Kling Avatar 2.0 talking avatar turns one portrait and an audio file into a clip of that person speaking or singing it. Render at 720p or 1080p; the clip length follows your audio, up to about 5 minutes.
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.
- Output7s
jazz-club-velvet-singer-hello 720p: `image_url` is a singer in a black velvet off-the-shoulder gown at a vintage microphone in a smoky jazz club under blue spotlights; `audio_url` is a slow, low female voice saying "Good evening, darling. Pull up a chair. This next song is just for you." Her lips follow the line and close in the pause after "darling", she tilts her head with a lazy smile as the prompt asks, and her fingers stay on the microphone. The speech ends at about 5.2 seconds; the returned clip runs 7.2 seconds and holds her closed-lip smile for the last two.
- 720p
- Output12s
rooftop-confession 1080p: a nervous, sincere delivery with a glance down and a shy laugh at the end, matched word for word to the source audio.
- 1080p
- Output12s
singer-between-songs 720p: a between-songs stage address, one hand resting on the microphone stand as directed in the prompt.
- Output9s
podcast-cold-open 720p: an upbeat, high-energy line delivered with matching eyebrow and smile animation throughout.
- Output12s
bar-counter-story 720p: a relaxed, low-key delivery, small nods and an easy smile matched to a specific imagined relationship.
This example starts at $0.051 per output second. The Playground updates the estimate when you change the settings.