Voice Production AI Public API

The Voice Production AI API lets you integrate text-to-speech generation, voice cloning, and voice browsing into your applications.

Base URL: https://api.voiceproductionai.com/v1

Authentication

All /v1 endpoints require an API key. Create one from Settings → API Keys in the dashboard.

Pass the key as a Bearer token:

curl https://api.voiceproductionai.com/v1/voices \
  -H "Authorization: Bearer vk_live_<your-key>"

API keys are workspace-scoped. The Scale plan is required to access the public API.

Voices

List voices

GET /v1/voices

Returns all voices available to your workspace (presets + cloned).

Response

{
  "items": [
    {
      "id": "uuid",
      "name": "Emma",
      "kind": "preset",
      "language": "en",
      ...
    }
  ]
}

Generations

Create a generation

POST /v1/generations

Request body

{
  "voiceId": "uuid",
  "script": "Hello, world!",
  "format": "mp3",
  "settings": {
    "speed": 1.0,
    "pitchSemitones": 0
  }
}

Response 202 Accepted

{
  "id": "uuid",
  "status": "queued",
  "estimatedCredits": 1
}

Get generation status

GET /v1/generations/:id

Response

{
  "id": "uuid",
  "status": "ready",
  "durationSec": 3,
  "downloadUrl": "https://...",
  "createdAt": "2025-01-01T00:00:00Z",
  "completedAt": "2025-01-01T00:00:05Z"
}

Status values: queued, running, enhancing, ready, failed.

Poll until status === "ready", then use the signed downloadUrl (valid 10 minutes).

Voice Cloning

Clone a voice

POST /v1/voices/clone

Request body

{
  "samplePaths": ["uploads/sample1.wav", "uploads/sample2.wav"]
}

Response 202 Accepted

{
  "id": "uuid",
  "status": "queued"
}

Requires Pro or Scale plan. Upload samples first using the Upload API.

Webhooks

Events

Event	Fired when
`generation.ready`	A generation completes successfully
`generation.failed`	A generation fails
`voice.cloned`	A voice clone job completes

Verifying webhook signatures

Every delivery includes a X-Voiceproductionai-Signature header:

X-Voiceproductionai-Signature: sha256=<hmac-hex>

Verify with your endpoint's secret:

const crypto = require('crypto');
function verifySignature(body, secret, signatureHeader) {
  const expected = 'sha256=' + crypto
    .createHmac('sha256', secret)
    .update(body)
    .digest('hex');
  return crypto.timingSafeEqual(
    Buffer.from(signatureHeader),
    Buffer.from(expected)
  );
}

Payload envelope

{
  "event": "generation.ready",
  "timestamp": "2025-01-01T00:00:00.000Z",
  "data": { ... }
}

Rate limits

Plan	Limit
Scale	60 requests / minute / workspace

When exceeded, the API returns 429 Too Many Requests with a retryAfter: 60 field.

Error codes

HTTP	Code	Meaning
401	`unauthorized`	Missing or invalid API key
402	`insufficient_credits`	Not enough credits
403	`public_api_requires_scale`	Scale plan required
403	`cloning_requires_paid_plan`	Pro/Scale required for cloning
404	`not_found`	Resource not found
429	`rate_limit_exceeded`	Rate limit hit

All error responses follow the shape:

{ "error": "error_code" }