Read Aloud (new "Vorlesen" tab):
- PDF (real page render + overlay highlight) / TXT reader with live word
highlighting, voice + speed, per-sentence synthesis-state colours, zoom
(fit-width/height, two-page, ±), resume, and a server-side book library
(syncs across devices; per-unit MP3 audio fetched on demand).
Book -> multi-speaker audiobook:
- "Cast as audiobook" attributes dialogue to characters via the LLM
(guillemet/quote-style aware, turn-taking, recent-context), with a
deterministic speech-tag fallback. Editable preview, non-blocking live
casting panel, then auto-saved as a reopenable Script Rehearser play.
- Audiobook export: synthesise every cast line -> one MP3 per chapter.
Character sheets:
- LLM-extracted, self-filling RPG-style sheets (with page+quote sources)
in both Read Aloud and the Rehearser.
Also: MP3 storage + per-page/sentence export, voice-library "Precompute
embeddings" pre-warm, German "Vorlesen" i18n + flag language toggle,
large-PDF performance (lazy raster, buffer/canvas eviction, yielded parse),
and the Seed Finder changelog entry.
New: routes/reader.py, POST /api/attribute-dialogue, POST /api/character-sheets,
static/js/{reader,audiobook,character-sheets}.js, static/sections/s-reader.html.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Adds a collapsible "🎲 Seed Finder" panel to the voice inspector pane.
Select a voice, expand the panel, set a seed range (default 1–15), and
click Run to generate audio samples with different seeds.
Each result row has Play and "Use this seed" buttons. "Use this seed"
saves the chosen seed to the faster-qwen3-tts voices.json via the new
/api/tts-voice-seed proxy endpoint (which calls /voice-seed on the TTS
server). The saved row gets a ✓ marker.
Test sentence auto-selects DE/EN mixed or EN-only based on voice name.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- voice_clone and streaming now return active library voices instead of
probing upstream /v1/models (which only exposed 8 model entries)
- Accept POST on /v1/audio/voices for clients that probe with POST
- Fall back to first active voice when voice field missing in /v1/audio/speech
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
## Script Rehearser (new feature)
- New section s-rehearser.html + rehearser.js + nav/loader wiring
- Phase 1: paste/upload script (.txt), auto-detect characters from
'CHARACTER: dialog' or ALL-CAPS screenplay format
- Phase 2: assign a TTS voice per character, or mark 'I play this'
- Phase 3: step-through rehearsal — synthesizes other characters via TTS,
shows level-meter + oscilloscope for your own lines, records them from mic
- Phase 4: session summary with per-line audio playback + download
## Connect Apps
- Removed duplicate standalone MCP/speak/hotkey full-width cards
- Kept the integration-grid cards (they use the real server URL from JS)
- Added Global Hotkey Daemon as a proper integration card with snippet-hotkey
populated by integrations.js (uses proxyBase URL dynamically)
## About page
- GET /api/changelog endpoint reads CHANGELOG.md and returns it as text
- Collapsible 'Changelog' <details> card fetches and displays it lazily
## Try It Out
- Reorganised into three cards: Voice & backend / Text to synthesize / Generate
- Backend help panel moved below the voice row (not in the same flex row)
- Style instruction field gains a dynamic badge ('style-aware ✓' / 'weak style')
and a yellow warning when a non-style-aware backend is selected while the
field is filled — wired to both backend-select change and input events
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Sentence text in typing bubble:
- Backend sends 'text' field with each audio SSE event (the sentence
being synthesised)
- Frontend audio queue stores {url, text} pairs
- playNextAudio() writes the sentence text into the '...' typing bubble
when LLM tokens haven't arrived yet (convCurrentSentenceBubble)
- convCurrentSentenceBubble cleared as soon as first LLM token arrives
so normal streaming takes over seamlessly
VAD noise fixes:
- VAD_THRESHOLD: 0.01 → 0.02 (background noise no longer counts as speech)
- VAD_MIN_REC_MS: 400 → 800ms (8/10s wait before silence detection starts,
gives user time to begin speaking without initial noise triggering send)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Speech gate (silence detection):
- vadHadSpeech flag: VAD auto-stop cancels without calling STT when no
speech was detected (fixes "[STT] No speech detected → gibberish" loop)
- cancelNextBlob flag: onstop skips processBlob when VAD cancels silently
- vadLastVoiceMs: gates preview transcription on actual detected speech
(prevents "reich" hallucination on initial silence chunks)
Hallucination filter:
- Client: HALLUCINATION_RE strips known Whisper phantoms from preview
- Server: _is_hallucination() in generate() treats "reich" / "danke" /
"thank you" etc. as "No speech detected" → never reaches LLM
Latency:
- VAD_SILENCE_MS: 1500 → 1000 ms (sends 500 ms sooner per turn)
- VAD_MIN_REC_MS: 500 → 400 ms
- MediaRecorder timeslice: 2500 → 1500 ms (preview text updates faster)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Replace serial LLM-wait-TTS with overlapped execution:
- LLM streams via background thread → asyncio.Queue (non-blocking event loop)
- _sentence_split() detects sentence boundaries in the token stream
- asyncio.create_task fires TTS for each sentence immediately — TTS for
sentence 1 runs while LLM is still generating sentences 2, 3, …
- Audio chunks stream to frontend in order as each task completes
- Time-to-first-audio drops from (LLM total + TTS total) to
roughly (LLM time-to-first-sentence + TTS latency for one sentence)
Frontend audio queue:
- enqueueAudio() / playNextAudio() chain multi-chunk responses seamlessly
- clearAudio() stops playback and cancels queue on new turn or mic click
- scheduleAutoMic() waits for queue to drain before restarting mic
- Error paths clear the queue to avoid stale audio playing after failure
Also fix missing contextlib import (silent bug when audio temp files
needed cleanup in the STT path).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Perceived startup speed:
- index.html: animated shimmer skeleton (header + toolbar + 8 voice cards)
visible immediately; fades out when loader.js finishes
- WaveSurfer (57KB) and MDI icon font (394KB woff2) now served from
static/vendor/ — removes 3 render-blocking external requests from <head>
- Flag-icons CSS loaded async (rel=preload onload trick) — non-blocking
loader.js:
- Fade out skeleton + remove from DOM (300ms transition)
- Reveal page-sections after JS finishes loading
Conversation playground:
- Qwen3 thinking mode fix: fall back to delta.reasoning_content when
delta.content is empty so think-only LLM turns produce visible output
- Better error message with /no-think hint when LLM returns empty
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
_AUDIO_EXTS lives in core.voice, not core.audio. The dead alias
'_VOICE_AUDIO_EXTS' was never used anywhere in the file.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
UploadFile | None = File(None) with from __future__ import annotations
caused FastAPI to still treat audio as required when omitted.
Changed to Optional[UploadFile] = None (no File() wrapper) so the
field is genuinely optional for text-input turns.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add VERSION file (1.1.0) at repo root
- core/constants.py: expose __version__ read from VERSION file
- routes/admin.py: GET /api/version endpoint returns {version}
- Settings → About: display "v1.1.0" next to app name via /api/version fetch
- CHANGELOG.md: full rewrite following Keep a Changelog + Semantic Versioning
- [Unreleased] staging section at top
- [1.1.0] 2026-05-29 — security, perf, refactor, UX changes from this session
- [1.0.0] 2026-05-28 — all pre-session features documented
- Compare links at bottom pointing to GitHub
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Frontend:
- Add pill-shaped text input + send button (→) to the left of the mic button
- Enter key or → click sends text directly without recording audio
- Input is disabled while a turn is processing; cleared on submit
- Welcome message updated to mention both input methods
- New CSS: .conv-input-bar, .conv-text-row, .conv-text-inp, .conv-send-btn,
.conv-divider (visual separator between text and mic sections)
Backend:
- /api/conversation/turn: audio is now optional (UploadFile | None)
- New text form field — when provided, STT step is skipped and text is
used as the transcript directly; SSE emits transcript event with stt_ms=null
- Raises 400 if neither audio nor text is supplied
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
