Speech to text

/

POST /v1/audio/transcriptions takes multipart/form-data, not JSON: send model as a form field and the recording as a file part named file. The reply is {"text": "…"}. POST /v1/audio/translations is the same shape and returns English. Unlike the video endpoints this is synchronous, so a long recording holds the connection open until it finishes.

POST /v1/audio/transcriptions 
curl https://api.chinaapi.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $CHINAAPI_KEY" \
  -F model=stepaudio-2.5-asr \
  -F file=@speech.mp3

# {"text":" China api text to speech verification."}
Lowest cost

stepaudio-2.5-asr

With step-asr, step-asr-1.1 and stepaudio-2-asr-pro. stepaudio-2.5-asr is by a wide margin the cheapest transcription model on the endpoint; the pro and 1.1 variants cost roughly fifteen times as much and are worth it only when accuracy on difficult audio matters.

Streaming

stepaudio-2.5-asr-stream

With step-asr-1.1-stream. These return partial text as the audio is consumed rather than one block at the end, which is what you want for live captioning; both cost more per minute than their non-streaming counterparts.

Multilingual and dialects

qwen3-asr-flash

With glm-asr-2512 and mimo-v2.5-asr. qwen3-asr-flash and glm-asr-2512 are the multilingual options, and mimo-v2.5-asr is the one tuned for Chinese dialects.

Tip Billing counts the length of the audio you upload, at a thousand tokens to the minute, and the duration is rounded up to a whole second before that conversion — so a five second clip bills as 83 tokens and anything under a second still bills as if it were one. The transcript itself is free. Cost therefore scales with recording length and not with how much speech the recording contains, which makes trimming silence worthwhile.