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.
- Output5s
terrace-one-more-sunset No audio file, 720p at 16:9: about 1358 x 678, 5.0 seconds, after about 1 min 45 s. She turns from the sea, tucks her hair behind her ear and says the line, and the transcription matched: "Stay for one more sunset. The boat can wait."
- 21
- 720p
- 16:9
- Output5s
bar-counter-own-voice A portrait plus a 5-second spoken clip as audio_url, 720p at 16:9: about 1358 x 678 at 25 fps, 5.0 seconds, after about 3 min 7 s. The lips followed the supplied audio, with a half smile and eyebrow movement, and the face stayed close to the input portrait. The prompt carries no words, just mood, movement and light.
- 11
- 720p
- 16:9
This example starts at $0.024 per output second. The Playground updates the estimate when you change the settings.