Learn Hedra
Talking characters from a picture and a voice. Upload an image, add audio or text, and get an expressive performance.
What Hedra is good at
- Talking-head and character videos from one image
- Audio upload or text-to-speech
- Expressive faces for explainers and social
- Stylised characters as well as photos
Quickstart
- Prepare a clear faceFront-facing, well lit, no heavy occlusion. Illustrated characters work too.
- Add the voiceUpload clean audio or type a script for text-to-speech.
- Set expression and motionWhere offered, tune how animated the character is; subtle reads as more natural.
- Keep the script with the clipThe script and the source image are the record; store them together.
Settings cheat-sheet
| Setting | What it does | Start with |
|---|---|---|
| Image | The character's face | Front-facing, well lit |
| Audio / script | Upload or text-to-speech | Clean audio |
| Voice | Built-in voices for TTS | Match the character |
| Expression | How animated the face is | Subtle |
| Aspect ratio | Portrait, square, landscape | Match the placement |
Hedra guides
Guides for Hedra are on their way. The quickstart and cheat-sheet above are kept current in the meantime.
The five most-asked questions
What does Hedra do?
Hedra animates a character from a single image to speak an audio track or a typed script, with lip sync and facial expression. It is used for presenters, characters and social explainers.
What input do I need?
One clear image of the character and either an audio file or a script for the built-in voices. Clean audio gives cleaner lip sync.
Can I use my own voice recording?
Yes, upload your recording; keep it free of music and noise. Check Hedra's terms on voice cloning and consent before using someone else's voice.
How long can a clip be?
Length limits depend on the plan and model version. Split long scripts into sections and cut them together.
Is Hedra free to try?
There is a free tier with limits and paid plans with more credits and resolution. Check the current pricing page.