Multi-speaker Speech

Multi-speaker text-to-speech (TTSD). Use the speakers array to declare each speaker (id + voice), then use the segments array to provide the lines split per speaker. The voice is specified with voice_id, with values taken from List Voices.

POST

/v1/audio/speech/speakers

Multi-speaker TTS. The request body is JSON; delivery_method=url returns JSON (containing a result URL), while delivery_method=audio (the default) returns the audio binary.

Authentication

Add Authorization: Bearer <API_KEY> to the request header to authenticate. You can generate a key on the "API Keys" page of the console.

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

Supported models

Field	Allowed values
model	`moss-ttsd`

Request fields

Field	Type	Required	Description
model	string	Yes	Model name; the value is `moss-ttsd`.
version	string	No	Specify a model version that is live and publicly available, e.g. `moss-ttsd-20260320`; omit it to use the server's current default.
speakers	array	Yes	The speaker configuration array, declaring each speaker and its voice; cannot be empty.
speakers[].id	string	Yes	The speaker identifier, referenced by `segments[].speaker`.
speakers[].voice_id	string	Yes	The speaker's voice ID; obtainable from the List Voices or Create Voice endpoint.
segments	array	Yes	The segment array, giving the lines per speaker; cannot be empty.
segments[].speaker	string	Yes	The speaker identifier; must match one of `speakers[].id`.
segments[].text	string	Yes	The text of this line.
response_format	string	No	Audio format for synchronous requests, e.g. `mp3` / `wav`; for asynchronous tasks the actual format is subject to the task query response.
delivery_method	string	No	`audio` returns the audio directly; `url` returns JSON and a result URL.
async	boolean	No	When set to `true`, creates an asynchronous task and immediately returns a task object; the audio result is delivered by URL.
webhook_url	string	No	The HTTPS URL called back after the asynchronous task completes.

Request example

curl https://api.mosi.cn/v1/audio/speech/speakers \
  -H "Authorization: Bearer $MOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moss-ttsd",
    "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"
  }'

Delivery methods

Request mode	Response
Default or `delivery_method=audio`	Returns the audio binary directly; `Content-Type` varies with `response_format`
`delivery_method=url`	Returns JSON containing the audio result URL
`async=true`	Returns an asynchronous task object; the task result is queried via `GET /v1/audio/tasks/{task_id}`

Synchronous URL response fields

When delivery_method=url, JSON (containing a result URL) is returned:

Field	Type	Always returned	Description
id	string	Yes	Task / result ID. Synchronous URL JSON responses uniformly use `id`.
object	string	Yes	Always `audio.speech`.
status	string	Yes	Task status, for example `SUCCESS`.
url	string	Yes	The audio result URL.
response_format	string	Yes	The actual output audio format, for example `mp3`.
content_type	string	Yes	The audio MIME type, for example `audio/mpeg`.
created_at	integer	Yes	Creation time, a Unix timestamp in seconds.

Asynchronous creation response fields

Returned immediately when async=true:

Field	Type	Always returned	Description
id	string	Yes	Task ID.
task_id	string	Yes	Task query ID, usually the same as `id`.
object	string	Yes	Always `audio.speech`.
status	string	Yes	Initial status, for example `PENDING`.
retry_after	integer	No	Suggested polling interval, in seconds.
created_at	integer	Yes	Creation time, a Unix timestamp in seconds.
updated_at	integer	No	Update time, a Unix timestamp in seconds.

Response example

{
  "id": "task_abc123",
  "object": "audio.speech",
  "status": "SUCCESS",
  "url": "https://cdn.example.com/out.mp3",
  "response_format": "mp3",
  "content_type": "audio/mpeg",
  "created_at": 1710000000
}

Next steps

List Voices

List the voices available to your account.

Single-speaker Speech

Text-to-speech endpoint.