Skip to content
English

Text to speech

POST https://api.nexinfer.com/v1/audio/speech

The request requires model, input, and voice. Current verified voices include:

Language Voice ID
Chinese zh_female_vv_uranus_bigtts
English en_female_jane_uranus_bigtts
Terminal window
curl https://api.nexinfer.com/v1/audio/speech \
-H "Authorization: Bearer $NEXINFER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-tts-2.0",
"input": "Welcome to NexInfer.",
"voice": "en_female_jane_uranus_bigtts",
"response_format": "mp3",
"speed": 1
}' \
--output speech.mp3

Supported response formats are mp3, wav, and opus. speed accepts 0.5 through 2.0, inclusive. An out-of-range speed returns 400 invalid_request and is not billed.

Billing is based on the accepted text character count. Check the HTTP status, file signature, duration, and usage log; do not rely on the file extension alone. Do not put keys or private input text in reports.