We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.
heygen/heygen-avatar-6A photo that says your recording
HeyGen Avatar 6 takes one photo of a person and one speech recording, and returns a video of that person saying it, lips moving with the words. The recording is the voice and sets the length of the video, and an optional sentence directs the acting. HeyGen calls it its smartest avatar model yet and reports, from its own study, that 84.4% of its results were judged indistinguishable from real footage side by side, against 44.4% for its earlier Avatar V. We have not tested Avatar 6 ourselves. Billed per second of video: 231.567 credits at 1080p, 335.772 at 2K, which is twice the 1080p price of Avatar 6 Turbo. Use only photos of people who have agreed to it: no photos of minors, and no public figures without their consent (HeyGen's own policy).
Last updated Nov 21, 2026
One photo and one recording in, a talking video out
No duration to set: the video lasts as long as the recording
An optional prompt asks for a smile, a nod or a hand gesture
Full HD by default, 2K when you need more detail
HeyGen calls it its smartest avatar model yet
84.4% judged indistinguishable from real footage, says HeyGen
Yes. Top up your Tchavi account with Orange Money, MTN MoMo, M-Pesa or another mobile money operator. No bank card is needed. Credits land as soon as the payment is confirmed and are deducted as you use them.
Yes. Keep your current OpenAI SDK, just change the base URL to Tchavi's (shown in the API tab) and use your Tchavi key. The rest of your code stays the same.
import Tchavi from '@tchavi/sdk';
const client = new Tchavi({ apiKey: 'API_KEY' });
const job = await client.videos.generations.create({
"model": "heygen-avatar-6",
"prompt": "A cinematic shot of a cat astronaut floating in space",
"resolution": "480p",
"duration": 5,
"aspect_ratio": "16:9",
"generate_audio": true
});
console.log('Job id:', job.id);
console.log('Credits used:', job.tchavi.credits_used);
// Poll for completion
let result = await client.videos.generations.retrieve(job.id);
while (result.status === 'pending' || result.status === 'processing') {
await new Promise((r) => setTimeout(r, 2000));
result = await client.videos.generations.retrieve(job.id);
}
console.log('Video URL:', result.output?.video_url);Every parameter this model accepts on the API. Check the SDK for full typings.
modelRequiredID of the video model (e.g. `heygen-avatar-6`).
promptRequiredText description of the video to generate.