t2a_v2 API — GoModel
translates the standard /v1/audio/speech endpoint into that dialect for you.
Configure
config.yaml:
MINIMAX_BASE_URL overrides the endpoint (default
https://api.minimax.io/v1); accounts on the China platform should set it to
https://api.minimaxi.com/v1.
Temperature
MiniMax requirestemperature in (0.0, 1.0] and rejects zero. GoModel clamps
a zero or negative temperature to 1.0 so OpenAI-style requests that pin
temperature: 0 keep working.
Text-to-speech
POST /v1/audio/speech is translated to MiniMax’s synchronous
t2a_v2
API and the hex-encoded audio is decoded back to binary:
voicetakes a MiniMax voice ID (for exampleEnglish_expressive_narrator), not an OpenAI voice name likealloy.response_formatsupportsmp3(default),wav,flac, andpcm.speedsupports0.5–2.0(default1.0).
/models listing, so add
them to the configured model list to make them routable:
Not supported by MiniMax
All of these returninvalid_request_error rather than silently dropping the
option:
- Speech
instructions(pick a voice ID that matches the style you want). - Speech
response_formatvalues other thanmp3/wav/flac/pcmandspeedoutside0.5–2.0. - Speech-to-text — MiniMax has no transcription API, so
/v1/audio/transcriptionsis rejected. - Realtime voice-to-voice — MiniMax’s conversational realtime schema is not
OpenAI-compatible, so it is not exposed at
/v1/realtime.