Skip to main content
POST
https://api.novita.ai
/
v3
/
glm-asr
GLM Audio to Text
curl --request POST \
  --url https://api.novita.ai/v3/glm-asr \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "file": "<string>",
  "prompt": "<string>",
  "hotwords": [
    {}
  ]
}
'
{
  "text": "<string>"
}
Use the GLM-ASR-2512 model to transcribe audio files into text, supporting multi-language transcription.

​
Request Headers

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

​
Request Body

​
file
string
required
The audio file URL or Base64 encoded string to be transcribed. Supported audio formats: .wav / .mp3. Limitations: file size ≤ 25 MB, audio duration ≤ 30 seconds
​
prompt
string
For long text scenarios, you can provide previous transcription results as context. Recommended to be less than 8000 characters.
​
hotwords
array
Hotword list to improve recognition accuracy for domain-specific vocabulary. Format example: [“person name”, “place name”]. Recommended not to exceed 100 items.Array length: 0 - 100

​
Response

​
text
string
The complete transcribed content of the audio