Files
openchamber/packages/ui/src/hooks/useMessageTTS.ts
T
gsxdsmandBohdan Triapitsyn 1ed5316ac7 feat(voice): add voice input/output support with multiple providers (#281)
* feat(voice): add voice input/output support with multiple providers

- Add BrowserVoiceButton component for Web Speech API voice input
- Add VoiceProvider context for managing voice state across the app
- Add TTS (Text-to-Speech) support with browser, macOS Say, and OpenAI providers
- Add message TTS buttons to read assistant messages aloud
- Add VoiceSettings page in OpenChamber settings
- Add server endpoints for TTS and summarization services
- Include slider component for voice rate/pitch/volume controls
- Add hidden session support for background voice operations
- Add Caddyfile for HTTPS support (required for microphone access)

* fix: Build errors fixed and removed outdated ElevenLabs test code.

* refactor(voice): use zen API with gpt-5-nano for TTS summarization

Replace the hidden session + OpenCode SDK approach with direct calls
to the opencode.ai zen API (same pattern used for commit message and
PR description generation).

- Rewrite summarization-service.js to call zen/v1/responses with gpt-5-nano
- Remove hidden session logic (hiddenSession.ts, sessionStore filtering)
- Remove summarizeModel setting and model selector from VoiceSettings
- Simplify client-side summarize.ts to no longer pass model params
- Clean up callers in useMessageTTS and useBrowserVoice

* fix(voice): remove false 'voice not supported' warning in settings

Mobile Safari does support voice but the isSupported check was
incorrectly flagging it. Remove the warning banner entirely.

* feat(voice): add configurable summary length limit for TTS output

Add a slider (50-2000 chars) in voice settings to control max summary
length. The limit is passed through the summarize endpoint and speak
endpoint to the zen API prompt, with token budget scaled accordingly.

* fix(voice): add diagnostic logging and sanitize TTS fallback

Add console logging throughout the summarization flow (client + server)
to trace why text may not be summarized. Fix silent error swallowing in
/api/tts/speak. Always apply sanitizeForTTS even when summarization is
disabled so raw markdown/code is never spoken verbatim.

* fix(voice): fix token budget starving model of output tokens

max_output_tokens includes both reasoning and output tokens. With
effort:'low', reasoning alone consumes ~128 tokens, so a budget of
100 left zero tokens for the actual summary text. Use a fixed 1000
token budget (matching commit message generation) and control output
length via the prompt's character limit instruction instead.

* chore(voice): remove diagnostic logging from summarization flow

* fix(voice): don't request mic permission on mobile page load

Remove the useEffect that pre-requested microphone permission when the
BrowserVoiceButton component mounted on mobile. This caused an unwanted
permission prompt immediately on page load before the user tapped the
mic icon. Permission is now only requested on explicit user interaction.

* fix(voice): remove unused BrowserVoiceButton binding

* fix(voice): desktop mic flow + non-continuous draft mode

* fix(voice): stabilize continuous loop and polish controls

* feat(settings): mark voice section experimental

---------

Co-authored-by: Bohdan Triapitsyn <artmore@protonmail.com>
2026-02-09 23:55:10 +02:00

128 lines
4.1 KiB
TypeScript

/**
* useMessageTTS Hook
*
* Hook for playing TTS on individual messages.
* Uses the configured voice provider (browser, OpenAI, or macOS Say).
*/
import { useCallback, useState } from 'react';
import { useConfigStore } from '@/stores/useConfigStore';
import { useServerTTS } from './useServerTTS';
import { useSayTTS } from './useSayTTS';
import { browserVoiceService } from '@/lib/voice/browserVoiceService';
import { summarizeText, shouldSummarize, sanitizeForTTS } from '@/lib/voice/summarize';
export interface UseMessageTTSReturn {
/** Whether TTS is currently playing for this message */
isPlaying: boolean;
/** Play the message text */
play: (text: string) => Promise<void>;
/** Stop playback */
stop: () => void;
}
export function useMessageTTS(): UseMessageTTSReturn {
const [isPlaying, setIsPlaying] = useState(false);
const {
voiceProvider,
speechRate,
speechPitch,
speechVolume,
sayVoice,
browserVoice,
openaiVoice,
summarizeMessageTTS,
summarizeCharacterThreshold,
} = useConfigStore();
const { speak: speakServerTTS, stop: stopServerTTS, isAvailable: isServerTTSAvailable } = useServerTTS();
const { speak: speakSayTTS, stop: stopSayTTS, isAvailable: isSayTTSAvailable } = useSayTTS();
const stop = useCallback(() => {
setIsPlaying(false);
stopServerTTS();
stopSayTTS();
browserVoiceService.cancelSpeech();
}, [stopServerTTS, stopSayTTS]);
const play = useCallback(async (text: string) => {
if (!text.trim()) return;
// Stop any existing playback
stop();
setIsPlaying(true);
try {
// Summarize text if enabled and over threshold
let textToSpeak = text;
if (summarizeMessageTTS && shouldSummarize(text, 'message')) {
textToSpeak = await summarizeText(text, {
threshold: summarizeCharacterThreshold,
});
} else {
// Still sanitize for TTS even when not summarizing
textToSpeak = sanitizeForTTS(text);
}
if (voiceProvider === 'openai' && isServerTTSAvailable) {
await speakServerTTS(textToSpeak, {
voice: openaiVoice,
speed: speechRate,
summarize: false, // We already summarized client-side
onEnd: () => setIsPlaying(false),
onError: () => setIsPlaying(false),
});
} else if (voiceProvider === 'say' && isSayTTSAvailable) {
const wordsPerMinute = Math.round(100 + (speechRate - 0.5) * 200);
await speakSayTTS(textToSpeak, {
voice: sayVoice,
rate: wordsPerMinute,
onEnd: () => setIsPlaying(false),
onError: () => setIsPlaying(false),
});
} else {
// Browser TTS
await browserVoiceService.waitForVoices();
await browserVoiceService.resumeAudioContext();
await browserVoiceService.speakText(
textToSpeak,
navigator.language || 'en-US',
() => setIsPlaying(false),
{
rate: speechRate,
pitch: speechPitch,
volume: speechVolume,
voiceName: browserVoice || undefined,
}
);
}
} catch (err) {
console.error('[useMessageTTS] Playback error:', err);
setIsPlaying(false);
}
}, [
voiceProvider,
speechRate,
speechPitch,
speechVolume,
sayVoice,
browserVoice,
openaiVoice,
summarizeMessageTTS,
summarizeCharacterThreshold,
isServerTTSAvailable,
isSayTTSAvailable,
speakServerTTS,
speakSayTTS,
stop,
]);
return {
isPlaying,
play,
stop,
};
}