diff --git a/CHANGELOG.md b/CHANGELOG.md
index d51bfaf..9e60377 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -5,6 +5,16 @@ Follows [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) · versioned wi
---
+## [1.20.8] — 2026-08-12
+
+### Added
+- **Fish Audio inline emotion-tag reference in Try It Out.** Selecting a Fish backend reveals a panel with all 49 documented tags (24 basic + 25 advanced); click any tag to insert it at the cursor, plus an "Insert example" button that loads a multi-emotion sample. Shown only for Fish, since it is the only engine that reads bracket tags from the text itself — other engines would speak "[happy]" aloud as literal words.
+
+### Fixed
+- **Fish-Speech showed "Fetched 0 voices" and was unusable from the UI.** It clones from the app's own saved WAV library, but was missing from the set of backends populated with those voices, so the code probed the Fish server for a voice-listing endpoint it does not have and got nothing. Now reports the full library (218 voices).
+- **Renamed the backend to "Fish Audio S2 Pro (Clone)"** — verified the running checkpoint is `fishaudio/s2-pro` at revision `1de9996b`, matching upstream HuggingFace exactly.
+- **Corrected Fish's advertised capabilities.** It was listed as `style_aware: true` with "Strong: emotion/tone markers … are honoured per request" — measured to be wrong while cloning. With a reference clip, S2-Pro prepends it as an in-context example and imitates its prosody, which overwhelms inline tags: identical text showed a 10x loudness spread across emotions with no reference, but only 1.2x with one ([screaming] vs [whisper] was inaudible). Every lever was tested — canonical tags, free-form descriptions, repeated and mid-sentence tags, temperature to 1.0, truncated references, `reference_id` vs inline. The backend is now billed on what it does well: deterministic, byte-reproducible cloning.
+
## [1.20.6] — 2026-08-11
### Fixed
diff --git a/VERSION b/VERSION
index e63679c..95393fc 100644
--- a/VERSION
+++ b/VERSION
@@ -1 +1 @@
-1.20.6
+1.20.8
diff --git a/routes/tts.py b/routes/tts.py
index b1b0f38..eaf419a 100644
--- a/routes/tts.py
+++ b/routes/tts.py
@@ -80,7 +80,7 @@ def _backend_display_name(backend: str, url: str) -> str:
"kokoro": "Kokoro FastAPI (82M)",
"vibevoice": "VibeVoice TTS",
"xtts": "XTTS v2",
- "fishspeech": "Fish-Speech (Clone + Emotion)",
+ "fishspeech": "Fish Audio S2 Pro (Clone)",
}
port = _backend_port_label(url)
return f"{port} {names.get(backend, backend)}" if port else names.get(backend, backend)
@@ -168,12 +168,22 @@ def _backend_capabilities(backend: str) -> dict:
"uses_wav": False, "style_aware": False, "true_streaming": False,
"speed": "~0.3× GPU", "latency": "1–3 s", "quality": "High", "ram": "~5 GB",
},
+ # Measured live against this exact checkpoint (fishaudio/s2-pro, rev 1de9996b):
+ # inline [tag] emotion markers work well ONLY when no reference audio is sent.
+ # With a reference (i.e. whenever cloning a library voice) S2-Pro prepends the
+ # clip as an in-context example and imitates its prosody, which overwhelms the
+ # tags: identical text scored a 10× loudness spread across emotions with no
+ # reference, but only 1.2× with one — [screaming] vs [whisper] was inaudible.
+ # Every lever was tried (canonical tags, free-form descriptions, repeated and
+ # mid-sentence tags, temperature up to 1.0, 3s truncated references,
+ # reference_id vs inline). So this backend is billed on what it actually does
+ # well: rock-solid deterministic cloning, not per-line emotion.
"fishspeech": {
- "purpose": "Clone a saved WAV voice AND control per-line tone via inline emotion markers.",
- "identity": "Clones the selected voice's reference WAV — consistent speaker identity across lines.",
- "style": "Strong: emotion/tone markers like (angry), (whispering), (excited) are honoured per request.",
- "best_for": "Consistent character voices that still react to tone changes — ideal for the Rehearser.",
- "uses_wav": True, "style_aware": True, "true_streaming": False,
+ "purpose": "Clone a saved WAV voice with byte-identical, reproducible output.",
+ "identity": "Excellent — clones the selected voice's reference WAV and is fully deterministic (same input always yields the same audio).",
+ "style": "Weak while cloning: inline [tag] markers are overwhelmed by the reference clip's own delivery. Tone follows the reference, so the emotion of the reference recording is what you hear.",
+ "best_for": "Consistent character voices and resumable bulk exports, where identical re-runs matter more than per-line emotion.",
+ "uses_wav": True, "style_aware": False, "true_streaming": False,
"speed": "~0.4× GPU", "latency": "1–4 s", "quality": "Premium", "ram": "~4 GB",
},
}
@@ -369,7 +379,12 @@ def _active_library_voice_options(settings: dict) -> list[dict]:
def _fetch_backend_voices(settings: dict, backend: str) -> list:
backend = _clean_preview_backend(backend)
- if backend in {"voice_clone", "streaming", "nvidia_zeroshot", "nvidia_flow"}:
+ # Fish-Speech clones from the app's own saved WAV library (see
+ # _fishspeech_request_audio, which resolves the voice via _find_voice_audio) and
+ # exposes no voice-listing endpoint of its own. Without it in this set the
+ # probe below found nothing and reported voice_count 0, so the Engines page
+ # listed it with no selectable voices even while the server was healthy.
+ if backend in {"voice_clone", "streaming", "nvidia_zeroshot", "nvidia_flow", "fishspeech"}:
return _active_library_voice_options(settings)
tts_url = _validate_http_url(_preview_backend_base_url(settings, backend), allow_private=True).rstrip("/")
key = (settings.get("voice_design_api_key") if backend == "voice_design" else settings.get("tts_api_key")) or ""
diff --git a/static/dist/main.min.js b/static/dist/main.min.js
index e2202aa..e0eddd4 100644
--- a/static/dist/main.min.js
+++ b/static/dist/main.min.js
@@ -738,7 +738,17 @@ This warms each voice so the engine caches its .pt and first playback is instant
- `;const close=()=>{ov.remove(),document.removeEventListener("keydown",onKey)};function onKey(e){e.key==="Escape"&&close()}ov.addEventListener("click",e=>{e.target===ov&&close()}),ov.querySelector(".vl-bdc-cancel").addEventListener("click",close),document.addEventListener("keydown",onKey),ov.querySelector(".vl-bdc-go").addEventListener("click",async()=>{const goBtn=ov.querySelector(".vl-bdc-go"),cancelBtn=ov.querySelector(".vl-bdc-cancel");goBtn.disabled=cancelBtn.disabled=!0;let done=0,errors=0;await runPool(ids,async id=>{try{(await fetch(`/api/voice/${encodeURIComponent(id)}`,{method:"DELETE"})).ok?done++:errors++}catch{errors++}},5,n=>{goBtn.innerHTML=` Deleting ${n}/${ids.length}\u2026`}),close(),toast(`Deleted ${done} voice${done!==1?"s":""}${errors?` (${errors} errors)`:""}`,errors?"error":"success"),_bulkSelected.clear(),await loadVoiceLibrary()}),document.body.appendChild(ov),ov.querySelector(".vl-bdc-cancel").focus()}async function _bulkSetEnabled(ids,enabled){let done=0;for(const id of ids)await saveMeta(id,{enabled}).catch(()=>{}),done++;return done}function backendVoiceId(value){return typeof value=="string"?value:(value==null?void 0:value.id)||(value==null?void 0:value.voice)||(value==null?void 0:value.name)||JSON.stringify(value)}function shouldFilterBackendVoices(backend){return["voice_clone","streaming","nvidia_zeroshot","nvidia_flow"].includes(backend||"")}function shouldReplaceWithLibraryVoices(backend){return backend==="voice_design"}async function activeLibraryVoiceIds(){return _voices.length||await loadVoiceLibrary(),new Set((_voices||[]).filter(v=>v.enabled!==!1).map(v=>v.id))}function cleanReferenceText(text){return String(text||"").trim()}function selectedPreviewLibraryVoice(){var _a2;const id=((_a2=$("tts-voice-select"))==null?void 0:_a2.value)||"";return id?(_voices||[]).find(v=>v.id===id):null}function previewVoiceWarnings(v){var _a2;const warnings=[],backend=backendById(((_a2=$("tts-backend-select"))==null?void 0:_a2.value)||"");backend&&backend.id&&!["voice_clone","streaming","nvidia_zeroshot","nvidia_flow"].includes(backend.id)&&warnings.push(backend.id==="nvidia_magpie"?"NVIDIA Magpie uses fixed speaker voices, not saved WAV clone identity.":"This backend may follow style/model voice more than the saved WAV identity."),backend&&backend.id==="nvidia_zeroshot"&&v.duration&&(Number(v.duration)<3||Number(v.duration)>10)&&warnings.push("NVIDIA Zeroshot works best with a clear 3-10 second prompt."),backend&&backend.id==="nvidia_flow"&&!v.transcript&&warnings.push("NVIDIA Flow requires the exact saved reference transcript for this voice."),v.transcript||warnings.push("No reference transcript is saved; cloned identity is harder to judge."),v.duration&&(Number(v.duration)<3||Number(v.duration)>20)&&warnings.push("Reference clip length is outside the 3-20 second sweet spot."),v.needs_tts_restart&&warnings.push("This voice changed since the last backend refresh; restart or clear restart flags before judging it.");const healthWarnings=v.health&&Array.isArray(v.health.warnings)?v.health.warnings:[];return warnings.push(...healthWarnings.slice(0,3)),warnings}function updatePreviewVoiceMatchPanel(){const panel=$("preview-match-panel");if(!panel)return;const v=selectedPreviewLibraryVoice();if(!v){panel.hidden=!0;return}panel.hidden=!1;const lang=v.language||v.lang||(v.id||"").split("_")[0]||"-",gender=v.gender||(v.id||"").split("_")[1]||"-",db=fmtDbfs(v),dur=v.duration?fmtDuration(v.duration):"-";$("preview-match-title").textContent=v.id,$("preview-match-detail").textContent=`${lang} \xB7 ${gender} \xB7 ${dur} \xB7 ${db} dBFS`;const warnings=previewVoiceWarnings(v);$("preview-match-warning").textContent=warnings.length?warnings.join(" "):"For a fair voice match check, play the WAV and synthesize the exact saved reference text.";const transcript=cleanReferenceText(v.transcript||"");$("preview-match-transcript").textContent=transcript||"No reference text saved for this voice.",$("preview-ref-use-text").disabled=!transcript,$("preview-ref-synth").disabled=!transcript;const audio=$("preview-ref-audio"),expected=voiceFileUrl(v);audio.dataset.src!==expected&&(audio.pause(),audio.src=expected,audio.dataset.src=expected);const actionsEl=panel.querySelector(".preview-match-actions");let personaBtn=panel.querySelector(".preview-persona-btn");v.persona?personaBtn||(personaBtn=document.createElement("button"),personaBtn.className="btn-secondary preview-persona-btn",personaBtn.type="button",personaBtn.textContent="Rewrite with persona",actionsEl==null||actionsEl.appendChild(personaBtn),personaBtn.addEventListener("click",async()=>{const text=$("preview-text-area").value.trim();if(!text){toast("Enter text to rewrite","error");return}const lv=selectedPreviewLibraryVoice();if(!(lv!=null&&lv.persona)){toast("This voice has no persona","error");return}personaBtn.disabled=!0,personaBtn.textContent="Rewriting\u2026";try{const llmUrl=localStorage.getItem("refine-llm-url")||(_appSettings==null?void 0:_appSettings.llm_url)||"http://localhost:11434/v1",r=await fetch("/api/rewrite-with-persona",{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify({text,persona:lv.persona,llm_url:llmUrl,model:(_appSettings==null?void 0:_appSettings.llm_model)||"",mode:"rewrite"})});if(!r.ok){const e=await r.json().catch(()=>({}));throw new Error(e.detail||r.statusText)}const d=await r.json();$("preview-text-area").value=d.text,toast("Text rewritten in persona style","success")}catch(e){toast("Persona rewrite failed: "+e.message,"error")}finally{personaBtn.disabled=!1,personaBtn.textContent="Rewrite with persona"}})):personaBtn==null||personaBtn.remove();const personaToggle=$("preview-persona-toggle");if(personaToggle){const label=personaToggle.closest("label");v.persona?(personaToggle.disabled=!1,label&&(label.title="Rewrite text through this voice's character persona before generating")):(personaToggle.checked=!1,personaToggle.disabled=!0,label&&(label.title="This voice has no character persona saved \u2014 set one on the Voice Inspector page first."))}}async function synthesizeSelectedReferenceText(){const v=selectedPreviewLibraryVoice();if(!v){toast("Select a library voice first","error");return}let text=cleanReferenceText(v.transcript||"");if(!text){toast("This voice has no reference text","error");return}if(v.needs_tts_restart){if(!confirm("This voice is marked as needing a TTS restart. If you already restarted the backend, clear the flag and synthesize anyway?"))return;await clearTtsRestartFlags(),v.needs_tts_restart=!1,updatePreviewVoiceMatchPanel()}const backend=$("tts-backend-select").value;if(!backend){toast("No available TTS backend","error");return}const btn=$("preview-ref-synth");btn.disabled=!0;try{$("preview-text-area").value=text;const source=await createTtsAudioSource(v.id,text,backend,$("preview-playback-mode").value,$("preview-style-instruction").value.trim());previewBlob=source.blob;const audio=$("preview-audio");audio.src=source.url,audio.style.display="",await audio.play(),$("save-preview-mp3-btn").disabled=!1,$("save-preview-btn").disabled=source.streaming,toast(source.streaming?"Reference text streaming":"Reference text synthesized","success")}catch(e){toast("Reference synthesis failed: "+e.message,"error")}finally{btn.disabled=!1}}$("fetch-tts-voices-btn").addEventListener("click",async()=>{var _a2;$("fetch-tts-voices-btn").disabled=!0;try{const backend=(_a2=$("tts-backend-select"))==null?void 0:_a2.value;if(!backend)throw new Error("No available TTS backend");let ids;if(shouldReplaceWithLibraryVoices(backend))_voices.length||await loadVoiceLibrary(),ids=(_voices||[]).filter(v=>v.enabled!==!1).map(v=>v.id);else{const rawVoices=await fetch("/api/tts-voices?backend="+encodeURIComponent(backend)).then(r=>r.json());let voices=Array.isArray(rawVoices)?rawVoices:[];if(shouldFilterBackendVoices(backend)){const activeIds=await activeLibraryVoiceIds();voices=voices.filter(v=>activeIds.has(backendVoiceId(v)))}ids=voices.map(backendVoiceId)}const sel=$("tts-voice-select"),prev=sel.value;window.VoicePicker?(VoicePicker.upgrade("tts-voice-select"),VoicePicker.populate("tts-voice-select",ids),prev&&ids.includes(prev)&&VoicePicker.setValue("tts-voice-select",prev)):(sel.innerHTML='',ids.forEach(id=>{const o=document.createElement("option");o.value=o.textContent=id,sel.appendChild(o)}),prev&&ids.includes(prev)&&(sel.value=prev)),updatePreviewVoiceMatchPanel();const suffix=shouldFilterBackendVoices(backend)||shouldReplaceWithLibraryVoices(backend)?" active voices":" voices";toast("Fetched "+ids.length+suffix,"success")}catch(e){toast("Fetch failed: "+e.message,"error")}finally{$("fetch-tts-voices-btn").disabled=!1}});function _ttsIsFishBackend(id){return/fish/i.test(id||"")}function _ttsApplyEmotionTag(text,emotionValue){var _a2;const backend=((_a2=$("tts-backend-select"))==null?void 0:_a2.value)||"";if(!_ttsIsFishBackend(backend)||!emotionValue||/^\s*\[/.test(text))return text;const tag=typeof _rehEmotionEnglishTag=="function"?_rehEmotionEnglishTag(emotionValue):"";return tag?`[${tag}] ${text}`:text}setTimeout(function(){const sel=$("preview-emotion-select");!sel||typeof window.REH_EMOTIONS=="undefined"||(window.REH_EMOTIONS.forEach(e=>{if(!e.value)return;const o=document.createElement("option");o.value=e.value,o.textContent=`${e.emoji} ${e.label}`,sel.appendChild(o)}),sel.addEventListener("change",()=>{var _a2;const backend=((_a2=$("tts-backend-select"))==null?void 0:_a2.value)||"",help=$("preview-emotion-help");if(_ttsIsFishBackend(backend))help&&(help.style.display=sel.value?"block":"none",help.textContent=sel.value?"Applied as an inline [tag] in the text for Fish-Speech \u2014 the style instruction field below is ignored by this backend.":"");else{help&&(help.style.display="none");const styleInput=$("preview-style-instruction");styleInput&&sel.value&&(styleInput.value=sel.value)}}))},0),$("tts-backend-select").addEventListener("change",()=>{var _a2;const sel=$("tts-voice-select");sel.innerHTML='',updateBackendHelp(),updatePreviewVoiceMatchPanel(),previewBlob=null,$("save-preview-mp3-btn").disabled=!0,$("save-preview-btn").disabled=!0,(_a2=$("preview-emotion-select"))==null||_a2.dispatchEvent(new Event("change"))}),$("tts-voice-select").addEventListener("change",updatePreviewVoiceMatchPanel),$("preview-ref-play").addEventListener("click",async()=>{updatePreviewVoiceMatchPanel();const audio=$("preview-ref-audio");try{await audio.play()}catch(e){toast("Reference playback failed: "+e.message,"error")}}),$("preview-ref-use-text").addEventListener("click",()=>{const v=selectedPreviewLibraryVoice(),text=cleanReferenceText((v==null?void 0:v.transcript)||"");if(!text){toast("This voice has no reference text","error");return}$("preview-text-area").value=text,toast("Reference text copied to target text","success")}),$("preview-ref-synth").addEventListener("click",synthesizeSelectedReferenceText);let _ttsStreamHealth=null;function effectiveTtsPlaybackMode(override="settings"){return override&&override!=="settings"?override:_appSettings.tts_stream_mode||"auto"}async function isTtsStreamAvailable(force=!1){if(_ttsStreamHealth&&!force)return _ttsStreamHealth.ok;try{return _ttsStreamHealth=await fetch("/api/tts-stream-health").then(r=>r.json()),!!_ttsStreamHealth.ok}catch{return _ttsStreamHealth={ok:!1},!1}}async function createTtsStreamUrl(voice,text,instruct=""){if(!await isTtsStreamAvailable())throw new Error("streaming backend unavailable");const r=await fetch("/api/tts-stream-session",{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify({text,voice,instruct})});if(!r.ok){const e=await r.json().catch(()=>({}));throw new Error(e.detail||r.statusText)}return(await r.json()).url}async function _ttsPreviewFetchWithRetry(body,tries){tries=tries||3;for(let i=1;i<=tries;i++)try{return await fetch("/api/tts-preview",{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify(body)})}catch(e){if(i===tries)throw e;await new Promise(r=>setTimeout(r,2500*i))}}function _ttsBackendForVoice(voiceId,fallbackBackend){if(!voiceId||voiceId==="me")return fallbackBackend;const v=(window._voices||[]).find(x=>x.id===voiceId);return v&&!v.has_ref?"voice_design":fallbackBackend}async function fetchTtsPreviewBlob(voice,text,responseFormat="wav",instruct="",backend="voice_clone",applyPersona=!1,extra=null){const body={text,voice,response_format:responseFormat,instruct,backend};applyPersona&&(body.apply_persona=!0),extra&&typeof extra=="object"&&Object.assign(body,extra);const r=await _ttsPreviewFetchWithRetry(body);if(!r.ok){const e=await r.json().catch(()=>({}));throw new Error(e.detail||r.statusText)}const blob=await r.blob();if(responseFormat==="wav"){const v=(window._voices||[]).find(x=>x.id===voice),gainDb=v&&v.loudness&&typeof v.loudness.gain_db=="number"?v.loudness.gain_db:0;if(gainDb)try{const nr=await fetch("/api/audio/apply-gain?gain_db="+encodeURIComponent(gainDb),{method:"POST",body:blob});if(nr.ok)return await nr.blob()}catch{}}return blob}function _textWords(s){return String(s||"").toLowerCase().normalize("NFKD").replace(/[̀-ͯ]/g,"").replace(/[^\p{L}\p{N}\s]/gu," ").split(/\s+/).filter(Boolean)}function _textSimilarity(a,b){const wa=_textWords(a),wb=_textWords(b);if(!wa.length&&!wb.length)return 1;if(!wa.length||!wb.length)return 0;const counts=new Map;wa.forEach(w=>counts.set(w,(counts.get(w)||0)+1));let overlap=0;return wb.forEach(w=>{const c=counts.get(w);c&&(overlap++,counts.set(w,c-1))}),2*overlap/(wa.length+wb.length)}async function _voiceRoundtripCheck(voiceId,text,backend,instruct=""){const blob=await fetchTtsPreviewBlob(voiceId,text,"wav",instruct,backend),fd=new FormData;fd.append("file",blob,"roundtrip.wav"),fd.append("backend","configured");const r=await fetch("/api/transcribe-bytes",{method:"POST",body:fd});if(!r.ok){const e=await r.json().catch(()=>({}));throw new Error(e.detail||r.statusText)}const d=await r.json();return{transcript:d.text||"",score:_textSimilarity(text,d.text||""),blob}}async function createTtsAudioSource(voice,text,backend="voice_clone",modeOverride="settings",instruct="",applyPersona=!1,extra=null){const mode=effectiveTtsPlaybackMode(modeOverride);if(backend!=="streaming"||mode==="buffered"){const blob=await fetchTtsPreviewBlob(voice,text,"wav",instruct,backend,applyPersona,extra);return{url:URL.createObjectURL(blob),blob,streaming:!1,label:"buffered"}}try{return{url:await createTtsStreamUrl(voice,text,instruct),blob:null,streaming:!0,label:"streaming"}}catch(e){if(mode==="streaming")throw e;const blob=await fetchTtsPreviewBlob(voice,text,"wav",instruct,backend,applyPersona,extra);return{url:URL.createObjectURL(blob),blob,streaming:!1,label:"buffered"}}}let previewBlob=null;const PREVIEW_SAMPLE_TEXT="Hello! This is a voice preview from TTS Voice Creator - Clone and Design.";$("preview-text-area").addEventListener("focus",()=>{$("preview-text-area").value===PREVIEW_SAMPLE_TEXT&&($("preview-text-area").value="")},{once:!0});function _onPreviewGenerated(source,voice,text,backend,instruct){typeof effectsSourceBlob!="undefined"&&(window._effectsSourceBlob=null),window._effectsSynthArgs={voice,text,instruct:instruct||"",backend};const ea=$("effects-apply-btn");ea&&(ea.disabled=!1);const ap=$("add-to-playlist-btn");ap&&source.blob&&(ap.disabled=!1),typeof historyPush=="function"&&source.blob&&historyPush(voice,text,backend,source.blob,source.url)}const _TRYOUT_SPEED_KEY="ttsvc_tryout_native_speed";(function(){const saved=localStorage.getItem(_TRYOUT_SPEED_KEY);if(saved){const el=$("preview-native-speed");el&&(el.value=saved)}})(),(_R=$("preview-native-speed"))==null||_R.addEventListener("change",function(){localStorage.setItem(_TRYOUT_SPEED_KEY,this.value)}),$("preview-btn").addEventListener("click",async()=>{var _a2,_b2,_c2,_d2;const voice=$("tts-voice-select").value,backend=$("tts-backend-select").value,instruct=$("preview-style-instruction").value.trim(),text=_ttsApplyEmotionTag($("preview-text-area").value.trim(),(_a2=$("preview-emotion-select"))==null?void 0:_a2.value),applyPersona=((_b2=$("preview-persona-toggle"))==null?void 0:_b2.checked)||!1;if(!backend){toast("No available TTS backend","error");return}if(!voice){toast("Select a TTS voice","error");return}if(!text){toast("Enter preview text","error");return}$("preview-btn").disabled=!0,$("save-preview-mp3-btn").disabled=!0,$("save-preview-btn").disabled=!0,$("add-to-playlist-btn")&&($("add-to-playlist-btn").disabled=!0),$("effects-apply-btn")&&($("effects-apply-btn").disabled=!0);const _nspd=parseFloat((_c2=$("preview-native-speed"))==null?void 0:_c2.value),_extra=!isNaN(_nspd)&&_nspd!==1?{speed:_nspd}:null;try{const audio=$("preview-audio"),source=((_d2=$("preview-chunked-toggle"))==null?void 0:_d2.checked)&&text.length>200&&typeof generateChunkedTts=="function"?await generateChunkedTts(voice,text,backend,instruct,_extra,applyPersona):await createTtsAudioSource(voice,text,backend,$("preview-playback-mode").value,instruct,applyPersona,_extra);previewBlob=source.blob,window._previewVoice=voice,window._previewBackend=backend,window._previewText=text,audio.src=source.url,audio.style.display="",await audio.play(),$("save-preview-mp3-btn").disabled=!1,$("save-preview-btn").disabled=source.streaming,_onPreviewGenerated(source,voice,text,backend,instruct),toast(source.streaming?"Streaming preview playing":source.label==="chunked"?`Chunked (${text.length} chars) playing`:"Preview playing","success")}catch(e){toast("TTS failed: "+e.message,"error")}finally{$("preview-btn").disabled=!1}}),$("save-preview-mp3-btn").addEventListener("click",async()=>{var _a2;const voice=$("tts-voice-select").value,backend=$("tts-backend-select").value,instruct=$("preview-style-instruction").value.trim(),text=_ttsApplyEmotionTag($("preview-text-area").value.trim(),(_a2=$("preview-emotion-select"))==null?void 0:_a2.value);if(!backend){toast("No available TTS backend","error");return}if(!voice||!text)return;const btn=$("save-preview-mp3-btn");btn.disabled=!0;try{const blob=await fetchTtsPreviewBlob(voice,text,"mp3",instruct,backend),a=document.createElement("a");a.href=URL.createObjectURL(blob),a.download=(voice||"preview")+"_preview.mp3",a.click(),toast("MP3 saved","success")}catch(e){toast("MP3 save failed: "+e.message,"error")}finally{btn.disabled=!1}}),$("save-preview-btn").addEventListener("click",()=>{if(!previewBlob)return;const a=document.createElement("a");a.href=URL.createObjectURL(previewBlob),a.download=($("tts-voice-select").value||"preview")+"_preview.wav",a.click()});const PERF_HISTORY_KEY="vcf-perf-history",PERF_HISTORY_MAX=50,PERF_HISTORY_SORT={key:"ts",dir:"desc"};function perfHistoryLoad(){try{return JSON.parse(localStorage.getItem(PERF_HISTORY_KEY)||"[]")}catch{return[]}}function perfHistorySave(entries){try{localStorage.setItem(PERF_HISTORY_KEY,JSON.stringify(entries.slice(-PERF_HISTORY_MAX)))}catch{}}function perfHistoryAdd(entry){const h=perfHistoryLoad();h.push(entry),perfHistorySave(h)}function perfSparklineSvg(rtfValues){if(!rtfValues.length)return"";const W=120,H=32,PAD=2,barW=Math.max(4,Math.floor((W-PAD*2)/rtfValues.length)-1),maxV=Math.max(...rtfValues,1),bars=rtfValues.map((v,i)=>{const bh=Math.max(3,Math.round(v/maxV*(H-PAD*2))),x=PAD+i*(barW+1),y=H-PAD-bh,col=v<1?"var(--green)":"var(--yellow)";return``}).join("");return``}function perfHistoryVoiceLookup(voiceId){return(Array.isArray(window._voices)&&window._voices.length?window._voices:typeof _voices!="undefined"&&Array.isArray(_voices)?_voices:[]).find(v=>v&&(v.id===voiceId||v.name===voiceId||v.voice_id===voiceId))||null}function perfHistoryVoiceMeta(entry){var _a2,_b2,_c2;const voice=(entry==null?void 0:entry.voice)||"",saved=(entry==null?void 0:entry.voiceMeta)||{},lib=perfHistoryVoiceLookup(voice)||{},language=saved.lang||saved.language||(entry==null?void 0:entry.lang)||(entry==null?void 0:entry.language)||lib.lang||lib.language||"",gender=String(saved.gender||(entry==null?void 0:entry.gender)||lib.gender||"").trim().toUpperCase().charAt(0);return{id:voice,label:saved.label||saved.display_name||(entry==null?void 0:entry.voiceLabel)||lib.display_name||lib.name||voice,lang:language,gender:["F","M","N"].includes(gender)?gender:"",flag:saved.flag||(entry==null?void 0:entry.flag)||lib.flag||"",avatar:saved.avatar||(entry==null?void 0:entry.avatar)||lib.avatar||"",hasPicture:!!((_c2=(_b2=(_a2=saved.has_picture)!=null?_a2:saved.hasPicture)!=null?_b2:entry==null?void 0:entry.hasPicture)!=null?_c2:lib.has_picture)}}function perfHistoryExtraFields(voice,backend){const lib=perfHistoryVoiceLookup(voice)||{};return{voiceMeta:{label:lib.display_name||lib.name||voice,lang:lib.lang||lib.language||"",gender:lib.gender||"",flag:lib.flag||"",avatar:lib.avatar||"",has_picture:!!lib.has_picture},device:typeof backendComputeDevice=="function"?backendComputeDevice(backend):""}}function perfHistoryGenderLabel(gender){return{F:"Female",M:"Male",N:"Diverse"}[gender]||""}function perfHistoryDeviceLabel(entry){return(entry==null?void 0:entry.device)||(typeof backendComputeDevice=="function"?backendComputeDevice((entry==null?void 0:entry.backend)||""):"")||"Unknown"}function perfHistoryDeviceHtml(entry){const label=perfHistoryDeviceLabel(entry),cls=typeof backendComputeDeviceClass=="function"?backendComputeDeviceClass((entry==null?void 0:entry.backend)||""):label.toLowerCase().includes("gpu")?"gpu":label.toLowerCase().includes("cpu")?"cpu":"";return`${escHtml(label)}`}function perfHistoryAvatarHtml(entry){var _a2;const meta=perfHistoryVoiceMeta(entry),title=meta.label||meta.id||"Voice";if(meta.hasPicture)return``;const icon=window.voiceAvatarIcon?window.voiceAvatarIcon(meta.avatar,24):null;if(icon)return`${icon.replace(/vp-avatar/g,"perf-history-avatar-icon")}`;const color=typeof avatarColor=="function"?avatarColor(meta.lang||meta.id||title):"#6b7280",init=((_a2=(title||"?").trim()[0])==null?void 0:_a2.toUpperCase())||"?";return`${escHtml(init)}`}function perfHistorySortValue(entry,key){switch(key){case"backend":return String(entry.backend||"").toLowerCase();case"language":return String(perfHistoryVoiceMeta(entry).lang||"").toLowerCase();case"gender":return String(perfHistoryGenderLabel(perfHistoryVoiceMeta(entry).gender)||"").toLowerCase();case"voice":return String(entry.voice||"").toLowerCase();case"device":return String(perfHistoryDeviceLabel(entry)||"").toLowerCase();case"avgLatencyMs":return Number(entry.avgLatencyMs);case"minLatencyMs":return Number(entry.minLatencyMs);case"avgRtf":return Number(entry.avgRtf);case"ts":default:return Number(entry.ts)}}function perfHistoryCompare(a,b){const av=perfHistorySortValue(a,PERF_HISTORY_SORT.key),bv=perfHistorySortValue(b,PERF_HISTORY_SORT.key);let result=0;if(typeof av=="string"||typeof bv=="string")result=String(av).localeCompare(String(bv),void 0,{numeric:!0,sensitivity:"base"});else{const an=Number.isFinite(av)?av:-1/0,bn=Number.isFinite(bv)?bv:-1/0;result=an===bn?0:an-bn}return PERF_HISTORY_SORT.dir==="asc"?result:-result}function perfHistoryHeadButton(key,label){const active=PERF_HISTORY_SORT.key===key,icon=active?PERF_HISTORY_SORT.dir==="asc"?"mdi-arrow-up":"mdi-arrow-down":"mdi-swap-vertical";return`