Audio Input
input
NodeTool Cloud is in alpha. Direct films and run workflows in the browser, on your own keys.NodeTool Cloud is in alpha. Try it →
Drop in a track and a visual style. The workflow transcribes the lyrics, reads the song's mood, renders one still per frame, and holds each still for an equal share of the track.
Script, storyboard, footage, sound, and the cut — on one canvas, with the editing tools sitting right next to the models. You direct the whole piece instead of generating parts of it.

Draft a script, choose a voice for each character and compare different readings of a line.
Create images, video, speech and music with models such as Flux, Seedance, Wan, Whisper and Suno, or voices from ElevenLabs. Connect your provider accounts or run supported models locally.
The agent arranges clips and audio in a timeline. Trim shots, adjust timing and change the soundtrack yourself.
Mask, retouch, extend, relight, upscale, layer, and composite. The tools you reach for live on the same canvas as the models.
Yes. Feed any audio file into the workflow. It transcribes the lyrics for the prompts and uses the track length to time the frames.
A speech recognition model for the lyrics, a language model for the prompts, and a text-to-image model for the stills. Pick each on your own keys. The template makes stills, not generated video clips.
Not this template. It spaces the stills evenly. The agent can detect the tempo with detect_audio_events, write a treatment with the music-video-treatment skill, and cut the timeline on the beat with the beat-sync-editing skill.
No. Open the template in NodeTool Studio, connect your keys, and run it. Rewire nodes on the canvas to change the look.
Download the open-source studio for macOS, Windows, and Linux. Open the template and direct it yourself, on your own keys.