HeyGen Avatar 6
Starts at $0.112 per second of audio
HeyGen's talking photo model that animates a single portrait with a speech track at 1080p or 2K, with prompts that direct motion and expression.
Craze runs HeyGen Avatar 6 when you ask for it by name.
What HeyGen Avatar 6 is good at
Emotion that follows the voice
Sighs, soft laughs and whispers show on the face, not just in the audio.
Prompts that direct the performance
A short prompt tells the avatar how to move: glance out of frame, smile on the last line, lean in for an aside.
Identity that holds through movement
The face stays the same person through head turns, profile angles and changing expressions, with fine detail like wrinkles and hair kept from the source photo.
1080p or 2K output
Choose 1080p for social and web, or 2K for larger screens and room to crop in the editor.
Direct. Create. Edit.
Stop prompting. Start directing.
Craze creatively jams, researches and plans with you.
Create tasteful content.
Craze generates anything imaginable. Video, audio, music, motion graphics and more.
Edit videos in minutes. Not days.
Craze watches your footage and builds a final cut. With a real editor if you need it.
Make videos people watch
- UGC videos
- Motion graphics
- Feature films
- Product visualization
- Micro dramas
- 3D films
- Music videos
- Brand films
- Wedding highlights
- YouTube reviews
How HeyGen Avatar 6 compares
Every model here runs on every Craze plan, including Free, and Craze can use a different one for each shot.
| HeyGen Avatar 6HeyGen | Seedance 2.5ByteDance Seed Team | Seedance 2.0ByteDance Seed Team | Seedance 2.0 FastByteDance Seed Team | |
|---|---|---|---|---|
| Makes | Text + Audio + Image to video | Text + Image + Video + Audio to video | Text + Image + Video + Audio to video | Text + Image + Video + Audio to video |
| Quality | Up to 2K | Up to 4K | Up to 4K | Up to 720p |
| Length | — | Up to 30s per clip | Up to 15s per clip | Up to 15s per clip |
| Sound | — | Generated with the picture | Generated with the picture | Generated with the picture |
| From | $0.112 per second of audio | $0.120 per second of video | $0.079 per second of video | $0.063 per second of video |
HeyGen Avatar 6 specs on Craze
| Task | Inputs | Resolution | Aspect ratios | Sound |
|---|---|---|---|---|
| Talking photo | Audio, First frame | 1080p, 2k | Follows the input | None |
Choose the plan for your next creation.
Free
$0 / month
- Limited usage
- Access to all media models
- Efficient chat tier
- 1 GB of storage
- Craze MCP
- Exports up to 720p
- Top up additional credits
Pro
$19 / month
- $19 of credits every month
- Access to all media models
- Every chat tier
- 50 GB of storage
- Craze MCP
- No resolution limits on exports
- Top up additional credits
Ultra
$59 / month
- $59 of credits every month
- Access to all media models
- Every chat tier
- 200 GB of storage
- Craze MCP
- No resolution limits on exports
- Top up additional credits
Max
$199 / month
- $199 of credits every month
- Access to all media models
- Every chat tier
- 1 TB of storage
- Craze MCP
- No resolution limits on exports
- Top up additional credits
Frequently asked questions
Why creators choose HeyGen Avatar 6
HeyGen Avatar 6 makes a photo speak. Give it one portrait and a voice track, and it returns a talking video where the lips follow the words, the head moves naturally and the face carries the emotion in the voice. It renders at 1080p or 2K, so the result holds up on a large screen.
Emotion that follows the voice
Sighs, soft laughs and whispers show on the face, not just in the audio. A voice track with expressive delivery, such as one made with ElevenLabs v3, gets a matching performance.
Prompts that direct the performance
A short prompt tells the avatar how to move: glance out of frame, smile on the last line, lean in for an aside. The words always come from the audio, so the prompt steers motion and expression only.
Identity that holds through movement
The face stays the same person through head turns, profile angles and changing expressions, with fine detail like wrinkles and hair kept from the source photo.
1080p or 2K output
Choose 1080p for social and web, or 2K for larger screens and room to crop in the editor.
How to use HeyGen Avatar 6 in Craze
- Upload or generate a portrait. A clear, well-lit photo of a face works best.
- Upload, record or generate the voice track the avatar should speak.
- Ask Craze for HeyGen Avatar 6, and describe how the avatar should move if you want to direct it.
- Craze animates the photo, and the video runs as long as the audio.
- Review in the editor and place the clip on your timeline.
HeyGen Avatar 6 pricing
HeyGen Avatar 6 is priced by the length of your audio, from $0.112 per second of audio. 2K costs more per second than 1080p. Use the cost calculator on this page for exact estimates.
How HeyGen Avatar 6 compares to other avatar models
OmniHuman 2 adds expressive full-body gesture. Kling Avatar 2 Pro focuses on stable hands and body movement. VEED Fabric 1.0 is the low-cost option at 480p or 720p. HeyGen Avatar 6 is the one to pick for 2K output and prompt-directed expression. To animate a cartoon or illustrated character instead of a photo, use HeyGen Avatar 6 Character.
Who HeyGen Avatar 6 is for
Storytelling and documentary-style pieces
Bring a character portrait to life for a monologue or a short scene, with the emotional beats of the voice showing on the face.
Marketing and spokesperson videos
Turn a founder or brand portrait into a talking pitch without a shoot.
Training and explainers
Give lessons a presenter from a single photo, and record new lines whenever the script changes.
More video models
All modelsSeedance 2.5
ByteDance Seed Team
- Text to video
- Image to video
- Reference to video
- Video extension
- Video editing
From $0.120 per second of video
Seedance 2.0
ByteDance Seed Team
- Text to video
- Image to video
- Reference to video
- Video extension
- Video editing
From $0.079 per second of video
Seedance 2.0 Fast
ByteDance Seed Team
- Text to video
- Image to video
- Reference to video
- Video extension
- Video editing
From $0.063 per second of video



















