Skip to main content

​
How authentication works

MyVocal API uses a single header for authentication on every endpoint:

​
Where to get your API key

  1. Sign in to MyVocal Account.
  2. Open Account Info.
  3. Copy your API key.

​
Header format

​
string
required
API key used to authenticate your request.

​
Security best practices

  • Keep API keys on your backend server.
  • Do not expose API keys in frontend code or mobile apps.
  • Do not commit API keys to Git repositories.
  • Rotate key immediately if you suspect leakage.

​
Example request

​
Text-to-Music and Interpretation

Text-to-Music (/sound_clone/api/v1/music) and Interpretation (/sound_clone/api/v1/interpretation) use the same accessKey header, the same public host and the same API-key account as every other endpoint on this page. There is no separate key, scope, host or login for them. They do not require a cloned voice and do not require a browser/workspace session. The account that owns the key is always the owner of the resources it creates: no request body, path or query parameter can select a different owner. Requesting a resource you do not own and requesting one that does not exist return the same not-found error, so the API never reveals whether an identifier exists. Three differences from the synchronous endpoints are worth remembering:
  • Both products are asynchronous: they return a project/job identifier immediately and you poll for the result. See Async jobs, polling and retries.
  • The Idempotency-Key header is required on the create/accept endpoints. Use a unique printable ASCII value of 16–64 characters per distinct operation. Replaying the same key with the same body is safe; replaying it with a different body is a conflict.
  • Credits are measured in Characters and are quoted before they are spent. See Characters, quotes and billing.

Text-to-Music quickstart

Brief → arrangement → quote → generate → play/download.

Interpretation quickstart

Upload → probe → quote → generate → play → export/download.

​
Accent model requests

The Accent model (myvocal_v3_accent_enhance) reuses everything on this page: the same accessKey header, the same API host and the same TTS endpoints. There is no separate key, scope or endpoint to request, and no extra header to send.

Model selection

Public model IDs and how the default path, myvocal_v3 and the Accent model differ.

Voice discovery

Get a compatible voiceId with modelId=myvocal_v3_accent_enhance.

Quickstart

Authentication, voice discovery, synthesis and history in one flow.