Skip to main content
POST
/
v3
/
glm-tts-voice-clone
GLM Voice Clone
curl --request POST \
  --url https://api.novita.ai/v3/glm-tts-voice-clone \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "text": "<string>",
  "input": "<string>",
  "audio_url": "<string>",
  "voice_name": "<string>"
}
'
{
  "voice": "<string>",
  "audio_url": "<string>"
}

Documentation Index

Fetch the complete documentation index at: https://novita.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

Using voice cloning technology to generate speech synthesis with specified voice timbre and text content based on sample audio.

​
Request Headers

​
Content-Type
string
required
Supports: application/json
​
Authorization
string
required
Bearer authentication format, for example: Bearer {{API Key}}.

​
Request Body

​
text
string
Text content of the sample audio, optional
​
input
string
required
Target text content for generating preview audio
​
audio_url
string
required
URL of the sample audio. Size limit is 10MB, recommended audio duration is between 3 to 30 seconds.
​
voice_name
string
required
Specify a unique voice name

​
Response

​
voice
string
Voice timbre
​
audio_url
string
URL of the generated preview audio file