Skip to content
Human Human

Voice Channel

Human supports real-time voice interaction through the built-in voice channel, enabling hands-free conversations with your AI assistant.

Overview

Section titled “Overview”

The voice channel provides:

  • Speech-to-text (STT) — converts spoken audio to text for processing
  • Text-to-speech (TTS) — reads responses aloud
  • WebSocket streaming — low-latency bidirectional audio
  • VAD (Voice Activity Detection) — automatic speech boundary detection

Configuration

Section titled “Configuration”

Enable voice in your config.json:

{
  "channels": {
    "voice": {
      "enabled": true,
      "stt_provider": "whisper",
      "tts_provider": "openai",
      "vad_threshold": 0.5,
      "sample_rate": 16000
    }
  }
}

Build Flag

Section titled “Build Flag”

Voice support is included by default. To explicitly enable:

Terminal window
cmake .. -DHU_ENABLE_VOICE=ON

Supported Providers

Section titled “Supported Providers”
ProviderSTTTTSNotes
OpenAI Whisper✓—Best accuracy
OpenAI TTS—✓Multiple voices
Deepgram✓—Low latency
ElevenLabs—✓Premium voices

Security

Section titled “Security”

Audio data is streamed directly to the configured provider and is not stored locally. All connections use TLS.