Voice Design

Generate a matching voice or speech preview from the text to synthesize and a natural-language voice-style description.

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.

   MOSS_API_KEY=<your_api_key_here>

2. Prepare the request input

   Prepare the request parameters for this scenario. A synchronous call can wait for the result directly; for long-running work, pass async=true and webhook_url.

   FieldTypeRequirementDescription

   model: stringRequired

   moss-voice-generator-1.0

   input: stringRequired

   Text to generate speech from

   instruction: stringRequired

   Voice style description

   delivery_method: stringOptional

   url returns JSON with a result URL

   response_format: stringOptional

   Audio format for synchronous requests; mp3 is recommended

   {
     "model": "moss-voice-generator-1.0",
     "input": "Welcome to tonight's show.",
     "instruction": "A gentle, natural young female voice with a hint of a smile",
     "delivery_method": "url",
     "response_format": "mp3"
   }

3. Send the first request

   Send a request to the scenario endpoint. A synchronous request returns audio bytes directly, or JSON containing a result URL when delivery_method=url; with async=true, it returns a task object.

   curl https://api.mosi.cn/v1/audio/voice/generations \
     -H "Authorization: Bearer $MOSS_API_KEY" \
     -H "Content-Type: application/json" \
     -d '{
     "model": "moss-voice-generator-1.0",
     "input": "Welcome to tonight’s program.",
     "instruction": "A gentle, natural young woman’s voice with a slight smile",
     "delivery_method": "url",
     "response_format": "mp3"
   }'

   import os
   import requests
   
   resp = requests.post(
       "https://api.mosi.cn/v1/audio/voice/generations",
       headers={
           "Authorization": f"Bearer {os.environ['MOSS_API_KEY']}",
           "Content-Type": "application/json",
       },
       json={
           "model": "moss-voice-generator-1.0",
           "input": "Welcome to tonight's show.",
           "instruction": "A gentle, natural young female voice with a hint of a smile",
           "delivery_method": "url",
           "response_format": "mp3"
       },
   )
   
   print(resp.status_code)
   print(resp.json())

   const response = await fetch("https://api.mosi.cn/v1/audio/voice/generations", {
     method: "POST",
     headers: {
       Authorization: `Bearer ${process.env.MOSS_API_KEY}`,
       "Content-Type": "application/json",
     },
     body: JSON.stringify({
     "model": "moss-voice-generator-1.0",
     "input": "Welcome to tonight's show.",
     "instruction": "A gentle, natural young female voice with a hint of a smile",
     "delivery_method": "url",
     "response_format": "mp3"
   }),
   });
   
   console.log(response.status);
   console.log(await response.json());

4. Retrieve the task result

   For synchronous calls with delivery_method=url, read the voice generation result URL from the response JSON. Passing async=true returns a task_id; query the task result via GET /v1/audio/tasks/{task_id}. The final audio format is determined by the task result.

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

5. Verify success

   Success indicator: you obtain audio generated in the described style or a result URL, and can download or play it.

Next steps