Create speech
Convert text into a complete audio file using a voice of your choice.
Endpoint
Path parameters
Request body
Supported languages by model
Voice settings
Unsupported settings are silently ignored — they don’t error.Voice settings by model
Response
Default (include_phonemes=false): Binary audio in the body.
Content-Type: audio/wavoraudio/mpeg(matchesoutput_format).X-Audio-Lengthheader: duration of the generated audio in seconds.
include_phonemes=true: JSON body with base64 audio plus phoneme arrays.
Notes
textover 300 characters returns400. Use the Python or TypeScript SDK for automatic chunking, or split manually — see Long text.speedapplies afterduration. Settingduration=5withspeed=2produces ~10 seconds of audio.- When
styleis omitted, the first value in the voice’sstylesarray is used. Different voices can have different defaults — call Get voice to check.
See also
Docs: Create speech
Stream speech
Authorizations
Path Parameters
Body
The text to convert to speech
300The language code of the text
en, ko, ja, bg, cs, da, el, es, et, fi, hu, it, nl, pl, pt, ro, ar, de, fr, hi, id, ru, vi, hr, lt, lv, sk, sl, sv, tr, uk The style of character to use for the text-to-speech conversion
The model type to use for the text-to-speech conversion
sona_speech_1, sona_speech_2, sona_speech_2_flash, supertonic_api_1, supertonic_api_3 The desired output format of the audio file (wav, mp3). Default is wav.
wav, mp3 Return phoneme timing data with the audio
Pre-normalized text for TTS. Only used with sona_speech_2 and sona_speech_2_flash models.
Response
Returns either binary audio or JSON with phoneme data based on include_phonemes parameter
Binary audio file (when include_phonemes=false or omitted)