Generate speech
POST/v1/audio/speech
Converts text to audio with the speech provider of the model. proxium reserves the budget, builds the provider request and returns the audio bytes. The cache, failover and the timeout header do not apply to this route.
Request
Responses
- 200
- 400
- 401
- 402
- 403
- 413
- 415
- 429
- 500
- 502
- 503
The audio. The content-type is the one that the provider row sets, and audio/mpeg when it sets none.
The body is not valid JSON (plain text), the body has no model (missing_model), or no speech provider serves it or the key may not use it (no_route).
The bearer virtual key is missing (missing_key), or it is not valid or it is revoked (invalid_key).
The project may not send calls (subscription_required). proxium.tech is in open beta and does not return this answer.
A content rule of the project blocked the request (guardrail_blocked). The message names the class and the field. It never holds the matched value. proxium.tech has no content rule on for a project today.
The body is larger than the request body limit, 32 MiB on proxium.tech. The body of this answer is plain text.
The content-type is not application/json. The body of this answer is plain text.
The key or the source used its budget window (tenant_capped or source_capped, retry-after: 60), or the project reached a monthly cap (credits_exhausted, retry-after: 3600). No project on proxium.tech has a monthly cap during the open beta.
Response Headers
Seconds to wait before the next call.
The configuration of the provider names an unknown response shape (bad_shape).
The provider could not be reached (upstream_failed), answered with an error status (upstream_error), or sent an answer that proxium cannot read (bad_upstream_response).
The key store or the limits store is not available (keystore_unavailable, limits_unavailable). A deployment that refuses calls while its budget store is down answers budget_unavailable with retry-after: 5; proxium.tech lets the call through.
Response Headers
Seconds to wait before the next call.