Voice cloning on Venice — returns a JSON voice ID ({ id, model }), NOT audio. Upload a reference sample to mint a reusable voice, paid per request in USDC on Base via x402, no API key. Resolve a compatible TTS model from GET /api/v1/models?type=tts, then pass the returned id as `
| Network | Scheme | Amount | Pay To |
|---|---|---|---|
| Base | exact | $0.001000 USDC | 0xA7f3...4689 |
| solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp | exact | 0.00 tokens | 5hqrYC...hrKY |