Asynchronous speech synthesis
Submit a text-to-speech asynchronous task. Choose one of text and text_file_id; poll through GET /minimax/v1/query/t2a_async_query_v2 after submission.…
POST
/minimax/v1/t2a_async_v2Body Parametersapplication/json
aigc_watermark boolean
Whether to add an AIGC watermark
audio_setting object
Audio output settings
properties bitrate integer
Bitrate
format string
Format
sample_rate integer
Sample rate
language_boost string
Language enhancements (e.g. `Chinese`, `English`)
model* string
T2A model
text string
Text to be synthesized (choose one from `text_file_id`)
text_file_id integer
Text file ID (alternative to `text`)
voice_setting* object
Sound settings
properties pitch integer
Pitch, range -12–12
speed number
Speech rate, range 0.5–2.0
voice_id* string
Voice ID
vol number
Volume, range 0–10
Responses
200 Task submitted successfully application/json
response-200 object
properties base_resp object
file_id integer
File ID
task_id integer
Asynchronous task ID
task_token string
Task token
usage_characters integer
Number of billed characters
400 Request parameter error application/json
response-400 object
401 Authentication failed application/json
response-401 object
429 Trigger current limit application/json
response-429 object
1{
2"model": "speech-02-hd",
3"text": "真正的危险不是计算机开始像人一样思考，而是人开始像计算机一样思考。",
4"voice_setting": {
5"pitch": 0,
6"speed": 1,
7"voice_id": "moss_audio_ce44fc67-7ce3-11f0-8de5-96e35d26fb85",
8"vol": 1
9}
10}
1curl -X POST "https://api.digislash.com/minimax/v1/t2a_async_v2" \
2-H "Authorization: Bearer <API Key>" \
3-H "Content-Type: application/json" \
4-d '{
5"model": "speech-02-hd",
6"text": "真正的危险不是计算机开始像人一样思考，而是人开始像计算机一样思考。",
7"voice_setting": {
8"pitch": 0,
9"speed": 1,
10"voice_id": "moss_audio_ce44fc67-7ce3-11f0-8de5-96e35d26fb85",
11"vol": 1
12}
13}'
1▼{
2▼"base_resp": {
3"status_code": 0,
4"status_msg": "success"
5},
6"file_id": 0,
7"task_id": 0,
8"task_token": "string",
9"usage_characters": 0
10}