AI Voice Generator Agent Skill — Text to Speech via AI Pass API

This skill enables AI agents to convert text to speech audio using AI Pass TTS API.

Setup

1. Create AI Pass account: aipass.one — $1 free credit on signup
2. Get API key: Developer Dashboard → API Keys
3. Set env: export AIPASS_API_KEY="your-key"

API Reference

Endpoint: POST https://aipass.one/apikey/v1/audio/speech

Auth: Authorization: Bearer $AIPASS_API_KEY

Returns: Binary MP3 audio

Python Implementation

import os, requests

AIPASS_API_KEY = os.environ["AIPASS_API_KEY"]

def text_to_speech(
    text: str,
    voice: str = "nova",
    model: str = "tts-1",
    output_path: str = "output.mp3"
) -> str:
    """
    Convert text to speech and save as MP3.
    
    Args:
        text: Text to convert (max ~4000 chars per request)
        voice: alloy|echo|fable|onyx|nova|shimmer
        model: tts-1 (fast) or tts-1-hd (high quality)
        output_path: Where to save the MP3 file
    
    Returns:
        Path to saved MP3 file
    """
    response = requests.post(
        "https://aipass.one/apikey/v1/audio/speech",
        headers={
            "Authorization": f"Bearer {AIPASS_API_KEY}",
            "Content-Type": "application/json"
        },
        json={
            "model": model,
            "input": text,
            "voice": voice
        },
        timeout=60
    )
    
    if response.status_code != 200:
        raise Exception(f"TTS failed: {response.status_code} {response.text}")
    
    with open(output_path, "wb") as f:
        f.write(response.content)
    
    return output_path


# Example usage
if __name__ == "__main__":
    # Generate audio
    path = text_to_speech(
        text="Welcome to AI Pass. The universal AI wallet for all your artificial intelligence needs.",
        voice="nova",
        model="tts-1",
        output_path="welcome.mp3"
    )
    print(f"Audio saved to: {path}")

Bash / curl Example

curl -s -X POST https://aipass.one/apikey/v1/audio/speech \
  -H "Authorization: Bearer $AIPASS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "input": "Hello! This is a test of the AI Pass text-to-speech system.",
    "voice": "nova"
  }' --output output.mp3

echo "Saved to output.mp3"

Available Voices

Multilingual Support

The TTS API handles multilingual text automatically. Write in Spanish, French, Japanese — the voice adapts:

# Works in any language
text_to_speech(
    text="Bonjour, bienvenue sur AI Pass!",
    voice="fable",
    output_path="french_welcome.mp3"
)

Related Resources

• Live App: AI Voice Generator
• Build Your Own Voice Generator App
• AI Audio Transcriber — speech-to-text
• Developer Dashboard