Get API Key Get API
Docs

Whisper-1 Audio Transcription

- Supports speech recognition in 99 languages

  • Multiple output formats: json, text, srt, vtt, etc.
  • Maximum file size 25 MB

Request example

curl --request POST \
  --url https://api.openveer.com/v1/audio/transcriptions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form 'file=@/path/to/audio.mp3' \
  --form 'model=whisper-1' \
  --form 'language=en' \
  --form 'response_format=json'

Response example

{
  "text": "This is a transcribed text from the test audio."
}

Authorizations

Authorization string

All interfaces require Bearer Token authentication

Get API Key:

Visit API Key Management Page to get your API Key

Add to request header:

Authorization: Bearer YOUR_API_KEY

Body

Note

⚠️ Online testing (Try it) is not supported for this endpoint

Due to file upload limitations, please test using:

  • Apifox / Postman - Manually change file parameter to file type after importing
  • cURL - Refer to code examples on the right
  • SDK - Use SDK examples in various languages
file string

Audio file to transcribe (File type)

⚠️ Note: When testing with Apifox or similar tools:

  1. After importing, manually change this parameter type to file
  2. Ensure request Content-Type is multipart/form-data

Supported formats: mp3, mp4, mpeg, mpga, m4a, wav, webm

Maximum file size: 25 MB

model string

Speech recognition model name

Example: "whisper-1"

language string

Language code of the audio (ISO-639-1 format)

Specifying the language can improve accuracy and speed

Supported languages include: zh (Chinese), en (English), ja (Japanese), ko (Korean), and 99 other languages

Example: "en"

prompt string

Optional text prompt to guide the transcription style or continue from previous audio

Maximum 224 tokens

response_format string

Output format

Supported formats:

  • json - JSON format (text only)
  • text - Plain text
  • srt - SRT subtitle format
  • verbose_json - Verbose JSON format (includes timestamps and metadata)
  • vtt - WebVTT subtitle format
temperature number

Sampling temperature, range 0 to 1

Higher values (like 0.8) make output more random, lower values (like 0.2) make it more deterministic and consistent

Response

text string

Transcribed text content

task string

Task type, fixed as transcribe

Only returned in verbose_json format

language string

Detected or specified language code

Only returned in verbose_json format

duration number

Audio duration (seconds)

Only returned in verbose_json format

segments array
Array of text segments Only returned in verbose\_json format
id integer

Segment ID

start number

Segment start time (seconds)

end number

Segment end time (seconds)

text string

Segment text content

temperature number

Sampling temperature used

avg_logprob number

Average log probability

compression_ratio number

Compression ratio

no_speech_prob number

No speech probability

This documentation is built and hosted on Mintlify, a developer documentation platform.