voice-mcp-server 0.1.21 → 0.1.22
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 +1 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -65,7 +65,7 @@ The system is built on a highly modular adapter pattern configured via `hydra` Y
|
|
|
65
65
|
| | `kokoro_speaker` | High-quality, emotive local ML Text-to-Speech. |
|
|
66
66
|
| | `elevenlabs_speaker` | Premium cloud-based ultra-realistic voices. |
|
|
67
67
|
| **🎙️ Microphones** | `live_mic` | Direct hardware integration via PyAudio. |
|
|
68
|
-
| **🤫 VAD (Activity)** | `silero_vad` | Conversational mode powered by Silero, heavily optimized for 1-second barge-ins. |
|
|
68
|
+
| **🤫 VAD (Activity)** | `silero_vad` | Conversational mode powered by Silero, heavily optimized for 1-second barge-ins. *(Note: **Headphones are strictly required** for this mode to prevent the AI from hearing its own audio output and endlessly interrupting itself).* |
|
|
69
69
|
| | `ptt_vad` | Manual Push-to-Talk / Walkie-Talkie mode. **(Default: Hold 'Shift' to talk)** |
|
|
70
70
|
| **📝 STT (Transcription)**| `mlx_whisper_large_v3`| Blazing fast local transcription leveraging Apple's MLX framework. |
|
|
71
71
|
|