English

Audio API

Submit a speech job and retrieve the generated audio.

API quickstartModel guidesClient setup

Audio API

Quote speech synthesis

curl "https://api.apimodel.store/v1/audio/quotes" \
  -H "Authorization: Bearer $MODELPORT_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{"model":"minimax-speech-2.8-hd","text":"Welcome to the show."}'

Submit speech synthesis

curl "https://api.apimodel.store/v1/audio/generations" \
  -H "Authorization: Bearer $MODELPORT_API_KEY" \
  -H "Idempotency-Key: YOUR_UNIQUE_REQUEST_KEY" \
  -H "Content-Type: application/json" \
  --data '{"model":"minimax-speech-2.8-hd","text":"Welcome to the show."}'

Poll the audio task

curl "https://api.apimodel.store/v1/audio/generations?task_id=$MODELPORT_JOB_ID" \
  -H "Authorization: Bearer $MODELPORT_API_KEY"

Set the job ID from data.taskId and read data.resultUrls on success. Supply a vendor voice ID as voice_id when the model supports it.

Find voice IDs