AI Video Generator with Audio
Silent clips need a second tool; clips with sound are ready to post. Turn on audio in the composer and the router restricts itself to models that generate sound with the picture, so footsteps, rain and dialogue land in sync. For speech you write, use the talking avatar or lip sync paths described below. Not every model produces native audio, and the page says which do.
Sign in to see your credit estimate. Creating needs a plan, from $4.99 a week.
Four ways to get sound
Native audio
Audio-capable models generate ambience, effects and even dialogue in the same pass as the video. Describe the sound in the prompt.
Generated voiceover
Type a script, pick a voice, and attach the speech as a reference track for the video to follow.
Talking avatar
A portrait plus speech becomes a presenter with synced lips and natural head motion.
Lip sync
Re-time the mouth in an existing video to new audio, for dubbing or fixing a line.
How the audio toggle changes routing
With audio on, only models flagged as audio-capable in the registry are candidates. Cinematic and Story presets favour them by default; Fast does not, because the fastest models are silent. The quote reflects any audio surcharge for the routed model.
If you attach a reference audio track instead, the router prefers models that can follow an external track, and the clip is timed to it.
Prompts that describe sound
Click one to load it into the composer on this page.
Models that generate native audio
Live from our model registry. Availability and specs update as models change.
Veo 3.1
Premium maximum-quality video with native audio.
Seedance 2.0
Balanced cinematic video with strong motion and reference support.
Kling 3.0
Narrative multi-shot video generation.
Not every model produces native audio. When you pick a preset or pin a model that is silent, the composer says so and offers the voiceover and lip-sync paths instead.
Private by default, publishable in one tap
Private library
Every creation is stored privately with its prompt, settings and model, so you can rerun, tweak or download it later.
Visibility controls
Publish as public, followers-only, unlisted or private, and decide whether others may remix.
Downloads
Full-resolution files, permanently hosted on our storage, downloadable from the library at any time.
Remix lineage
If you do publish, remixes credit you and appear under your original.
Frequently asked
- Can I write exact dialogue?
- Yes. Native-audio models follow quoted lines in the prompt reasonably well for short exchanges. For precise delivery, generate the speech first with a voice and attach it, or use the talking avatar.
- Can I add my own music?
- Attach it as a reference audio track and the router picks models that can follow it. For finished edits, you can also add music in your editor after download.
- Which languages are supported for voices?
- Generated voices cover major languages. Uploaded audio works in any language for lip sync and reference tracks.
- 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.