Live studio · image, video & voice
Generate AI media. Keep every output.
Run text-to-image, video, and TTS on fal.ai and RunPod with transparent credits — or connect Higgsfield for BYOK. History and assets stay in one library.
What you can do today
Image, video, voice, character swap, and assets are live. Custom LoRA training is not offered.
Image generate & edit
Text-to-image and image-to-image in one workbench. Pick a model, set aspect and batch, and run—credits debit only after a successful generation.
Video
Text-to-video, image-to-video, motion control, edits, and background removal — with duration, resolution, and aspect matched to each model.
Voice / TTS
Turn scripts into speech with Dia, F5-TTS, or MiniMax. Preview and save clips alongside your other assets.
Character swap
Drop a source face and target scene, compare models side by side, and save swapped outputs to your library.
Assets library
Every successful run lands in Assets—filter by type, preview full size, download originals, and bulk-delete when you are done.
Credits
Transparent per-run costs for image, video, and voice. Your balance and ledger live in the header and account page.
Open the studio
Sign up, verify your email, and head to Generate. Your work saves to Assets automatically.