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 / –:––
Late-night storytelling intro in the George voice George read 126 characters with stability 0.4 and mp3_44100_128; the result is an 8.75-second mono MP3, and the [softly] cue shapes the delivery without being pronounced.
- George
- 0.4
- mp3_44100_128
- 0:00 / –:––
Museum notice read by Daniel with a whisper cue Daniel, language en, seed 7 and mp3_22050_32 produced this 5.17-second file at 22.05 kHz and 32 kbps; the [whispers] tag itself is not spoken aloud.
- 7
- en
- Daniel
This example starts at $0.096 per 1,000 characters. The Playground updates the estimate when you change the settings.
