> ## Documentation Index
> Fetch the complete documentation index at: https://docs.neuralcleave.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Voice Overview

> NeuralCleave's local voice pipeline — wake word, VAD, STT, and TTS, all in-process.

NeuralCleave ships a complete, local voice pipeline. Unlike tools that bolt on a cloud STT plugin, the voice stack runs in the same Python process as the gateway.

## Pipeline

```
Microphone
    ↓
OpenWakeWord (wake word detection)
    ↓  on wake
Voice Activity Detection (VAD — energy or WebRTC)
    ↓  speech detected
faster-whisper (STT)
    ↓  transcript
NeuralCleave LLM pipeline (same as text chat)
    ↓  reply text
TTS (ElevenLabs → Kokoro → pyttsx3)
    ↓
Speaker output
```

With Ollama + Kokoro + faster-whisper: **zero external API calls**.

## Quick enable

```toml theme={null}
[voice]
stt = "whisper"
stt_model = "base"
tts_engine = "kokoro"
wake_word = "alexa"
continuous_voice_enabled = true   # required alongside wake_word — see Wake Word
```

Then restart the gateway. The Voice dashboard page at `/voice` shows live status.

## Voice modes

| Mode               | How to trigger                 | Use case                       |
| ------------------ | ------------------------------ | ------------------------------ |
| Wake word          | Say the wake word              | Hands-free, always-on          |
| Push-to-talk (PTT) | Hold the PTT button in the UI  | Low-latency, no false triggers |
| Continuous listen  | Toggle in the Voice page       | Voice-first workflows          |
| Microphone button  | Click mic icon in chat toolbar | One-shot voice input           |

## Subsystem availability

The Voice page in the dashboard shows the live status of each subsystem:

* **STT** — faster-whisper loaded and ready
* **TTS** — TTS backend configured
* **Wake Word** — detector active (amber pulse when listening)
* **PTT** — push-to-talk configured

## Next steps

<CardGroup cols={2}>
  <Card title="Wake Word" icon="tower-broadcast" href="/voice/wake-word">
    Configure OpenWakeWord — always-on detection.
  </Card>

  <Card title="Push-to-Talk" icon="phone" href="/voice/push-to-talk">
    PTT mode for low-latency, manual-trigger input.
  </Card>

  <Card title="Voice Providers" icon="microphone-lines" href="/voice/providers">
    Configure STT and TTS backends.
  </Card>
</CardGroup>