AI Talking Avatar Generator
Upload one portrait, paste a script or record your voice, and generate a presenter video with synchronised lips, blinking and subtle head movement. Use it for explainers, greetings, course intros, or to give one of your saved characters a voice. The composer below is in Avatar mode: it needs a portrait and an audio source, and it quotes the cost before you run.
Add a portrait
Front-facing, well lit
Add voice audio
MP3, WAV or M4A up to 50MB
Sign in to see your credit estimate. Creating needs a plan, from $4.99 a week.
How it works
- 01
Choose a face
A clear, front-facing portrait: a photo, an illustration, or one of your saved characters.
- 02
Add speech
Type a script and pick a voice to generate it, or upload an MP3 or WAV for exact delivery and timing.
- 03
Optional performance notes
'Calm, confident, slight smile.' The prompt field guides expression rather than content.
- 04
Generate
Get a presenter clip framed for vertical or horizontal use, downloadable from your library.
Capabilities
Script to speech
Type text, choose a voice; no recording required. Voices cover major languages.
Your own audio
Upload a recording for exact wording, pacing and emotion.
Expressive motion
Natural blinking, micro-expressions and head turns, not a static mouth overlay.
Pets and fictional subjects
Illustrated characters and animals work where the routed model supports non-human faces.
Character-aware
Use a saved character so the presenter matches the rest of your videos.
Uses
- Course and onboarding videos
- Personalised greetings at scale
- Product walkthroughs and updates
- Character dialogue for stories
- Localised versions of the same message
Best input practices
- Front-facing, evenly lit portrait with the mouth visible and closed or neutral.
- Head and shoulders framing; avoid hands near the face.
- Clean audio without music for the most accurate sync.
- Keep scripts under a minute per clip; chain clips for longer pieces.
Avatar models in the registry
Live from our model registry. Availability and specs update as models change.
OmniHuman 1.5
Talking avatar from a portrait and audio.
Avatar templates
Frequently asked
- How long can the speech be?
- Durations depend on the routed model and your plan; the composer shows the maximum and the credit cost before you confirm.
- Can I use any photo?
- Use photos of yourself, people who have consented, or fictional faces. Impersonation is against the community guidelines.
- Which languages are supported?
- Generated voices cover major languages, and uploaded audio works in any language.
- Do I have to pick an AI model?
- No. Choose a style preset such as Fast, Cinematic or Story and the router selects the best available model for that intent, aspect ratio, duration and the inputs you attached. If a model is degraded, the router falls back to a comparable one without charging you twice. Advanced users can still pin a specific model.
- How much does a generation cost?
- Every generation is quoted in credits before you confirm, based on the routed model, duration and resolution. Credits are reserved when you start and released automatically if the generation fails, so you only pay for what completes. Plans start at $4.99 a week and include a credit allowance; subscribers can top up with credit packs.
- Are my generations private?
- Yes by default. Everything you generate lands in your private library. You decide per creation whether to publish it to the feed, share it unlisted, restrict it to followers or keep it private, and whether others may remix it.
- Can I download the videos?
- Yes. Every completed generation can be downloaded in full resolution from your library. Files are stored permanently on our own media storage, not on the provider's temporary links.
Related
Ready when you are.
Plans from $4.99 a week. Publish when you're proud of it.