> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/b1ink0/vassist/llms.txt
> Use this file to discover all available pages before exploring further.

# Voice Features

> Configure text-to-speech (TTS) and speech-to-text (STT) for voice interactions

VAssist supports voice-based interactions through text-to-speech (TTS) for AI responses and speech-to-text (STT) for voice input.

## Text-to-Speech (TTS)

### Enable TTS

<ParamField path="ttsConfig.enabled" type="boolean" default="false">
  Master toggle for text-to-speech functionality.

  When enabled, AI responses are spoken aloud using the configured TTS provider.
</ParamField>

### TTS Providers

VAssist supports three TTS providers:

<Tabs>
  <Tab title="Kokoro (Default)">
    **Local, high-quality neural TTS**

    Kokoro-JS runs entirely in your browser using WebAssembly and WebGPU. No API keys or internet required.

    **Advantages**:

    * Free and private
    * Natural-sounding voices
    * Fast generation with WebGPU
    * No API costs
    * Works offline
  </Tab>

  <Tab title="OpenAI TTS">
    **Cloud-based premium voices**

    Uses OpenAI's text-to-speech API for professional-quality voices.

    **Advantages**:

    * Extremely natural voices
    * Consistent quality
    * Multiple voice options
    * Fast cloud processing

    **Requires**: OpenAI API key and credits
  </Tab>

  <Tab title="OpenAI-Compatible">
    **Custom TTS endpoints**

    Connect to any OpenAI-compatible TTS API (self-hosted or third-party).

    **Use cases**:

    * Self-hosted TTS servers
    * Custom voice models
    * Alternative TTS services
  </Tab>
</Tabs>

## Kokoro TTS Configuration

<ParamField path="ttsConfig.provider" type="string" default="kokoro">
  Set to `kokoro` for local browser-based TTS.
</ParamField>

### Voice Selection

<ParamField path="ttsConfig.kokoro.voice" type="string" default="af_heart">
  Choose from 24+ high-quality voices.

  **American Female (af\_)**:

  * `af_heart` - Warm and friendly (default)
  * `af_alloy` - Clear and professional
  * `af_aoede` - Expressive storyteller
  * `af_bella` - Youthful and energetic
  * `af_jessica` - Confident and articulate
  * `af_kore` - Calm and soothing
  * `af_nicole` - Neutral professional
  * `af_nova` - Bright and engaging
  * `af_river` - Smooth and natural
  * `af_sarah` - Friendly conversational
  * `af_sky` - Light and airy

  **American Male (am\_)**:

  * `am_adam` - Deep and authoritative
  * `am_echo` - Resonant and clear
  * `am_eric` - Warm and approachable
  * `am_fenrir` - Strong and powerful
  * `am_liam` - Youthful and friendly
  * `am_michael` - Professional narrator
  * `am_onyx` - Rich and smooth
  * `am_puck` - Playful and energetic
  * `am_santa` - Jolly and warm

  **British Female (bf\_)**:

  * `bf_alice` - Refined British accent
  * `bf_emma` - Clear and elegant
  * `bf_isabella` - Sophisticated
  * `bf_lily` - Gentle and warm

  **British Male (bm\_)**:

  * `bm_daniel` - Distinguished British
  * `bm_fable` - Narrative storyteller
  * `bm_george` - Classic British
  * `bm_lewis` - Modern British
</ParamField>

### Performance Options

<ParamField path="ttsConfig.kokoro.device" type="string" default="auto">
  Backend for TTS processing.

  * **`auto`**: Auto-detect (WebGPU if available, else WASM)
  * **`webgpu`**: GPU acceleration (2-10x faster, requires compatible GPU)
  * **`wasm`**: CPU fallback (universal compatibility)

  <Info>
    WebGPU provides significantly faster generation but requires a compatible GPU. Auto mode automatically falls back to WASM if WebGPU is unavailable.
  </Info>
</ParamField>

<ParamField path="ttsConfig.kokoro.speed" type="number" default="1.0">
  Speech rate multiplier.

  * **Range**: 0.5 - 2.0
  * **0.5-0.8**: Slower, clearer speech
  * **1.0**: Normal speed (recommended)
  * **1.2-2.0**: Faster speech
</ParamField>

<ParamField path="ttsConfig.kokoro.keepModelLoaded" type="boolean" default="true">
  Keep the TTS model loaded in memory.

  * **Enabled**: Faster subsequent generations, uses \~150-300MB RAM
  * **Disabled**: Slower but frees memory between uses
</ParamField>

### Advanced Settings

<ParamField path="ttsConfig.kokoro.modelId" type="string" default="onnx-community/Kokoro-82M-v1.0-ONNX">
  Hugging Face model identifier for Kokoro.

  Default model is optimized for quality and performance.
</ParamField>

<ParamField path="ttsConfig.chunkSize" type="number" default="500">
  Maximum characters per TTS chunk.

  * Larger chunks: Fewer API calls, more continuous speech
  * Smaller chunks: Lower latency, faster first audio
</ParamField>

<ParamField path="ttsConfig.minChunkSize" type="number" default="100">
  Minimum characters before creating a chunk.

  Prevents extremely short audio segments.
</ParamField>

## OpenAI TTS Configuration

<ParamField path="ttsConfig.provider" type="string">
  Set to `openai` for OpenAI's TTS service.
</ParamField>

<ParamField path="ttsConfig.openai.apiKey" type="string" required>
  Your OpenAI API key.

  <Warning>
    Keep your API key secure. It's stored locally and never shared.
  </Warning>
</ParamField>

<ParamField path="ttsConfig.openai.model" type="string" default="tts-1">
  OpenAI TTS model.

  * **`tts-1`**: Standard quality, faster, lower cost
  * **`tts-1-hd`**: High-definition quality, slower, higher cost
</ParamField>

<ParamField path="ttsConfig.openai.voice" type="string" default="nova">
  OpenAI voice selection.

  Available voices:

  * **`alloy`**: Neutral, balanced
  * **`echo`**: Male, clear
  * **`fable`**: British male, expressive
  * **`onyx`**: Deep male voice
  * **`nova`**: Female, friendly (default)
  * **`shimmer`**: Female, warm
</ParamField>

<ParamField path="ttsConfig.openai.speed" type="number" default="1.0">
  Speech rate (0.5 - 2.0).
</ParamField>

## OpenAI-Compatible TTS

<ParamField path="ttsConfig.provider" type="string">
  Set to `openai-compatible` for custom endpoints.
</ParamField>

<ParamField path="ttsConfig['openai-compatible'].endpoint" type="string" default="http://localhost:8000" required>
  TTS API endpoint URL.

  Must be compatible with OpenAI's TTS API format.
</ParamField>

<ParamField path="ttsConfig['openai-compatible'].apiKey" type="string">
  API key for the custom endpoint (if required).
</ParamField>

<ParamField path="ttsConfig['openai-compatible'].model" type="string" default="tts">
  Model name or identifier for the TTS service.
</ParamField>

<ParamField path="ttsConfig['openai-compatible'].voice" type="string" default="default">
  Voice name supported by your TTS service.
</ParamField>

<ParamField path="ttsConfig['openai-compatible'].speed" type="number" default="1.0">
  Speech rate multiplier.
</ParamField>

## Speech-to-Text (STT)

### Enable STT

<ParamField path="sttConfig.enabled" type="boolean" default="false">
  Master toggle for speech-to-text functionality.

  When enabled, users can dictate messages using the microphone button.
</ParamField>

### STT Providers

<Tabs>
  <Tab title="Chrome AI Multimodal">
    **Free, local transcription**

    Uses Chrome's built-in multimodal AI for speech recognition.

    **Requirements**:

    * Chrome 138+
    * Multimodal Input flag enabled

    **Advantages**:

    * Free and private
    * Works offline
    * No API costs
    * Fast processing
  </Tab>

  <Tab title="OpenAI Whisper">
    **Cloud-based transcription**

    OpenAI's Whisper API for high-accuracy speech recognition.

    **Advantages**:

    * Excellent accuracy
    * Multilingual support
    * Punctuation and formatting

    **Requires**: OpenAI API key
  </Tab>

  <Tab title="OpenAI-Compatible">
    **Custom STT endpoints**

    Self-hosted Whisper or alternative STT services.

    **Use cases**:

    * Local Whisper deployment
    * Privacy-focused setups
    * Custom speech models
  </Tab>
</Tabs>

## Chrome AI STT Configuration

<ParamField path="sttConfig.provider" type="string" default="chrome-ai-multimodal">
  Set to `chrome-ai-multimodal` for Chrome's built-in STT.
</ParamField>

<ParamField path="sttConfig['chrome-ai-multimodal'].temperature" type="number" default="0.1">
  Transcription randomness (0.0 - 2.0).

  Lower values are recommended for transcription accuracy.
</ParamField>

<ParamField path="sttConfig['chrome-ai-multimodal'].topK" type="number" default="3">
  Token selection diversity (1 - 128).
</ParamField>

<ParamField path="sttConfig['chrome-ai-multimodal'].outputLanguage" type="string" default="en">
  Transcription language.

  Supported: `en`, `es`, `ja`
</ParamField>

## OpenAI STT Configuration

<ParamField path="sttConfig.provider" type="string">
  Set to `openai` for Whisper API.
</ParamField>

<ParamField path="sttConfig.openai.apiKey" type="string" required>
  OpenAI API key.
</ParamField>

<ParamField path="sttConfig.openai.model" type="string" default="whisper-1">
  Whisper model name.

  Currently only `whisper-1` is available via API.
</ParamField>

<ParamField path="sttConfig.openai.language" type="string" default="en">
  Input audio language (ISO 639-1 code).

  Examples: `en`, `es`, `fr`, `de`, `ja`, `zh`

  <Info>
    Specifying the language improves accuracy and reduces latency.
  </Info>
</ParamField>

<ParamField path="sttConfig.openai.temperature" type="number" default="0">
  Transcription sampling temperature.

  * **0**: Deterministic, most accurate
  * **0.1-0.5**: Slight variability
</ParamField>

## OpenAI-Compatible STT

<ParamField path="sttConfig.provider" type="string">
  Set to `openai-compatible`.
</ParamField>

<ParamField path="sttConfig['openai-compatible'].endpoint" type="string" default="http://localhost:8000" required>
  STT API endpoint.
</ParamField>

<ParamField path="sttConfig['openai-compatible'].apiKey" type="string">
  API key (if required).
</ParamField>

<ParamField path="sttConfig['openai-compatible'].model" type="string" default="whisper">
  Model name.
</ParamField>

<ParamField path="sttConfig['openai-compatible'].language" type="string" default="en">
  Transcription language.
</ParamField>

<ParamField path="sttConfig['openai-compatible'].temperature" type="number" default="0">
  Sampling temperature.
</ParamField>

## Recording Settings

<ParamField path="sttConfig.recordingFormat" type="string" default="webm">
  Audio recording format.

  * **`webm`**: Widely supported, good compression
  * **`mp4`**: Alternative format
  * **`wav`**: Uncompressed, larger files
</ParamField>

<ParamField path="sttConfig.maxRecordingDuration" type="number" default="60">
  Maximum recording length in seconds.

  Prevents excessively long recordings and API timeouts.
</ParamField>

<ParamField path="sttConfig.audioDeviceSwitchDelay" type="number" default="300">
  Delay (ms) when switching audio devices.

  Allows hardware to stabilize before recording.
</ParamField>

## Using Voice Mode

### Voice Input

1. **Enable STT** in settings
2. **Click the microphone icon** in the chat input
3. **Speak your message** (up to max duration)
4. **Click stop** or wait for silence detection
5. Message is transcribed and ready to send

### Voice Output

1. **Enable TTS** in settings
2. AI responses are automatically spoken
3. **Adjust speed** in TTS settings if needed
4. **Change voice** to match your preference

### Voice Conversation Mode

<Info>
  Enable both TTS and STT for a fully voice-based conversation experience:

  1. Speak your question → STT transcribes
  2. AI processes and responds
  3. TTS reads the response aloud
  4. Repeat for natural voice interaction
</Info>

## Troubleshooting

<AccordionGroup>
  <Accordion title="Kokoro TTS not working">
    **Check**:

    1. Browser supports WebAssembly
    2. Sufficient memory available (\~300MB for model)
    3. No browser extensions blocking WASM
    4. Try switching device from `webgpu` to `wasm`

    **WebGPU issues**: If GPU acceleration fails, auto mode falls back to WASM automatically.
  </Accordion>

  <Accordion title="OpenAI TTS/STT errors">
    **Common issues**:

    * Invalid API key
    * Insufficient credits
    * Rate limiting (reduce request frequency)
    * Model name typo

    Check OpenAI dashboard for quota and usage.
  </Accordion>

  <Accordion title="Chrome AI STT unavailable">
    **Verify**:

    1. Chrome 138+ installed
    2. Multimodal Input flag enabled (`chrome://flags`)
    3. Chrome restarted after enabling flag
    4. Microphone permission granted
  </Accordion>

  <Accordion title="Microphone not working">
    **Steps**:

    1. Grant microphone permission in browser
    2. Check system audio settings
    3. Test microphone in browser settings
    4. Ensure no other app is using the mic
    5. Try a different browser if persistent
  </Accordion>

  <Accordion title="Audio playback issues">
    **Check**:

    1. Browser audio not muted
    2. System volume turned up
    3. No headphone detection issues
    4. Try different audio output device
    5. Check browser console for errors
  </Accordion>
</AccordionGroup>