Convert text into audio for narration, announcements, and voiceovers.
Request
| Item | Description |
|---|---|
| Method | POST |
| Path | /v1/audio/speech |
| Gateway URL | https://ailink.nativex.com |
| Authentication | Authorization: Bearer sk-xxxx; replace the placeholder with your API Key |
| Request format | application/json |
Replace MODEL_ID with a model from the Model Marketplace that supports this endpoint. Available models, parameters, and permissions depend on your account.
Parameters
| Parameter | Location | Type | Required | Description |
|---|---|---|---|---|
model |
Body | string | Yes | A model that supports speech synthesis |
input |
Body | string | Yes | Text to read aloud. Legacy TTS endpoints accept up to 4096 characters; other models have their own limits. |
voice |
Body | string | Yes | Voice. Legacy TTS voices include alloy, echo, fable, onyx, nova, and shimmer; other models may differ. |
response_format |
Body | string | No | mp3, opus, aac, flac, wav, or pcm. Legacy endpoints default to mp3. |
speed |
Body | number | No | Speech speed. The legacy range is 0.25–4, with a default of 1. Support depends on the model. |
Example
curl -X POST 'https://ailink.nativex.com/v1/audio/speech' \
-H 'Authorization: Bearer sk-xxxx' \
-H 'Content-Type: application/json' \
-d '{
"model": "MODEL_ID",
"input": "Welcome to AiLink.",
"voice": "alloy",
"response_format": "mp3"
}' \
--output 'speech.mp3'
Response
On success, the response contains binary file data. The --output option above saves the result to a local file. Do not parse it as JSON.
| Field or result | Description |
|---|---|
| Audio file | Save in the format specified by response_format |
Error handling
For unsuccessful responses, check the HTTP status and error body first. Verify the API Key, model name, account balance, and parameters. If rate limited, reduce concurrency and retry later.