Single-speaker Speech

Synthesize text into speech. This endpoint aligns with POST /v1/audio/speech; voice_id accepts only a voice id, not a voice url, a multipart voice file, or base64.

POST

/v1/audio/speech

Text-to-speech. The request body is JSON; delivery_method=url returns JSON (with a result URL), and delivery_method=audio (default) returns binary audio.

Authentication

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

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

Supported models

Field	Allowed values
model	`moss-tts`

Request fields

Field	Type	Required	Description
model	string	Yes	Model name; see "Supported models" for allowed values, for example `moss-tts`.
version	string	No	Specify a model version that is live and publicly available; omit it to use the server's current default.
input	string	Yes	The text to synthesize.
voice_id	string	Yes	Voice ID; get one via List Voices, or go to the Mossland voice library and copy it from a voice card's copy icon. TTS accepts only a voice ID and does not support `voice_url` / `voice_data`, nor inline or reference audio.
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` (default) returns binary audio directly; `url` returns JSON with a result URL.
async	boolean	No	When set to `true`, creates an asynchronous task and immediately returns a task object; the result is obtained via task query or `webhook_url`.
webhook_url	string	No	The HTTPS URL to call back once the asynchronous task completes.

Request example

curl https://api.mosi.cn/v1/audio/speech \
  -H "Authorization: Bearer $MOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moss-tts",
    "input": "hello",
    "voice_id": "<voice_id>",
    "response_format": "mp3",
    "delivery_method": "url"
  }'

Response fields

When delivery_method=url, JSON (with 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	Fixed as `audio.speech`.
status	string	Yes	Task status, for example `SUCCESS`.
url	string	Yes	Audio result URL.
response_format	string	Yes	Actual output audio format, for example `mp3`.
content_type	string	Yes	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.

Create Transcription

Audio transcription endpoint.