# AiSpace Audio Voice Cloning Upload

> AiSpace Audio Voice Cloning Upload is a paid API for AI agents from x402.aispace.bot, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Uploads a sample audio file to clone or register a custom voice for use with a TTS model on the AiSpace/Venice.ai platform

## Facts

- Endpoint: POST https://x402.aispace.bot/api/v1/audio/voices
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/aispace-audio-voice-cloning-upload-50592d6a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_FqQvOYWjzESpb5TCvNhl2

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability aispace-audio-voice-cloning-upload-50592d6a -d '<json body>'
```

Example prompt: I want to clone my voice on AiSpace — upload this WAV file as a voice sample using the tts-chatterbox-hd model so I can use it for text-to-speech later.

## When to prefer this

Use this endpoint when you need to register a custom cloned voice on AiSpace (Venice.ai) for subsequent TTS generation. Prefer this over generic TTS endpoints when the user wants to use their own voice or a specific speaker's voice, and the target TTS model supports voice cloning (e.g. tts-chatterbox-hd).

## Known failure modes

- Invalid or unsupported audio file format — only WAV, MP3, M4A accepted
- Missing required 'model' query parameter pointing to a valid TTS model ID
- Audio file too large or corrupted
- Invalid TTS model ID not found in /api/v1/models?type=tts
- Payment not processed (x402 payment required at $0.001 USDC)
- Network timeout during audio file upload

## How this service works

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 `

## Output

A JSON object with an 'ok' boolean field indicating whether the voice sample was successfully uploaded and registered with the specified TTS model.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "file": {
   "type": "string",
   "format": "binary",
   "description": "Reference audio sample uploaded as multipart/form-data."
  },
  "model": {
   "type": "string",
   "description": "Venice TTS model id that supports cloning. See GET /api/v1/models?type=tts."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "id": "vv_aHR0cHM6Ly92M2IuZmFsLm1lZGlhL2ZpbGVzL2IvMGFhODhiMDMvVmVWUm9aNzlKWEhTR09ySHBFTjJkX3ZvaWNlLXNhbXBsZS53YXY",
  "model": "tts-chatterbox-hd"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/aispace-audio-voice-cloning-upload-50592d6a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.aispace.bot](https://www.zero.xyz/host/x402.aispace.bot/llms.txt)