curl --request POST \
--url https://api.omnimux.ai/v1/tasks/autodl \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model": "indextts-2",
"prompt_text": "Hello, this is a voice clone test.",
"prompt_simple": "https://example.com/voice.wav",
"emo_control_method": "与音色参考音频相同"
}'
{
"id": "task_sl8rnyewmb1O2ygKljRFnSIFnnmUSdeu",
"task_id": "task_sl8rnyewmb1O2ygKljRFnSIFnnmUSdeu",
"model": "indextts-2",
"status": "queued",
"created_at": 1789704195
}
curl --request POST \
--url https://api.omnimux.ai/v1/tasks/autodl \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model": "indextts-2",
"prompt_text": "Hello, this is a voice clone test.",
"prompt_simple": "https://example.com/voice.wav",
"emo_control_method": "与音色参考音频相同"
}'
{
"id": "task_sl8rnyewmb1O2ygKljRFnSIFnnmUSdeu",
"task_id": "task_sl8rnyewmb1O2ygKljRFnSIFnnmUSdeu",
"model": "indextts-2",
"status": "queued",
"created_at": 1789704195
}
Index TTS
Index TTS voice clone
AutoDL Index-TTS voice clone · model indextts-2
curl --request POST \
--url https://api.omnimux.ai/v1/tasks/autodl \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model": "indextts-2",
"prompt_text": "Hello, this is a voice clone test.",
"prompt_simple": "https://example.com/voice.wav",
"emo_control_method": "与音色参考音频相同"
}'
{
"id": "task_sl8rnyewmb1O2ygKljRFnSIFnnmUSdeu",
"task_id": "task_sl8rnyewmb1O2ygKljRFnSIFnnmUSdeu",
"model": "indextts-2",
"status": "queued",
"created_at": 1789704195
}
POST
/
v1
/
tasks
/
autodl
curl --request POST \
--url https://api.omnimux.ai/v1/tasks/autodl \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model": "indextts-2",
"prompt_text": "Hello, this is a voice clone test.",
"prompt_simple": "https://example.com/voice.wav",
"emo_control_method": "与音色参考音频相同"
}'
{
"id": "task_sl8rnyewmb1O2ygKljRFnSIFnnmUSdeu",
"task_id": "task_sl8rnyewmb1O2ygKljRFnSIFnnmUSdeu",
"model": "indextts-2",
"status": "queued",
"created_at": 1789704195
}
- Create:
POST /v1/tasks/autodlwithmodelindextts-2 - Poll:
GET /v1/tasks/{task_id}(fetch output audio throughGET /v1/tasks/{task_id}/artifacts) - Dedicated workflow channel supporting reference voice clone and emotional nuance control
- Recommended: For 3-second instant generation, prefer official mainstream
seed-audio-1.0voice clone mode
Identity
| Field | Value |
|---|---|
| Series | Audio |
| Brand | Index TTS / AutoDL |
| model | indextts-2 |
Endpoint
| Method | Path |
|---|---|
POST | /v1/tasks/autodl |
GET | /v1/tasks/{task_id} |
GET | /v1/tasks/{task_id}/artifacts |
https://api.omnimux.ai
Authorizations
| Name | In | Type | Required | Description |
|---|---|---|---|---|
Authorization | header | string | yes | Bearer sk-... (API key) |
Body
| Field | Type | Required | Description |
|---|---|---|---|
model | string | yes | Must be indextts-2 |
prompt_text | string | yes | Text script to read and synthesize |
prompt_simple | string | yes | Voice timbre reference audio URL |
emo_control_method | string | yes | Emotion mode, recommended "与音色参考音频相同" |
emo_happy | number | no | Happiness intensity [0, 1], e.g. 0.5 |
emo_sad | number | no | Sadness intensity [0, 1] |
emo_angry | number | no | Anger intensity [0, 1] |
Response
200 (Create)
| Field | Type | Description |
|---|---|---|
id / task_id | string | Task identifier |
status | string | queued |
Poll & Artifacts
After completion, fetch the synthesized WAV audio throughGET /v1/tasks/{task_id}/artifacts.