1
Upload one clear photo
A single front-facing photo is enough — Kineo builds the talking avatar from it.
A talking-head video from your photo and voice
Kineo can put you on camera without filming. Upload one clear photo and a 30-second voice recording, and it builds a talking-head avatar of you with natural lip-sync, narrated by a clone of your own voice. Use it as a full-screen presenter or as a corner overlay on top of other footage — in video after video, no studio, no re-recording.
How it works
2
Record 30 seconds of your voice
A short clip is all it needs to clone your pitch, tone, and delivery.
3
Write or paste your script
Or let Kineo write it from an article or topic — the avatar narrates it for you.
4
Generate — full-screen or corner
Use the avatar as the whole shot, or as a picture-in-picture presenter over B-roll.
At a glance
- Input: one photo + a 30-second voice recording
- Output: lip-synced talking-head, full-screen or corner overlay
- Voice: a clone of your own, or a preset voice
- Length: up to 3 minutes per video
- Languages: English · 繁體中文 · 简体中文 (plus Cantonese narration)
- Runs on your own WaveSpeed key — $0 platform markup
What it costs
Creating the avatar and voice clone is part of Kineo's flat subscription; the per-video compute is billed to your own WaveSpeed key at the provider's price, with $0 platform markup. The free tier lets you try a short (up to 1-minute), watermarked video first.