Multi-Speaker Dialogue Speech Generation

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

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, use speakers to declare each speaker (id + a created voice_id), then use segments to provide the lines split by speaker.

   speakers: mapping of speaker id to voice_id segments: lines split by speaker delivery_method and response_format: control whether a URL or audio is returned

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

   15 voices

   Browse more voices in the Mossland voice library.

   Preview	Voice name	Voice ID	Description	Language
   	Mambo (Accented)	c6c0a40a-ea82-4468-9a21-333d3c4a76f6	Anime, Character Dubbing · Brisk, Cute, Funny	Chinese · Mandarin
   	Ming Taizu (Hongwu Emperor)	f80b6698-0066-430b-88a0-f0fb8796db34	Character Dubbing, Film & TV · Aloof, Calm, Domineering CEO	Chinese · Mandarin
   	VOX AKUMA	ddc6e38b-6f55-4415-b21b-a88cad2cc1d9	Podcast, Social Media · Lazy, Magnetic, Professional	English · British English
   	Li Bai	7662a8a1-700c-466a-b66b-57ece9e2e231	Film & TV, People · Ancient Style, Passionate	Chinese · Mandarin
   	Jake (Narrator)	f9a1416b-d006-4b77-9581-8f0e8ec1e401	Character Dubbing, People · Calm, Magnetic, Professional	English · British English
   	Experienced Female Teacher	faf7f550-0627-4fc6-8db0-d3bfdad49358	Education, Social Media · Aloof, Natural	Chinese · Mandarin
   	Youthful Male Voice	fe85a513-9bf3-4ef7-aa0b-8b2d11e4db93	Audiobook, Narration · Gentle, Magnetic, Natural	Chinese · Mandarin
   	Male History Narrator	0804710c-8e5e-4b67-acda-5785ef13c309	Audiobook, Film & TV Commentary · Calm, Magnetic	Chinese · Mandarin
   	Elegant British Lady	9d1e88e9-3b9c-4992-a414-7a1cb3ff7ab5	Film & TV, People · Gentle, Magnetic, Natural	English · British English
   	Bright & Lively Female Voice	806c9695-6160-404e-8722-4f788d935af3	Customer Service, Trending Play · Brisk, Lively, Natural	Chinese · Mandarin
   	Classical Chinese Poetry Recitation	2fdf194e-c16e-4587-9027-0d3464e09b4e	Education, Narration · Calm, Magnetic, Professional	Chinese · Mandarin
   	Forbidden City Documentary	133bd03b-d717-4a55-8974-7ffc9afc1b51	Documentary, Narration · Calm, Magnetic, Professional	Chinese · Mandarin
   	Brother Hu (Northeast China)	26838557-6890-4505-bc7c-e8198443a141	Entertainment, Social Media · Funny, Lazy	Chinese · Mandarin
   	Melancholy Autumn	19411508-8731-4b68-901d-7e4b8a98e23f	Film & TV, People · Gentle, Lazy	Chinese · Mandarin
   	Agriculture & Rural Affairs Narrator	944eb93b-3820-49f3-b2c0-4e37a31d1161	Documentary, Narration · Brisk, Magnetic, Professional	Chinese · Mandarin

   {
     "model": "moss-ttsd-1.0",
     "speakers": [
       { "id": "A", "voice_id": "<speaker_a_voice_id>" },
       { "id": "B", "voice_id": "<speaker_b_voice_id>" }
     ],
     "segments": [
       { "speaker": "A", "text": "How is the progress today?" },
       { "speaker": "B", "text": "The API integration testing is already complete." }
     ],
     "delivery_method": "url",
     "response_format": "mp3"
   }
   

3. Send the first request

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

   curl https://api.mosi.cn/v1/audio/speech/speakers \
     -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/speakers",
       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/speakers', {
     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. For longer tasks, you can pass async=true and webhook_url to create an asynchronous task, then query it with the returned 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