Single-Speaker Speech Generation

Synthesize a piece of text into speech with a single voice, suited to narration, customer-service scripts, announcements, and audio content generation.

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

   Use model to specify the model, and fill in the input fields required for single-speaker speech synthesis. For a reference voice, first create one with POST /v1/audio/voices, then use the resulting voice_id here.

   input: text to synthesize voice or voice_id: target voice response_format: output format, defaults to mp3 delivery_method: audio or url

   {
     "model": "moss-tts",
     "input": "Welcome to the MOSI speech synthesis service. This is a sample voiceover.",
     "voice_id": "<voice_id>",
     "response_format": "mp3",
     "delivery_method": "url"
   }
   

3. Send the first request

   Send a request to POST /v1/audio/speech. When delivery_method=url, JSON and a result URL are returned synchronously.

   cURLPythonTypeScript

   curl https://api.mosi.cn/v1/audio/speech \
     -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/speech",
       headers={"Authorization": f"Bearer {os.environ['MOSS_API_KEY']}"},
       json=payload,
   )
   print(resp.json())
   

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

4. Retrieve the result

   When delivery_method=url, read the result URL from the JSON of the synchronous response. If you pass async=true, the endpoint first returns a task_id, which you then use to query the task.

   cURLPythonTypeScript

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

   resp = requests.get(
       f"https://api.mosi.cn/v1/audio/tasks/{task_id}",
       headers={"Authorization": f"Bearer {os.environ['MOSS_API_KEY']}"},
   )
   print(resp.json())
   

   const resp = await fetch(`https://api.mosi.cn/v1/audio/tasks/${taskId}`, {
     headers: { Authorization: `Bearer ${apiKey}` },
   })
   

5. Verify success

   Success indicator: you obtain the result audio (delivery_method=audio) or a result URL (delivery_method=url), and can download or play the generated audio.

Next steps