The Voho API covers speech, agents, and the endpoints that read something rather than say it. Every endpoint lives under one base URL, takes the same bearer token, and draws down the same credit balance.

​
Authentication

Every request needs an API token in the Authorization header.
Tokens are created in the Voho console and begin with voho_sk_live_.
The plaintext token is shown once, at creation. Only its hash is stored, so a lost token cannot be recovered. Create a new one and revoke the old. Revoking takes effect immediately.
A missing, malformed, or revoked token returns 401:

​
Endpoints

Everything the console can do is reachable here, billed from the same balance, with the same error codes.

​
Response headers

Every response carries X-Voho-Engine. Successful synthesis calls add the details of what was produced:
X-Voho-Characters and X-Voho-Cost-Cents let you track spend per request without a separate usage call. Log them alongside your own request IDs.

​
Credits

One balance funds every endpoint. Each is billed for the thing it produces, and the cost of each call comes back in X-Voho-Cost-Cents. Cost is rounded up, so a very short request still costs at least one cent. The text utilities are free. They neither synthesise nor read anything. When the balance reaches zero, every billable endpoint returns 402:
Streaming calls are billed after the stream finishes, so a synthesis that fails partway is not charged.

​
Errors

Errors are JSON with a stable code and a human-readable message. Branch on code, never on message.
See Errors for the full list.

​
Limits

  • Synthesis: 5,000 characters per request. Longer text returns text_too_long, split it into sentences and concatenate the audio.
  • Uploads: 8 MB. Documents are PDF, PNG, JPEG or WebP; audio is WAV, MP3, OGG, WebM or FLAC, up to 60 seconds.
  • Files go up as multipart/form-data with the file attached, or as JSON with a base64 file and a mime_type. Both are accepted everywhere a file is.

Synthesise speech

The core endpoint.

Browse voices

Find a voice by dialect.