Diffusion Studio vs Rescript

Diffusion Studio is an AI video editor that pairs an infinite canvas with a timeline to organize connected scenes. It describes itself as an editor for agents and people, with edits written to a codebase that coding agents can read, change, and render. Controls cover timing, position, scale, layout, effects, audio mixing, filters, Bezier curves, spring easing, and motion presets. Agents can analyze footage, edit and animate scenes, generate video, images, audio, and sound effects, transcribe, localize, add captions, and export. The site lists integrations with Claude Code, Codex, Cursor, VS Code with Copilot, Antigravity, Gemini CLI, Devin (Windsurf), and other agents that support MCP. Every plan includes unlimited exports up to 4K without watermarks, and exports do not consume credits. The web editor, desktop app, dapi CLI, and skills are open source under MPL 2.0. It is available on web, Windows, macOS, Linux, and API. Free includes 50 one-time credits; Pro is $19 a month, billed annually, with 2,500 credits monthly.

Rescript is a text-based video and audio editor available on web, Windows, macOS and Linux. Transcription, editing, voice generation and export run on the user's device, and video and audio files are not uploaded for those tasks. Features include automatic captions and silence removal, and users can import SRT, VTT or JSON caption files. Exports include MP4, WebM, M4A, MP3, WAV, TXT, Markdown, SRT, VTT and JSON, with a maximum listed resolution of 4K. Voice regeneration supports English, Spanish, French, German, Italian and Portuguese; cloning another person's voice requires consent. Local features are free without an account, trial or usage meter, but free use is noncommercial under the PolyForm Noncommercial 1.0.0 license. Commercial use requires a paid license. A Chromium-based browser is recommended, with a WASM fallback for WebGPU. The Whisper model downloads once from Hugging Face and is cached.