Skip to main content
POST
/
v1
/
audios
/
generations
curl --request POST \
  --url https://api.evolink.ai/v1/audios/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "qwen3-tts-vd",
  "prompt": "Good evening, listeners. Welcome to the evening news broadcast.",
  "voice": "qwen-tts-vd-announcer-voice-20260402-a1b2"
}
'
{
  "created": 1775122733,
  "id": "task-unified-1775122733-lozyt2i5",
  "model": "qwen3-tts-vd",
  "object": "audio.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 10,
    "audio_type": "tts"
  },
  "type": "audio",
  "usage": {
    "credits_reserved": 0.32
  }
}

Authorizations

​
Authorization
string
header
required

##All endpoints require Bearer Token authentication##

Get your API Key:

Visit the API Key management page to obtain your API Key

Add the following header to every request:

Authorization: Bearer YOUR_API_KEY

Body

application/json
​
model
enum<string>
default:qwen3-tts-vd
required

Model name

Available options:
qwen3-tts-vd
Example:

"qwen3-tts-vd"

​
prompt
string
required

Text to synthesize

Constraints:

  • Maximum 600 characters
Maximum string length: 600
Example:

"Good evening, listeners. Welcome to the evening news broadcast."

​
voice
string
required

Voice name

  • Must first create a voice via Qwen Voice Design
  • Obtain the value from result_data.voice in the Voice Design task result
  • System built-in voices are not supported
Example:

"qwen-tts-vd-announcer-voice-20260402-a1b2"

​
language_type
enum<string>

Language hint to help the model select pronunciation rules

Auto-detected if not provided

Available options:
Auto,
Chinese,
English,
Japanese,
Korean,
French,
German,
Spanish,
Italian,
Russian,
Portuguese
Example:

"Auto"

​
callback_url
string<uri>

HTTPS callback URL invoked when the task completes

Trigger conditions:

  • Triggered when the task is completed, failed, or cancelled
  • Sent after billing confirmation

Security restrictions:

  • HTTPS only
  • Internal IP addresses are blocked (127.0.0.1, 10.x.x.x, 172.16-31.x.x, 192.168.x.x, etc.)
  • URL length must not exceed 2048 characters

Callback behavior:

  • Timeout: 10 seconds
  • Up to 3 retries after failure (at 1s / 2s / 4s intervals)
  • Response body format matches the task query API response
  • A 2xx status code is considered success; other codes trigger a retry
Example:

"https://your-domain.com/webhooks/tts-completed"

Response

Speech synthesis task created successfully

​
created
integer

Task creation timestamp

Example:

1775122733

​
id
string

Task ID

Example:

"task-unified-1775122733-lozyt2i5"

​
model
string

Actual model name used

Example:

"qwen3-tts-vd"

​
object
enum<string>

Specific task type

Available options:
audio.generation.task
​
progress
integer

Task progress percentage (0-100)

Required range: 0 <= x <= 100
Example:

0

​
status
enum<string>

Task status

Available options:
pending,
processing,
completed,
failed
Example:

"pending"

​
task_info
object

Audio task details

​
type
enum<string>

Task output type

Available options:
audio
Example:

"audio"

​
usage
object

Usage and billing information