Multi-speaker Speech

Synthesize multi-character dialogue text into complete dialogue audio, suited to podcasts, role-play, audiobooks, and course dialogues.

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

   Use speakers to declare each speaker and voice_id, and use segments to assign lines to speakers. Synchronous calls return audio bytes or a result URL according to delivery_method; for long-running work, pass async=true and query the returned task_id.

   FieldTypeRequirementDescription

   model: stringRequired

   moss-ttsd-1.0

   speakers: arrayRequired

   Mapping between speaker IDs and voice_id values

   segments: arrayRequired

   Ordered text segments associated with speakers.id through speaker

   delivery_method: stringOptional

   Controls whether a synchronous request returns a URL or audio directly; response_format only controls synchronous output format

   Preview a voice and copy its Voice ID into your request.

   Browse more voices in the Mossland voice library.

   {
     "model": "moss-ttsd-1.0",
     "speakers": [
       {
         "id": "speaker_a",
         "voice_id": "7e5020e3-b88e-4271-a996-2908a182dd32"
       },
       {
         "id": "speaker_b",
         "voice_id": "2925f9ce-75af-4354-8757-b52c3e541e8c"
       }
     ],
     "segments": [
       {
         "speaker": "speaker_a",
         "text": "诶，我最近看了一篇讲人工智能的文章，还挺有意思的，想跟你聊聊。"
       },
       {
         "speaker": "speaker_b",
         "text": "哦？是吗，关于啥的啊？又是哪个公司发了什么逆天的新模型吗？"
       }
     ],
     "response_format": "wav",
     "delivery_method": "audio"
   }

3. Send the first request

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

   curl --fail-with-body -sS -X POST "https://api.mosi.cn/v1/audio/speech/speakers" \
   -H "Authorization: Bearer $MOSS_API_KEY" \
   -H "Platform: moss-platform" \
   -H "Content-Type: application/json" \
   -d '{
   "model": "moss-ttsd-1.0",
   "speakers": [
   {
   "id": "speaker_a",
   "voice_id": "7e5020e3-b88e-4271-a996-2908a182dd32"
   },
   {
   "id": "speaker_b",
   "voice_id": "2925f9ce-75af-4354-8757-b52c3e541e8c"
   }
   ],
   "segments": [
   {
   "speaker": "speaker_a",
   "text": "诶，我最近看了一篇讲人工智能的文章，还挺有意思的，想跟你聊聊。"
   },
   {
   "speaker": "speaker_b",
   "text": "哦？是吗，关于啥的啊？又是哪个公司发了什么逆天的新模型吗？"
   }
   ],
   "response_format": "wav",
   "delivery_method": "audio"
   }'

   import os
   import requests
   
   resp = requests.post(
       "https://api.mosi.cn/v1/audio/speech/speakers",
       headers={
           "Authorization": f"Bearer {os.environ['MOSS_API_KEY']}",
           "Content-Type": "application/json",
       },
       json={
           "model": "moss-ttsd-1.0",
           "speakers": [
               {
                   "id": "speaker_a",
                   "voice_id": "<speaker_a_voice_id>"
               },
               {
                   "id": "speaker_b",
                   "voice_id": "<speaker_b_voice_id>"
               }
           ],
           "segments": [
               {
                   "speaker": "speaker_a",
                   "text": "Hello, I am A."
               },
               {
                   "speaker": "speaker_b",
                   "text": "Hello, I am B."
               }
           ],
           "delivery_method": "url",
           "response_format": "mp3"
       },
   )
   
   print(resp.status_code)
   print(resp.json())

   const response = await fetch("https://api.mosi.cn/v1/audio/speech/speakers", {
     method: "POST",
     headers: {
       Authorization: `Bearer ${process.env.MOSS_API_KEY}`,
       "Content-Type": "application/json",
     },
     body: JSON.stringify({
     "model": "moss-ttsd-1.0",
     "speakers": [
       {
         "id": "speaker_a",
         "voice_id": "<speaker_a_voice_id>"
       },
       {
         "id": "speaker_b",
         "voice_id": "<speaker_b_voice_id>"
       }
     ],
     "segments": [
       {
         "speaker": "speaker_a",
         "text": "Hello, I am A."
       },
       {
         "speaker": "speaker_b",
         "text": "Hello, I am B."
       }
     ],
     "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 result URL from the response JSON. Passing async=true returns a task_id; query the task result via GET /v1/audio/tasks/{task_id}.

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

5. Verify success

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

Next steps