d8dfun/claudecodeui
1
0
Fork 0
mirror of https://github.com/siteboon/claudecodeui.git synced 2026-06-25 20:25:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat(voice): add optional speech-to-text input and read-aloud TTS

Browse Source 
Adds a push-to-talk mic button in the composer and a read-aloud button on
assistant messages. Both are opt-in and hidden unless a voice backend is
configured via VOICE_SIDECAR_URL.

The auth-gated /api/voice proxy forwards to a configurable backend exposing
/transcribe and /tts (provider-agnostic); the frontend probes /api/voice/health
and hides the controls when disabled. Adds i18n keys and docs/voice.md.

Includes a local, no-API-key reference backend in voice-sidecar/ (faster-whisper
for STT, Kokoro-82M for TTS, both CPU-capable).
This commit is contained in:
newsbubbles
2026-06-08 00:47:14 +01:00
parent af3a28abc7
commit d05585e1f4
17 changed files with 720 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
server/index.js
View File

@@ -72,6 +72,7 @@ import userRoutes from './routes/user.js';
import geminiRoutes from './routes/gemini.js';
import pluginsRoutes from './routes/plugins.js';
import providerRoutes from './modules/providers/provider.routes.js';
import voiceRoutes from './voice-proxy.js';
import { startEnabledPluginServers, stopAllPlugins, getPluginPort } from './utils/plugin-process-manager.js';
import { initializeDatabase, projectsDb, sessionsDb } from './modules/database/index.js';
import { configureWebPush } from './services/vapid-keys.js';
@@ -204,6 +205,8 @@ app.use('/api/providers', authenticateToken, providerRoutes);
// Agent API Routes (uses API key authentication)
app.use('/api/agent', agentRoutes);
app.use('/api/voice', authenticateToken, voiceRoutes);
// Serve public files (like api-docs.html)
app.use(express.static(path.join(APP_ROOT, 'public')));