MiniMax Speech-2.5 HD Preview API

The brand new HD model. Ultimate Similarity, Ultra-High Quality. Supports 40+ languages including Tamil, Hebrew, Swedish, etc.

Endpoint

POST https://api.hedra.com/v3/models/minimax-speech-25-hd-preview

Example request

curl -X POST "https://api.hedra.com/v3/models/minimax-speech-25-hd-preview" \
  -H "Authorization: Key $HEDRA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"input": {"prompt": "a cinematic shot of a city at dusk"}}'

Parameters

textstringrequired

Generation prompt. At most 9999 characters.

stabilitynumber

Voice stability. Higher values give a steadier, more consistent delivery; lower values allow more expressive variation between generations. From 0 to 1.

speednumber

Speech rate multiplier; 1.0 is the voice's natural pace. From 0.7 to 1.2.

languagestring

Language code; 'auto' by default.

voice_idstringrequired

Voice to speak with (`voice_<uuid>`). List valid voices at GET /v3/models/minimax-speech-25-hd-preview/voices.