Audio Transcription

Convert audio into text — ideal for meetings, interviews, voice messages, and media content processing.

Workflow

1. Create an API Key

   Open the API Key management platform, create an API Key, and save it as an environment variable. Do not write the API Key into client-side code or commit it to a repository.

   export MOSS_API_KEY="<your-api-key>"
   

2. Prepare the request input

   Set model to moss-transcribe and provide the audio to transcribe (file, file_id, url, or audio_url).

   file / file_id / url / audio_url: audio to transcribe model: moss-transcribe response_format: json / text, etc.

   {
     "model": "moss-transcribe",
     "file_id": "<file_id>",
     "response_format": "json"
   }
   

3. Send your first request

   Send a request to POST /v1/audio/transcriptions; a synchronous request returns the transcription result directly.

   cURLPythonTypeScript

   curl https://api.mosi.cn/v1/audio/transcriptions \
     -H "Authorization: Bearer $MOSS_API_KEY" \
     -H "Content-Type: application/json" \
     -d @request.json
   

   import json
   import os
   import requests
   
   payload = json.load(open("request.json"))
   resp = requests.post(
       "https://api.mosi.cn/v1/audio/transcriptions",
       headers={"Authorization": f"Bearer {os.environ['MOSS_API_KEY']}"},
       json=payload,
   )
   print(resp.json())
   

   const resp = await fetch('https://api.mosi.cn/v1/audio/transcriptions', {
     method: 'POST',
     headers: {
       Authorization: `Bearer ${apiKey}`,
       'Content-Type': 'application/json',
     },
     body: JSON.stringify(payload),
   })
   

4. Retrieve the result

   A synchronous request returns the transcription result directly. If you pass async=true, the endpoint first returns a task_id, which you then use to query the transcription task.

   curl https://api.mosi.cn/v1/audio/transcriptions/$TASK_ID \
     -H "Authorization: Bearer $MOSS_API_KEY"
   

5. Verify success

   Success indicator: you obtain the transcribed text.

Next steps