Voice & TTS

PocketPaw can convert text to speech using OpenAI’s TTS API or ElevenLabs.

Providers

OpenAI TTS

Terminal window
export POCKETCLAW_OPENAI_API_KEY="sk-..."
export POCKETCLAW_TTS_PROVIDER="openai"
export POCKETCLAW_TTS_VOICE="alloy"  # alloy, echo, fable, onyx, nova, shimmer

ElevenLabs

Terminal window
export POCKETCLAW_ELEVENLABS_API_KEY="your-key"
export POCKETCLAW_TTS_PROVIDER="elevenlabs"
export POCKETCLAW_TTS_VOICE="your-voice-id"

Usage

User: Read this article aloud: [article text]
Agent: [uses voice tool] → [audio file]

Tool Schema

{
  "name": "voice",
  "description": "Convert text to speech audio",
  "input_schema": {
    "type": "object",
    "properties": {
      "text": {
        "type": "string",
        "description": "Text to convert to speech"
      },
      "voice": {
        "type": "string",
        "description": "Voice to use (optional)"
      }
    },
    "required": ["text"]
  }
}

Policy Group

Belongs to group:voice. Also included in group:media.

Last updated: February 12, 2026
Edit this page