Acoust REST API
Use the Acoust REST API to generate speech, list voices, and check API usage from your application or automation workflow. The API is in Beta; its contract may change.
Base URL
https://api.acoust.io/v1
Authentication
Send an API key in the Authorization header. The Acoust API-key control is currently hidden in the app, so do not expect to create or manage a key from the visible Developer page. If you do not already have API-key access, contact Acoust support to ask about availability. REST API requests use API keys; MCP uses a separate OAuth flow.
Authorization: Bearer YOUR_API_KEY
All request bodies are JSON and should include Content-Type: application/json.
Responses and errors
Successful responses use HTTP 200. Errors use this shape:
{
"error": {
"code": "invalid_request",
"message": "A required parameter is missing."
}
}
Swipe or scroll sideways to read all columns. With the table focused, use the left and right arrow keys.
| Status | Code | Meaning |
|---|---|---|
400 | invalid_request, voice_not_found, text_too_long | The request is invalid, the voice is unavailable, or the text exceeds a limit. |
401 | invalid_api_key | The API key is missing or invalid. |
402 | quota_exceeded | The account has no remaining generation quota. |
403 | plan_required | The account plan does not include this operation. |
429 | rate_limit_exceeded | The request rate limit was exceeded. |
500 | generation_failed | Speech generation failed or its outcome could not be confirmed. |
Successful generation responses and generation errors include a UUID request_id, generation_outcome, and quota_status; failed or uncertain 500 generation responses also set retry_safe: false. 400, 402, 403, and 429 generation errors do not include retry_safe. Errors that happen before the generation route, such as authentication failures, may not include these diagnostics. A 500, timeout, or disconnected response may have an unknown outcome and may consume quota. The API does not provide idempotency or result recovery. Do not automatically resubmit an uncertain request; a new request may generate audio and charge quota again.
Quota
REST generation shares the text-to-speech quota with the Acoust app. See GET /v1/usage for usage, remaining quota, scope, and reset time. Generating speech with a cloned voice counts twice the input text length against quota. The account billing cycle determines the reset; reset_at reports the current value when available.