Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
- 0:00 / –:––
noisy-voice-message In our tests, the noisy voice message had a noise floor of about −24 dB before processing and about −35 dB after cleanup. The 12.00-second source returned an 11.98-second MP3.
- 0:00 / –:––
market-video-sound In our tests, the 6.04-second market video returned a 6.04-second MP3 audio track. Compare the returned speech with the source soundtrack; the result has no video picture.
This example starts at $0.0022 per output second. The Playground updates the estimate when you change the settings.
