ORorthogonal
MiniMax

High-fidelity speech synthesis. Model fixed to speech-2.8-hd. Returns a downloadable audio URL (valid 24h) in data.audio; stream fixed to false.

Changed on
post/minimax-08853f/v1/t2a/speech-2.8-hd

Request

Request body

textstring required

Text to synthesize, under 10,000 characters. Supports <#x#> pause markers and interjection tags like (laughs).

voice_settingobject

{voice_id, speed [0.5,2], vol (0,10], pitch [-12,12], emotion}. Use a system voice_id such as English_expressive_narrator.

audio_settingobject

{sample_rate, bitrate, format (mp3|pcm|flac|wav|opus...), channel}.

language_booststring

Language hint, e.g. English, Chinese, or auto.

pronunciation_dictobject

Custom pronunciation overrides.

voice_modifyobject

Voice effects (pitch, intensity, timbre, sound_effects).

subtitle_enableboolean

Return a subtitle file URL.

Response

Successful response

Changes