feat(tts): add TTS buttons to PlanView and FilesView markdown preview with configurable input mode (#1443)

Add TTS controls to markdown preview surfaces so users can listen to plans
and markdown files directly from the preview toolbar.

Changes:
- Add read-aloud / stop buttons to PlanView markdown preview.
- Add read-aloud / stop buttons to FilesView markdown preview for markdown files.
- Respect the existing showMessageTTSButtons preference in both preview views.
- Add a persisted ttsInputMode setting with sanitized/raw modes.
- Keep sanitized mode as the default for backward compatibility.
- Allow raw markdown only for server TTS providers that can handle markdown.
- Always use sanitized text for browser and macOS say fallback paths.
- Add Voice Settings controls for TTS input mode.
- Add i18n keys for the new preview buttons and setting labels.
- Merge latest main and preserve newer FilesView toolbar/editor changes.

Validation:
- bun test packages/ui/src/stores/useConfigStore.test.ts packages/ui/src/components/chat/message/parts/ToolPart.test.ts packages/web/server/lib/tts/routes.test.js
- bun run type-check
- bun run lint
- git diff --check

---------

Co-authored-by: Bohdan Triapitsyn <artmore@protonmail.com>
This commit is contained in:
yangyaofei
2026-06-08 19:31:21 +03:00
committed by GitHub
co-authored by Bohdan Triapitsyn
parent a6bf73b245
commit ba95e13b36
21 changed files with 191 additions and 19 deletions
+7 -3
View File
@@ -35,6 +35,7 @@ export function useMessageTTS(): UseMessageTTSReturn {
const openaiCompatibleUrl = useConfigStore((state) => state.openaiCompatibleUrl);
const openaiCompatibleTtsModel = useConfigStore((state) => state.openaiCompatibleTtsModel);
const showMessageTTSButtons = useConfigStore((state) => state.showMessageTTSButtons);
const ttsInputMode = useConfigStore((state) => state.ttsInputMode);
const isServerProvider = voiceProvider === 'openai' || voiceProvider === 'openai-compatible';
const shouldCheckOpenAIAvailability = showMessageTTSButtons && isServerProvider;
@@ -64,7 +65,9 @@ export function useMessageTTS(): UseMessageTTSReturn {
setIsPlaying(true);
try {
const textToSpeak = sanitizeForTTS(text);
const shouldUseRaw = ttsInputMode === 'raw' && isServerProvider;
const sanitizedText = sanitizeForTTS(text);
const textToSpeak = shouldUseRaw ? text : sanitizedText;
if (isServerProvider && isServerTTSAvailable) {
const voice = voiceProvider === 'openai-compatible' ? openaiCompatibleVoice : openaiVoice;
@@ -83,7 +86,7 @@ export function useMessageTTS(): UseMessageTTSReturn {
});
} else if (voiceProvider === 'say' && isSayTTSAvailable) {
const wordsPerMinute = Math.round(100 + (speechRate - 0.5) * 200);
await speakSayTTS(textToSpeak, {
await speakSayTTS(sanitizedText, {
voice: sayVoice,
rate: wordsPerMinute,
onEnd: () => setIsPlaying(false),
@@ -94,7 +97,7 @@ export function useMessageTTS(): UseMessageTTSReturn {
await browserVoiceService.waitForVoices();
await browserVoiceService.resumeAudioContext();
await browserVoiceService.speakText(
textToSpeak,
sanitizedText,
navigator.language || 'en-US',
() => setIsPlaying(false),
{
@@ -123,6 +126,7 @@ export function useMessageTTS(): UseMessageTTSReturn {
openaiCompatibleTtsModel,
isServerTTSAvailable,
isSayTTSAvailable,
ttsInputMode,
speakServerTTS,
speakSayTTS,
stop,