Speech

Method	Path
`POST`	`/v1/audio/speech`

The request is JSON (OpenAI {input, voice}) and the response body is binary audio returned with the upstream Content-Type.

Check public_protocols first. speech-2.8-hd / speech-2.8-turbo offer MiniMax T2A, not this endpoint (model_protocol_not_offered). Use MiniMax Audio Inbound Protocol.

bash

curl https://api.modelgo.ai/v1/audio/speech \
  -H "Authorization: Bearer $MODELGO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"<openai-speech-model>","input":"Hello from ModelGo.","voice":"alloy"}' \
  --output speech.mp3

For MiniMax-native fields (voice mix, subtitles, hex JSON, SSE), see MiniMax Audio Inbound Protocol.