Handling Large Files

When sending requests with audioData, you need to encode the audio file into Base64 format and include it in the request. However, for large file sizes or long-duration audio files, Gowajee supports using Pre-signed URLs to avoid encoding the file data to base64

Using Presigned URLs

To transcribe large or long-duration files, you can use a pre-signed URL. By providing the pre-signed URL in the audioData field instead of base64 encoded data, our API will automatically download the audio file from the provided URL and process the transcription.

Example Request with pre-signed URL:

POST /v1/speech-to-text/${MODEL}/transcribe HTTP/1.1
Host: api.gowajee.ai
Content-Type: application/json
X-Api-Key: ${YOUR_API_KEY}

{
  "audioData": "https://example.com/presigned_url_to_audio_file"
}

Notes

• Base64 Encoding: Ensure the audio data is base64 encoded if you are not using Presigned URLs.

• Presigned URLs: Use Presigned URLs for large files or long-duration audio to optimize performance and avoid base64 encoding overhead.