Skip to main content
POST
/
v3
/
glm-asr
GLM Audio-to-Text
curl --request POST \
  --url https://api.highwayapi.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, with support for multilingual transcription.

​
Request Headers

​
Content-Type
string
required
Enum value: application/json
​
Authorization
string
required
Bearer authentication format: Bearer {{API Key}}.

​
Request Body

​
file
string
required
The URL or Base64-encoded string of the audio file to transcribe. Supported audio file formats: .wav / .mp3. Limits: file size ≤ 25 MB, audio duration ≤ 30 seconds.
​
prompt
string
In long-text scenarios, you can provide previous transcription results as context. Recommended to be fewer than 8,000 characters.
​
hotwords
array
A hotword list used to improve recognition accuracy for domain-specific vocabulary. Format example: [“person name”,“place name”]. Recommended to include no more than 100 items.Array length: 0 - 100

​
Response Information

​
text
string
The complete transcribed content of the audio