Quickstart

Make your first API call with a minimal request. You only need an API Key and a valid voice_id.

Get an API Key

Go to the API Key Management Platform to create an API Key. The complete key is shown only once. Store it in a server-side environment variable or secret manager, and never put it in browser code or a public repository.

Configure an environment variable

For local development, configure the API Key as an environment variable.

export MOSS_API_KEY="<your_api_key>"

$env:MOSS_API_KEY="<your_api_key>"

Make your first request

The following call uses the single-speaker speech endpoint. You can obtain a voice_id from List Voices or Create Voice.

curl -X POST "https://api.mosi.cn/v1/audio/speech" \
  -H "Authorization: Bearer $MOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moss-tts-1.5-flash",
    "input": "Welcome to Moss API. [pause 0.8s]Now let us generate speech.",
    "voice_id": "94aa4989-c7e9-5007-ae42-ab401823e6c9",
    "response_format": "mp3",
    "delivery_method": "url"
  }'

Read the result

This request uses delivery_method=url. After it succeeds, read the url field to get the generated audio. For an asynchronous request, use the returned task_id with GET /v1/audio/tasks/{task_id} to query the final status and result.

Next steps