Text-to-speech

POST

/v1/audio/speech

Synthesise speech from text using the OpenAI TTS API.
Returns raw audio bytes with the appropriate Content-Type header.

Request

Body Params application/jsonRequired

Examples

Responses

🟢200

audio/mpeg

Audio bytes

Headers

🟠400BadRequest

🟠401Unauthorized

🔴502ProviderError

🔴503Unavailable

Request Example

Shell

JavaScript

Java

Swift

curl --location '/v1/audio/speech' \
--header 'Content-Type: application/json' \
--data '{
    "provider": "bedrock",
    "model": "aws-polly",
    "input": "Hello from The Delegation",
    "voice": "Joanna",
    "response_format": "mp3"
}'

Response Example

400 - Example 1

{
    "error": {
        "message": "string",
        "type": "invalid_request_error",
        "code": "string",
        "request_id": "string"
    }
}

Modified at 2026-10-20 19:28:20

Transcribe audio with AWS Transcribe

Generate images with Gemini