voicecc 1.1.24 → 1.1.26
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +5 -3
- package/dashboard/dist/assets/index-Be2Vi14F.js +11 -0
- package/dashboard/dist/assets/{index-B906UGQq.css → index-CXkaHeKx.css} +1 -1
- package/dashboard/dist/index.html +2 -2
- package/dashboard/routes/providers.ts +15 -0
- package/init/defaults/system.md +8 -2
- package/package.json +2 -2
- package/server/services/tunnel.ts +2 -4
- package/server/voice/browser-server.ts +6 -1
- package/server/voice/twilio-server.ts +6 -1
- package/dashboard/dist/assets/index-B5gZCpYT.js +0 -11
package/README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Voice CC
|
|
2
2
|
|
|
3
|
-
A Claude Code
|
|
3
|
+
A Voice Agent Platform running on Claude Code. Create, manage, and deploy conversational voice agents powered by Claude, with real-time speech-to-text, text-to-speech, and voice activity detection via ElevenLabs.
|
|
4
4
|
|
|
5
5
|
## Project Structure
|
|
6
6
|
|
|
@@ -25,11 +25,13 @@ bin/ CLI entry point (voicecc command)
|
|
|
25
25
|
|
|
26
26
|
### Install
|
|
27
27
|
|
|
28
|
+
Sets up Cloudflared Quicktunnel (optional), protects installation with password (optional), and sets up your Elevenlabs API key.
|
|
29
|
+
|
|
28
30
|
```bash
|
|
29
31
|
# 1. Install Voice CC
|
|
30
32
|
npm install -g voicecc
|
|
31
33
|
|
|
32
|
-
# 2. Start the
|
|
34
|
+
# 2. Start the platform
|
|
33
35
|
voicecc
|
|
34
36
|
```
|
|
35
37
|
|
|
@@ -52,7 +54,7 @@ npm run dev:dashboard
|
|
|
52
54
|
2. **Voice activity detection**: Silero VAD v5 detects speech segments
|
|
53
55
|
3. **Speech-to-text**: ElevenLabs Scribe API transcribes audio
|
|
54
56
|
4. **Endpointing**: VAD silence-based turn detection
|
|
55
|
-
5. **Claude inference**: Transcript sent to Claude
|
|
57
|
+
5. **Claude inference**: Transcript sent to Claude Agent SDK session with streaming response
|
|
56
58
|
6. **Narration**: Claude's response stripped of markdown and split into sentences
|
|
57
59
|
7. **Text-to-speech**: ElevenLabs streaming TTS API generates audio
|
|
58
60
|
8. **Speaker playback**: Audio output through browser at 24kHz
|