Read Aloud, Try a
Voice, and Conversation.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
For a designed voice the instruct prompt is the voice's identity — the TTS
engine reproduces the voice from that text alone. The only copy saved was the
`note` display summary, clipped to 240 characters, which left 43 of 73 voices
cut off mid-sentence. Save the complete prompt in its own field so the engine
can register a voice from the whole description.
Existing voices keep working from the clipped copy (it still carries gender,
accent and timbre) and pick up the full text when next redesigned.
Pairs with the engine-side fix in tts-dgx-spark-faster-qwen3-tts.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Voice consistency:
- Read back each voice's pinned seed (Seed Finder / Batch Seeds) on every
generation. The seed was saved to voice metadata but only ever read by the
Seed Finder's own benchmark path, so all per-voice seed pinning was inert.
- Stop coercing the "voice_design_playback" stability profile back to
"voice_clone". The pseudo-backend key isn't a real routing target, so the
backend-name normalizer silently rewrote it — reintroducing the hardcoded
seed:0 that profile exists to avoid, overriding every per-voice pin.
- Apply the accent clause on every line, not just at voice-creation time,
and reorder the instruct so emotion leads and accent trails (Qwen3-TTS
doesn't reliably follow multiple conflicting instructions).
- Pass an explicit language to Voice Design instead of leaving it on "Auto".
Audio effects:
- Add a limiter after compressor makeup gain. Makeup gain pushed peaks to
~1.9, and the final hard clip turned that into broadband distortion that
swamped the rest of the chain.
- Cascade highpass/lowpass 3 stages each (~18 dB/octave). Single-pole
filters were too gentle to band-limit speech audibly.
- Add a Bandpass control and wire it into the Telephone/Radio presets —
compression alone never sounded like a phone; band-limiting is the
defining trait.
Persona / Try It Out:
- Disable "Apply character persona" with an explanatory tooltip when the
voice has no persona saved, and error clearly server-side instead of
silently no-op'ing. Persona is typed manually per voice, never auto-filled.
- Stop dropping applyPersona in the chunked generation path (>200 chars).
- Populate the Voice Design dropdown from the user's own library rather than
filtering the engine's discovery list, which never contains custom voices.
Navigation and library:
- Use pushState instead of replaceState so browser Back/Forward step through
in-app navigation instead of leaving the app entirely.
- Show real dialogue line counts in the character sidebar instead of the
capped reference-quote count (which showed a misleading uniform "12").
Also fixes a crash in /api/transcribe-bytes that referenced an undefined
source_id in its cleanup path.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Introduces the new Studio section (Source -> Characters -> Voices ->
Perform & Export) that reuses the existing Read Aloud/Library/Script
Rehearsal code via DOM reparenting instead of duplicating it, and rolls up
a long tail of bugs found while producing a real audiobook through it:
umlaut-eating name sanitizers, a voice picker that mispositioned itself and
capped results at 60, PDF pagination silently breaking on trimmed \f
markers, a race letting stale audio keep playing after a new line was
clicked, an alias-overlap bug that could silently redirect a voice/image
save onto the wrong character, voice design failing outright during brief
TTS backend restarts instead of retrying, sparse cast entries defaulting to
English/wrong gender, and a reassigned voice never reaching an already-open
Stage session or invalidating its cached audio. Also adds a persistent
per-line audio cache, audiobook export browsing/download, and an inline
voice-design prompt editor. Full details in CHANGELOG.md.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
A fresh (non-resume) cast unconditionally nulled _audiobook.rehId even
when retrying or recasting a book that already had a linked Rehearsal
Library record from a prior attempt — silently orphaning it and
creating a new one on the next save. Now only nulled for a genuinely
first-ever cast; retries/recasts overwrite the existing record.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Same pattern as the Casting audiobook Prompt button: a collapsible
textarea with the full extraction prompt (fields + sources/citation
schema), named-preset save/load/delete, and live persistence so edits
apply from the next passage onward. Server-side, _charsheets_prepare()
now accepts a character_sheets_prompt override (shared by the blocking
and streaming endpoints), following the same pattern already used for
the audiobook attribution prompt override.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Was a small 420px dialog with a collapsible one-line JSON preview and a
cramped 2-column chip grid. Now a big panel matching the audiobook
casting live view's shape: passage text (left) and live JSON output
(right) side by side, with a character sidebar on the right edge whose
just-updated entries are highlighted — so the user can watch each sheet
actually being built from its source passage instead of a tiny opaque
progress bar.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Two gaps observed in real casting output:
1. A mid-quote " - " (em-dash pause) was being read as the end of the
quotation, handing the rest of the line to a wrong/new speaker.
2. Narration naming whose voice is about to speak (e.g. "Marcians
Stimme wirkte nicht mehr so fest") wasn't being used to resolve the
following unattributed line away from 'Unknown'.
Added as rules 11/12 to the client-side AB_DEFAULT_PROMPT (the prompt
actually sent to the LLM) and to normalizeCastingPrompt()'s migration
so already-saved custom prompts pick them up automatically, same
mechanism as the earlier Doppelpunkt-Regel upgrade. Also added
equivalent rules to the server-side fallback prompt in
routes/conversation.py for completeness, though the client-sent prompt
is what's actually used in normal operation.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A document-level "click outside closes the popup" handler only exempted
clicks on the paragraph's speaker label, not clicks anywhere else in the
passage text. Since mousedown fires before click, this closed the popup
(clearing assignModeRow) before the v1.14.13 name-click logic ever ran,
making "click a name elsewhere to feed the open popup" silently do
nothing. Passage-text clicks/drags no longer auto-close the popup.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The intended flow is: click the broken paragraph's speaker label to open
"Assign to", then supply the name (type, click it anywhere in the text,
or drag-select it). But clicking or drag-selecting a name with no popup
open yet used to open/target a popup for whichever paragraph that name
lived in, silently reassigning THAT paragraph instead of the one the
user meant to fix. Both paths now require an already-open popup before
they do anything — a paragraph is only ever selected via its own
speaker label (or the existing double-click fast-assign shortcut).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The Characters Found sidebar, the "Assign to" popup's character list,
and the "merge with an already-found character" list now show each
character's saved portrait when one exists (same source as the profile
detail panel), falling back to the existing colour-keyed initial-letter
dot otherwise.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Clicking a name inside a paragraph's text always retargeted the "Assign
to" popup (and its highlight) to that paragraph, even when the popup was
already open for a different one. That made it look like the wrong
paragraph was being reassigned when the user just wanted to reuse a name
they saw elsewhere. Now, while a popup is open, clicking a name outside
its target paragraph only fills the search box.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Passage/Thinking boxes in the audiobook casting live view can now be
resized vertically. Also fixed the character-list collapse button's
chevron pointing opposite to the direction the panel edge actually moves.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Confirmed by directly probing a streaming response from vllm-0.23.1rc1:
its delta objects carry reasoning text under "reasoning", not the more
common "reasoning_content" key every reasoning-display code path was
checking for. Added a shared _reasoning_text() helper that checks both,
used by the Conversation Playground, audiobook casting's live view, and
character sheets.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Was 6min/3min. 122B+ models can take longer than that just to produce
a first token; 10min also happens to match the server-side cap
(_request_timeout_seconds), so this is the max without raising that too.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The "LLM Reading…" split view showed the same passage text three times
(reader pane, Passage column, and a full-width block toggled by the
chevron that duplicated the Passage column). Removed the redundant
full-width block, repurposed the chevron to show/hide the two-column
view itself, and swapped the columns to Passage (left) / Thinking (right).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Reasoning-model chain-of-thought is now separated from the spoken/displayed
reply on the server (handles both a dedicated reasoning_content field and
inline <think> blocks, including chat templates that inject the opening tag
as a prompt prefix so it never appears in the stream). The client shows it
in a panel collapsed behind a "Thinking" chevron instead of dumping raw
reasoning text into the chat or speaking it aloud via TTS.
Also moved the noise-gate slider out of its own row and next to the mic
button, grouping it with Auto-stop/Hands-free/Live agent.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Two unclosed <div class="card"> tags in the TTS settings markup left the
add-engine dialog nested inside the TTS panel's DOM subtree, so it
rendered at zero size whenever another Engines sub-tab (e.g. Speech
Recognition) was active. Also fixed a `let` declared after its first
use, which threw a ReferenceError on every Engines-tab page load.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Streaming playback never produces an in-memory blob, but the enable
logic required one. Now enables unconditionally and lazily
re-synthesizes a buffered blob on demand if effects are applied before
one exists.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- App Routing's output-voice field gets the same searchable
avatar-thumbnail dropdown used elsewhere, as a browse button
alongside the existing free-text input (which must stay editable to
target vd_ Voice Design presets not in the voice library).
- My Voices table: Gender and Rating filter dropdowns existed in the
JS (populateLibraryFilters, libraryFilterMatch) but their <select>
elements had been dropped from the visible layout after an earlier
redesign, replaced with hidden dead placeholders just to keep the
code from erroring - and since populateLibraryFilters() early-returns
if any of the three elements are missing, this silently broke the
already-visible Language/Type dropdowns too. Restored the real
elements and removed the hidden scaffold; added new Tag and Group
dropdowns wired to the same filter state the sidebar chips use.
- Audio effects failing with "pedalboard is not installed" despite
requirements.txt listing it: the package WAS installed, but its
native extension (pedalboard_native) links against libatomic.so.1,
an OS-level shared library missing from the python:3.11-slim-bookworm
base image. Added libatomic1 to the Dockerfile and rebuilt - verified
`import pedalboard` now succeeds in the running container.
- Relabeled "edit ID"/"copy ID" to "rename filename"/"copy filename"
in the voice inspector - the feature already renamed the underlying
.wav/.meta.json/.reference.txt/picture files via the existing
/api/voice/rename endpoint, it just wasn't obvious "ID" meant
"filename."
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Confirmed in production: a streaming attribution/character-sheets
request held _attribution_llm_lock for 11+ minutes, well past its
configured timeout, silently rejecting every subsequent passage as
"Attribution engine busy" and falling back to the non-streaming view -
looking exactly like live-thinking had stopped working, when actually
one earlier request never finished.
Root cause: requests' timeout= on a stream=True call only covers the
connect + first byte, not gaps between later body reads. If the LLM
backend goes silent mid-stream (connection left open, no more chunks),
the blocked socket recv() inside iter_lines() can hang indefinitely.
Since that's a native blocking call, not a Python-level yield point,
neither an in-loop wall-clock check nor GeneratorExit from a
disconnected client can interrupt it - both only take effect at the
next bytecode boundary, which never arrives while blocked in the C
extension.
Added _watchdog_close: a daemon thread that force-closes the upstream
connection if the wrapped block hasn't finished within the configured
timeout. Closing the socket from another thread makes the blocked
recv() raise, unblocking the generator so its normal except/finally
cleanup (including releasing the lock) actually runs. Verified against
the live LLM backend post-restart: stream completes normally with
real token-by-token deltas, and the lock is confirmed free immediately
after.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
It used position:sticky with a top:40vh offset - sticky's containing
block grows with the document, so on a long PDF the pill drifted
toward the bottom instead of staying a fixed distance from the
viewport's actual visible top. Switched to position:fixed.
Also investigated a "characters all gone" report: verified directly
in the SQLite database that all 47 records for the book are intact,
and a fresh browser session renders them correctly with no errors -
this was a transient/stale-page display issue, not data loss.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Character Sheets generation only ever showed a progress bar - no
visible reading/thinking/filling-out, unlike the casting flow which
already streams the LLM's output live. Refactored
/api/character-sheets into shared _charsheets_prepare/_charsheets_parse
helpers (same split used for attribution) and added
/api/character-sheets/stream, proxying the LLM's SSE stream through
the same shared lock used by the other attribution endpoints.
Client: new csGenerateStream (mirrors audiobookAttributeStream) tries
the streaming endpoint first per passage, updating a new "Live output"
panel in the progress dialog with the raw JSON answer as it's written
- itself the "watch it fill out the sheet" experience, since there's
no separate reasoning channel worth hiding it behind here. Falls back
to the blocking endpoint on any stream failure.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A leftover rule colored the icon accent-blue from when this button
was still .btn-secondary (accent icon on a white background). After
making it the primary blue button in the last release, that same blue
rendered blue-on-blue against the button's own background - invisible.
Confirmed via computed style before/after (blue -> white) rather than
guessing from the screenshot alone.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Recasting one character out of a 149-passage book was reading the
entire text every time, exactly as flagged: "you only need to read a
couple of paragraphs before and after his name." csForReaderSelective
now matches the picked character's name + known aliases against the
book's chunks, keeps one chunk of context on either side for
pronoun/"he" resolution, and only extracts from those - falling back
to the full book only if nothing matched at all (e.g. a name typo).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Character sheet generation is already available from "Cast Characters"
in the Casting flow, so the standalone button here was a duplicate
entry point. Removed it and made "Cast as audiobook" the primary blue
action, moved to the end of the toolbar as the clear next step in the
pipeline.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
csForReaderSelective passed the ENTIRE roster to csGenerate as the
target list, so the "N cast characters queued" progress dialog showed
every character regardless of what was actually checked in the picker
- only the final save step was correctly filtered, making the whole
run look like it ignored the selection. Now only the picked name(s)
go in as the target roster.
Also fixed the "Recast options" dropdown opening off-screen: its
anchor sits in the bottom action bar, so opening downward (the
default) routinely pushed it past the viewport edge. Opens upward
when there isn't enough room below, with more prominent styling.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The backend hint box sat beside the 4 tuning rows via grid-row: 1 /
span 4, forcing it to stretch to their combined height no matter how
short its own text was - usually leaving a large empty gap below a
1-3 line hint. Moved it full-width below the rows instead, sized to
its own content, and dropped the now-redundant two-column grid and
mobile-breakpoint overrides that existed only to manage it.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Merging two characters could block the main thread long enough to
trigger the browser's own "Page Unresponsive" dialog - the merge
itself is a fast array loop, but redrawing the whole feed afterward
(thousands of DOM rows, each running highlightText's regex pass) was
one long synchronous chunk. A plain spinner overlay can't fix that,
since it freezes right along with everything else in the same JS
turn. Split _abMergeCharacters into a fast relabel step plus a new
_abRedrawSegmentsChunked that rebuilds the feed across animation
frames, driving a real progress bar in the busy overlay instead of a
static "please wait".
Also added search + sort (line count / alphabetical) to the Casting
sidebar's character list, matching the Library's character list
controls.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The earlier table-view fix (display:table-row on <tr>) wasn't the
whole story: display:flex directly on a <td> (Stimme, Tags columns)
also broke its table-cell participation in Chromium, rendering that
cell stacked at the PREVIOUS column's x-position regardless of
table-layout mode - confirmed via direct DOM/rect inspection, not
guesswork. Moved flex layout to inner wrapper divs and switched to
table-layout:fixed with an explicit colgroup so column widths are
never re-negotiated by content again.
Also added actual character merging to the "also known as" alias
popup: picking an existing roster entry (e.g. "Schmied" from Darag's
popup, when the LLM split one person into two roster names) reassigns
every one of its segments to the character you opened the popup from,
with undo support - not just a linked library alias that left the
live cast still showing both as separate people.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Any selection under 40 chars was treated as "assign this as a
character name," including short quoted lines like "»Henker«." that
the user clearly meant to split into their own Unknown-speaker
segment - guillemets/quotes are never part of a name. Selections
starting with a quote mark now skip the assign-popup hijack and fall
through to the already-visible "Split text to Unknown Speaker" button.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Table view was rendering as stacked blocks instead of columns: rows
reused .lib-char-card for its event wiring, but that class's
display:flex;flex-direction:column turned every <tr> into a flex
column. Reset to display:table-row and stripped the leaked-in card
chrome.
Split /api/character-generate-prompts into four independent per-field
LLM calls (from two paired calls) and added a `fields` filter, so the
UI can offer one Generate button per prompt box instead of a single
button that always regenerated all four - cheaper, and further
shrinks each response to reduce truncation risk.
Added a Sort dropdown (Role/Alphabet/Lines/Gender/Voice assigned) to
the Characters/Cast list, persisted like the Cards/Table toggle.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
"Cast Characters" always blindly regenerated the whole cast from
scratch, even for a book already fully cast - no way to just look at
what's there or touch up a handful of characters without redoing
everyone. Once clGetAllByTagOrBook finds existing characters for this
book, the button becomes a split control: View Characters (jump to the
Library overview) plus a dropdown for Recast all or Recast selected...
(checkbox picker that re-scans the book but only saves updates for the
characters checked).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Replaces the horizontal avatar strip above the transport bar with a
sidebar next to the script page, reusing Read Aloud's Casting sidebar
classes (.ab-cv-side/.ab-char-item) directly instead of a separate
look. Same collapse-to-avatars control, now shows each character's
line count, and clicking a character scrolls the script to their
first line. Removed the CSS/HTML this replaces.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Server logs showed /api/analyze-characters succeeding on every attempt
but /api/voice-design never once being called - the bulk voice-design
loop accessed rehState.cast[sp].voice unguarded right after that
(multi-second, for a large cast) request resolved. Any cast-entry
change during that window threw an uncaught TypeError, silently
killing the whole run with no toast, no further requests, and the
button stuck disabled. Guarded the access and wrapped the remaining
flow in try/catch/finally so failures are visible and the UI always
resets.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Table view: one row per character (avatar, name, sex, line count, voice
language, alignment, voice, tags, prompt-availability checks), toggled
next to the card grid and persisted.
Bulk voice auto-assign: checkbox per character + "Auto-assign selected"
per production, sequential so later picks see what earlier ones just
took (avoids duplicate voice assignments).
Character tags (auto-set to the book of origin) are now visible on
cards - the field always existed, cards just never rendered it, so a
character recurring across books had no visible link between records.
Detail fields (Backstory, Motivation, etc.) now show small numbered
links to their exact source citation when the sheet has one, instead
of making the reader search the full "Quellen im Text" list.
Added gender as an actual extracted character-sheet field - the UI
already had a gender icon but the LLM was never asked for the value.
Fixed SillyTavern/Concept Art prompts still coming back empty despite
the earlier token-budget increase: they're the last two fields in one
JSON object, so truncation always cost the same two regardless of the
ceiling. Split into two independent, concurrent LLM calls instead.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The streaming attribution endpoint decoded the LLM's SSE response with
requests' guessed encoding (Latin-1 fallback when no charset is declared),
mangling every German umlaut. Forced UTF-8 explicitly.
The "LLM Thinking" pane duplicated the passage text for models that
ignore the <think> instruction and stream straight into JSON - it now
only shows real reasoning when present, and otherwise labels raw output
honestly instead of passing it off as thinking.
Also fixed three UI bugs found while testing a live multi-hour cast:
- A-/A+ font buttons had no effect (a hardcoded font-size on .ab-cv-row
always overrode the CSS variable they set).
- Typing a name + Enter in the "Assign to" popup (and drag-to-assign,
which reuses it) silently did nothing after the first cast/recast run
in a session - the popup is a page-lifetime singleton but its input
handlers closed over the first run's now-stale assignName/closePopup.
Every popup open now repoints them at the current run.
- "Split text to Unknown Speaker" split at the wrong spot when the
selected phrase repeated earlier in the same paragraph (indexOf found
the first occurrence, not the dragged one). Now uses the exact DOM
range offset instead.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The static-asset caching middleware used BaseHTTPMiddleware, which has a
known Starlette bug: a client disconnecting mid-StreamingResponse (the new
live-attribution SSE stream hitting its idle timeout) raced its internal
task group and raised "RuntimeError: No response returned", crashing that
request. Rewritten as plain ASGI middleware that only touches headers via
the raw send callable, removing the race.
Also found the real cause of the casting timeouts/405s: the streaming
attribution endpoint had its own lock instead of sharing the one the
blocking endpoint already used to serialize on the LLM's single slot -
letting a stream call and its own blocking fallback fire concurrently,
exactly the ghost-request pile-up that lock was built to prevent. Unified
onto one lock and added server-side logging for stream failures.
The "LLM Thinking" pane now shows the model's actual <think> reasoning
instead of the in-progress JSON answer echoed back at the user.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The LLM Reading card splits into thinking-stream (left) and passage
(right), fed by a new SSE endpoint that shares prompt-building and
parsing with the blocking one and falls back to it on any stream
failure (inactivity timeout, not overall). The deterministic resolver
no longer invents speakers from scenery nouns (PLATZ/GESICHTER/
KLEINIGKEIT) — person-noun whitelist plus a clause-subject pattern —
and gains the impersonal post-quote formula and strict two-person
alternation with colon/page/window guards. All reported failure cases
verified against the exact book sentences.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The recast/quality view's sidebar rebuilt its roster from only the
lines being checked, appearing to wipe every named character (the cast
itself was safe: named lines are never recast targets and increases in
Unknowns already roll back). The sidebar now seeds from the full cast
and refreshes during the run. Error notes fall back to the HTTP status
(statusText is empty on HTTP/2). The deterministic grammar resolver
runs before any LLM call in quality runs.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The LLM left ~44% of dialogue Unknown even with all deduction rules in
its prompt, so the mechanical ones now run in code per passage: colon
rule (with a non-agent-noun stoplist), post-quote inquit, and the "who
had spoken" pattern. Fills only Unknowns, never overrides the LLM.
Tested against the exact reported failure cases.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The saved casting prompt was the 2nd-quality verification prompt, so
first-pass attribution ran with the wrong job description and none of
the deduction rules — and the client-side prompt migration had no
anchor to upgrade. The server now appends the rules to any prompt
lacking them, and the saved prompt was reset to the default (backed up
to config/audiobook_prompt.backup.txt). Also: single-pass combined name
regex (a shorter alias could match inside a longer name's data-name
attribute and leak raw style="..." into the feed), stopword filter so a
comma-split alias like "Die, die den Vampir verließ" can't underline
every article, heading-like narration renders bold/centered, and A-/A+
font controls in the casting toolbar sharing the Rehearser Stage scale.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Characters/Cast gains a "Casting" button back to the active casting
session, the pipeline stepper renders on the Library section, and the
stepper's Cast Characters stop navigates instead of side-effect-running
sheet generation. Prompt generation: 4096-token budget (1600 truncated
the four-prompt JSON so two fields silently arrived empty), truncated
answers salvage completed fields, all-empty responses fail loudly, and
partial results name the missing prompts. The PDF-extraction progress
pill is enlarged and vertically centered.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The per-word <span> wrapping behind "click any word to assign" created
~100k DOM nodes at book scale and froze the tab on every feed redraw;
replaced with native caretRangeFromPoint word detection plus a single
reused hover overlay — same UX, zero extra DOM. Export button gained a
2s re-entry guard (queued clicks during a freeze fired as a download
burst) and now delivers one zip: the cast script in Markdown plus a
sheet per character. Character detail view gains a Generation Prompts
section — four fold-out copy boxes (Voice Design, Character Image,
SillyTavern card, Concept Art sheet) filled by one LLM call over the
full profile via the new /api/character-generate-prompts endpoint.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The casting prompt now teaches the deduction patterns behind most false
Unknown/Narrator assignments: colon-introduced quotes, post-quote inquit
attribution, pronoun resolution to the last-named matching-gender
character, addressee rule, strict two-person ping-pong, and role names
(Ork, Nachbar) as valid speakers. Saved prompts upgrade in place; the
2nd Quality Run prompt gets the same toolkit. The attribution language
hint falls back to detecting the book's language from its text instead
of relying on a usually-empty dropdown.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Speed: OCR renders only the heading band (was full page at 2.5x),
Tesseract worker freed after extraction, name-underline index cached
instead of rebuilt per segment, constant regexes hoisted, old drafts
migrate segment page numbers once at load (single-path feed renderer).
Quality: global [hidden]{display:none!important} ends the empty-box bug
class; racy deferred cast-restore + _readerSuppressCastRestore flag
replaced by a synchronous, caller-wins restore; card collapse defaults
move to data-collapse-default markup; duplicated join/colour/alias/LLM-
target helpers now delegate to their canonical implementations; dead
reader state removed; stepper hide-guard fixed for the merged Source key.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- Add a 6-stage pipeline stepper (Source -> Cast Audiobook -> Cast Characters
-> Script Rehearser -> Generate MP3s -> Audiobook) with direct, non-destructive
jumps between stages and a prominent guided-tour look
- Split PDF import into an explicit "load" then "Extract Text" step, with
in-browser OCR (Tesseract.js, vendored) to recover chapter headlines baked
into a PDF as images instead of real text
- Fix casting feed silently merging pages after leaving/returning: segments
now carry their own page number instead of re-guessing it from text
- Fix excessive "Unknown" speaker attribution: restore the attribution LLM's
output token budget, which had been cut roughly in half and was truncating
dialogue-dense passages
- Fix Theater Play library cards failing to open (dead pre-migration
IndexedDB API calls, missing section navigation)
- Fix bulk "Set tag" wiping a voice's existing tags instead of adding to them
- Start merging Casting's feed with Script Rehearser's Stage UI: collapsible
character sidebar, shared "paper" page styling, inline text editing
- Fix a performance regression from that merge (per-row listeners on every
redraw) by moving to event delegation
- Various layout/clutter fixes: hide reader chrome until a document is
loaded, collapse secondary settings by default, fix overlapping toolbar
icons, fix duplicate "opening" notifications
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
After a successful /api/voices fetch, results are written to sessionStorage
(key ttsvc_vc). On the next page load loadVoiceLibrary() reads the cache and
renders voices immediately before the network request completes, eliminating
the blank-list / skeleton flash entirely.
The background fetch always runs and overwrites the cache with fresh data.
Error handling is graceful: if the network fails but cache was served, the
error is suppressed (stale data stays visible). The Refresh button clears the
cache first to force a full reload cycle.
Silent-refresh logic (from v1.12.19) prevents the second loadVoiceLibrary()
call (engines.js batch E) from blanking already-rendered voices.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Root cause 1 (v1.12.18): `window.loadVoiceLibrary = () => loadVoiceLibrary()`
overwrites the global binding the arrow function references, causing immediate
RangeError: Maximum call stack size exceeded on every call. Changed to direct
assignment `window.loadVoiceLibrary = loadVoiceLibrary`.
Root cause 2 (v1.12.18): `loadSettings()` called `renderSettingsAbout()` which
lives in conversation.js (batch E), loaded after init.js. Guard added with
typeof check; nav.js already calls it safely when the About section opens.
Also (v1.12.18): s-library.html duplicated cl-book-filter / cl-search / cl-grid
from s-characters.html, breaking getElementById. Characters panel in Library
now redirects to s-characters instead of duplicating its DOM nodes.
Also (v1.12.19): engines.js triggers a second loadVoiceLibrary() after nav.js
already rendered voices, blanking the list briefly. Second call now silently
re-fetches without clearing the list when voices are already present.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
loadSettings() was crashing with "Cannot set properties of null" because
many settings input elements were moved out of their original sections
during the Library restructure. All bare .value assignments are now
routed through a local sv() helper that silently skips absent elements.
This was also blocking My Voices from rendering on page load.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
After a batch benchmark completes, successful entries are saved to each
voice's meta.json via POST /api/voice/meta. window.loadVoiceLibrary() is
then called so My Voices Factor + WPM columns update instantly without
a manual reload.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Voice selection list now shows flag + gender symbol on each row.
Batch results table adds Lang and Gender columns. All columns are
sortable by clicking the header (↑↓ indicator); defaults to Factor
descending. Sort logic handles strings (locale) and numbers uniformly.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Voices table: removed Length, Duration, Time — only Factor and WPM remain
from benchmark data. Setup → Benchmark batch results now shows Duration,
Factor (sorted fastest-first, colour-coded), Time, and WPM. Factor replaces
Avg RTF with the same data flipped to a more intuitive direction (higher=better).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The old combined `21.8s · 1.30x` Speed cell is replaced by two separate
sortable columns:
- Factor (x.xx): audio÷render multiplier, green/amber/red colour-coded
- Time (Xs): total render time
Column order: Length · Duration · Factor · Time · WPM · Seed · dBFS · ...
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Previously the bench/wpm cells only updated after loadVoiceLibrary() at
the end of the full batch. Now each row is patched in-place immediately
after its voice finishes, for both batch and single-voice benchmarks.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
WPM (words per minute) is derived from the benchmark audio duration and
sentence word count, revealing how fast a voice speaks — independent of
GPU speed. 130–180 wpm is comfortable for audiobooks. Column is sortable.
Info (ⓘ) icons on Speed and WPM headers explain both metrics on hover.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Speed column now displays 1.32× instead of 1.3× for better precision.
Sorting by Speed ranks by the RTF multiplier (faster = higher ×) rather
than raw elapsed time, so the sentence length no longer skews the ranking.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Voices cloned from a Script Rehearsal now show the script title in the
SOURCE column without requiring manual entry. `_displaySource()` parses
the note field (`Rehearser · <title> · <character> — …`) and returns the
title segment as the source. Explicit `origin` values still take priority.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add Source input to voice inspector panel (saves to origin in meta.json)
- Auto-detect fish-audio voices via tag — SOURCE column now shows
"fish-audio" for tagged voices even without an explicit origin field
- Bulk "Set source" action in the multi-select toolbar
- Source cell in table reflects the live-displayed value and updates
immediately when changed via the inspector
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Casting completion auto-saves to Rehearser IndexedDB (same format
as script rehearsals). Manual speaker corrections in the cast view
debounce-save after 1.5s.
- rehId tracked across session (stored in localStorage draft) so
updates go to the same record instead of creating duplicates.
- Voice assignments made in Script Rehearser survive an auto-update:
only script text and emotions are overwritten; voice/instruct/soul
are merged from the existing record.
- "Edit in Rehearser" button in the completed cast footer opens the
saved record directly in Script Rehearser, ready for voice casting.
- Expose rehDbGetById + rehLoadRecord globally from rehearser.js.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Saves accumulated segments after every chunk. On page refresh or crash,
reopening Cast as Audiobook for the same document restores the session
automatically — shows a banner with completion % and save age.
Manual speaker reassignments in the cast view are also autosaved so
review corrections survive a refresh. Draft clears when the script is
saved to Script Rehearsals or a fresh Recast All is triggered.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Click any gap divider to reveal the hidden segments between two Unknown
passages inline — shows speaker + text so context is clear before
making an assignment. Displays line count ("42 lines hidden — click
to expand") so users know what they are opening.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Pulsing blue dot on the Read Aloud nav item while casting is active
- Navigating away and returning restores the cast panel automatically
- Reassigning a segment's speaker decrements the old count so the
Characters Found panel stays in sync; speakers at 0 disappear
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Conversation: adjustable noise gate slider (RMS threshold + 300 ms
minimum burst duration) prevents short noise spikes from triggering
STT; level meter shows gate position as a blue marker
- Conversation stats panel now collapsible (chevron button) to free
chat width; floating expand button restores it; state persists
- Read Aloud: text search input in PDF toolbar (Enter = next hit,
Shift+Enter = previous, Esc = clear)
- Sidebar: tooltip now works for all item types including sub-items
that had no .nav-label span (text extracted by stripping icon/badge)
- Sidebar active section indicator added (.nav-tree-item.active was
previously unstyled — active section now has bg + right accent bar)
- Casting audiobook: prompt instructs LLM to handle ?« / !« endings
and unclosed » at passage end as dialogue; deterministic fallback
also handles unclosed opening quote
Bumps to v1.12.2.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Hovering the collapsed 56 px rail no longer expands the whole sidebar,
which was pushing the main content left and right. Each nav item now
shows a small floating tooltip (JS-positioned fixed div) next to its
icon on hover — layout stays completely stable.
Bumps to v1.12.1.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Sidebar collapses to a 56px icon rail; hovering flies the full menu out as
an overlay (icons + titles/nested items). Language picker moved to Settings.
- Unify settings collapsibles to the app's standard card-collapse style:
Conversation, Read Aloud (drag-&-drop now inside), Try It Out, Casting panel.
- Read Aloud: reordered (settings → toolbar → document → transport/synth) and
the document fits the viewport height so controls below stay visible; remove
the redundant My Books card (lives in Library → Books).
- Conversation: stacked full-width config, fills viewport height; fix
intermittent webm decode in hands-free mode (recorder restarts cleanly,
in-browser WAV encode); barge-in via Live agent.
- Fix casting feed overflow that pushed the sidebar off-screen.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- Conversation Playground: STT/LLM/TTS/System prompt now full-width stacked.
- Fix conversation mic upload on ARM64: decode recording in-browser to
16 kHz mono WAV, bypassing server ffmpeg webm/EBML parser (with fallback).
- Document v1.10.0 (unified Library + character tags) and v1.10.1.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Restructure the sidebar into Voices / Speak / Setup groups and fuse the
Read Aloud and Script Rehearser features into one workspace:
- New combined Library section (Books · Theater Plays · Characters/Cast)
with cross-links (Rehearse a book, Read Aloud a play).
- Character tags like voice tags: one record, many productions, reusable
across books/scripts; seeded with origin book, editable in the editor.
- Shared cast resolution: opening a production fills empty cast slots from
the character roster (matched by book OR tag); voice choices written back
on save. Productions joined by normalized title (prodKey).
- Tags nav group for voices (distinct tags + counts, Cloned/Designed/Fav).
- Fold standalone Characters into Library; Read Aloud now a single entry.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Longer mixed DE/EN phrase covering dotted numbers, compound nouns,
umlauts, special characters, English technical vocabulary, time
formats and prose — reveals more of a voice's character per seed.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- voice-inspector: move `curGender` const before its first use — it was
declared at line 86 but referenced at line 61, causing a ReferenceError
(temporal dead zone) that silently aborted selectVoice() on every click
- Calc dB, Precompute, Batch Seeds now filter to checked voices when a
bulk selection is active, matching Benchmark's existing behaviour
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Auto-scroll to bottom is now gated on the user being within 80px of
the bottom. Scrolling up to review or edit a line freezes the feed
in place — new rows are still added, but the viewport doesn't move.
- Row-trimming is likewise suppressed while the user is scrolled up,
so old lines stay visible as long as they're being read/edited.
Trim limit raised from 80 → 600 rows so almost nothing is evicted.
- A floating "↓ Live" pill button appears at the bottom of the feed
whenever the user has scrolled up. Clicking it returns to the live
bottom and re-enables auto-scroll.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Casting view improvements:
- "LLM Reading…" row now shows a preview of the passage being processed.
A chevron button expands it to a full scrollable view of the passage
text (up to 260px), so you can follow what the LLM is reading live.
- Page-break dividers ("Page N") appear in the casting feed whenever the
source PDF page changes, giving a real-time view of page boundaries.
Bug fix:
- Page numbers in the Rehearser script were 0-indexed (PDF-internal) so
the first page break showed "Page 1" for what was PDF page 2, etc.
Now always emits 1-indexed page numbers (\f${page+1}).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
When a PDF audiobook is cast and saved to the Rehearser, page breaks now
carry the source PDF page number. In the Stage view each divider renders
as "— Page N —" instead of the generic "— Page break —".
Implementation:
- audiobook.js: `audiobookBuildScript()` encodes the page number in the
form-feed line (\fN instead of bare \f) at each page boundary.
- rehearser-parse.js: `parseScript()` now matches `line.startsWith('\f')`
and extracts the trailing page number into `line.page`.
- rehearser.js: `buildScriptPage()` renders "— Page N —" when `line.page`
is set; `toScript()` round-trips the number back (\fN) so it survives
save/reload; `importPDFScript()` also encodes page numbers (\f<pageIdx+1>)
when importing screenplay PDFs directly.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Exposes the `speed` parameter (0.5–2.0) on the TTS `/v1/audio/speech`
request so audio is generated at the target tempo natively via the
faster-qwen3-tts backend rather than post-processing.
- Backend: `/api/tts-preview` now extracts and forwards a `speed`
override (clamped 0.1–4.0) through the same extra-params mechanism
already used for seed/temperature; backends that reject it fall back
cleanly via `_post_tts_with_fallback`.
- Try it out: "Native Speed" number input (0.5–2, step 0.05) added to
the text card; value persists in localStorage per browser; passed as
`extra` through `createTtsAudioSource` and `generateChunkedTts`.
- Read aloud: "Native Speed" control added to the generation controls
row alongside seed/temperature; included in `readerGenParams()` and
saved/restored with library documents (each book tracks its own speed).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
audiobookScopeText now records PDF page boundaries as character offsets in the
scope text; audiobookBuildScript realigns each segment against the source and
emits \f page-break markers at the nearest boundary. Saved/opened cast scripts
keep the book's pagination instead of collapsing to one flow.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- Character sheets: stop sending the dead localhost:11434 default; fall back to
the server's configured llm_url so extraction uses the same working LLM.
- Audiobook casting: hoist highlightText to module scope so the "Review & cast"
manual-correction preview renders its segment rows again.
- Stage: unify narrator/dialog font size, add A-/A+ play text-size control
(scales A4 + paginated views), and make the cast chip list collapsible.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Add a persistent, book-scoped Character Library (new Characters section,
IndexedDB) that auto-fills from Character-sheet analysis with editable cards.
Enrich extraction with six narrative fields (backstory, relationships,
motivation, fears, mannerisms, voice/speech) plus the greyscale Good↔Evil
alignment bar, arc arrow, and 5-area Deep Analysis. Add ⋯ separators between
non-contiguous passages in Recast unknown, and harden dialogue attribution
against hallucination with same-language emotion tags.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
