1
Record 10–30 seconds of your voice
One clean clip of you speaking is enough for Kineo to clone your pitch, tone and pacing. You only do this once.
AI video narrated in your own voice
Kineo can narrate your videos in a clone of your own voice. Record 10–30 seconds of clear speech once, and Kineo reuses that cloned voice to read the script over AI-generated visuals — from any article or topic — so every short sounds like you without recording a word each time. Up to 3 minutes, on your own WaveSpeed key, with $0 platform markup.
How it works
2
Kineo clones it
Your voice becomes a reusable narrator you can pick for any video — in Cantonese, Mandarin or English.
3
Paste a topic or article
Kineo writes the script and generates the visuals; your cloned voice reads it, timed to how fast you actually speak.
4
Generate — and reuse
Narrate your AI b-roll, or pair the voice with a talking-head avatar of yourself. The same cloned voice carries across video after video.
At a glance
- Voice sample: one 10–30 second clip of clear speech
- Languages: Cantonese · Mandarin · English narration
- Reusable: clone once, narrate every video
- Pairs with: AI b-roll, subtitles, an optional avatar of you
- Length: up to 3 minutes per video
- Runs on your own WaveSpeed key — $0 platform markup
What it costs
Cloning your voice is part of Kineo's flat subscription; each video's compute is billed to your own WaveSpeed key at the provider's price, with $0 platform markup, and the estimate is shown before you generate. The free tier lets you try a short (up to 1-minute), watermarked video first.