Audio (speech2text)
Send the first inference using our API in the Audio environment (speech2text). Use your endpoint address and include:
Transcriptions
If you want to perform transcription on an audio file.
Example: https://71bd1b92256e.app.modelserve.ai/transcriptions?response_format=text
cURL:
curl -X 'POST' \
'https://{address}/transcriptions/?response_format=text' \
-H 'Authorization: Bearer X' \
-H 'Accept: application/json' \
-F 'file=@/path/to/modelserve-example.mp3;type=audio/mpeg'
Download file: modelserve-example.mp3
Translations
If you want to perform transcription and translation on an audio file.
Example: https://71bd1b92256e.app.modelserve.ai/translations?response_format=text&language=english
cURL:
curl -X 'POST' \
'https://{address}/translations?response_format=text&language=english' \
-H 'Authorization: Bearer X' \
-H 'Accept: application/json' \
-F 'file=@/path/to/audio.mp3;type=audio/mpeg'
Download file: modelserve-example.mp3
Remember to replace the "X" in Authorization with your real Access Token. Where to find your Access Token (Bearer)? Learn more in the 🚀 Quickstart section.
Check the Notebooks section where you will find ready-made solutions to test.