Tools

One default tool for each stage

Script2Film does not synthesize voices, generate video or edit by itself. It splits a film into stages, connects an existing tool to each, and passes work between stages only as files in a folder. That is why any stage can be swapped for the tool you prefer.

Core flow

All of these run on your computer, free

The first example uses only this part. You install the models and packages yourself; the install check tells you what is missing.

Narration

Qwen3-TTS

Local speech synthesis. About ten seconds of reference audio is enough to match your voice, or you can design a synthetic voice from a text description.

Runs on
Your computer
Cost
Free, open source (Apache-2.0)
Swap for
Any other voice tool, such as CloneVoice.ai
Timing and subtitles

whisper.cpp

Transcribes the finished narration back to text and measures when every word is spoken. Take picking, subtitles and the timing of visuals all depend on it.

Runs on
Your computer
Cost
Free, open source
Swap for
Groq or ElevenLabs Scribe (cloud, needs a key, and the narration audio is sent out)
Code-drawn visuals

HyperFrames + GSAP

Each of the 27 scenes is a web animation that HyperFrames captures frame by frame into video. The scene code is in this project.

Runs on
Your computer
Cost
Free (HyperFrames is Apache-2.0; GSAP has its own no-charge license)
Swap for
Scenes you write yourself with AI
Assembly and check

HyperFrames + ffmpeg

Joins narration, visuals and subtitles into one film. Every exported film is measured for length, black frames, loudness and whether the sound effects made it into the mix; explainers also get the check sheet.

Runs on
Your computer
Cost
Free, open source
Swap for
Works well with Concat, which is free and open source
Music and sound effects

Composed music + CC0 sound effects

Background music is written by the project's composer program from the on-screen events and rendered offline with a SoundFont. Sound effects are Kenney's CC0 assets and some made in-house.

Runs on
Your computer
Cost
Free; you download the SoundFont yourself
Swap for
Your own music (credit CC BY tracks), or a song made with MiniMax Music 3 below
Fonts

Noto Sans TC, Noto Serif TC

The fonts used for visuals and subtitles. The license text ships next to the font files. Two optional fonts, LXGW WenKai and jf open-huninn, are listed with their original download links.

Runs on
The asset layer that ships with the project
Cost
Free (SIL OFL 1.1)
Swap for
Any font you have a license for
Optional

For live footage, a host, generated video of any kind, or a song, consider these options

All of them are optional: you can make a film without them. When you connect one, the tool works inside the account you logged in to yourself: submit, wait, collect, check. The agent asks before spending credits or compute units, and you type your own account name and password.

Generated shots

VideoExpress

Video from text or images. Script2Film works out how long each shot must be, writes the prompts, lays them out as a run sheet, submits and collects them, then measures the clips and checks for bad first and last frames. The project also includes a full set of prompt-writing rules and storyboard tools for VideoExpress.

Runs on
VideoExpress's service
Cost
A one-time-purchase AI video platform with no further fees; output can be used commercially.
Swap for
Any video generator (Seedance, Kling and so on): generate to the run sheet's durations and prompts, then put the files back in the folder under the expected names
About VideoExpress (lifetime plan, about US$143)
Host

TalkingPhotos

One portrait plus text or audio makes a lip-synced host. Script2Film cuts the narration into segments, uploads the look image, submits each segment, collects the results and places them back on the timeline as a circle, a side frame or full frame.

Runs on
TalkingPhotos's service
Cost
A one-time-purchase AI presenter video platform with no further fees; output can be used commercially.
Swap for
Any lip-sync tool: feed it each audio segment and put the results back under the same file names
About TalkingPhotos (lifetime plan, about US$78)
Generated shots and host

MiniMax H3 (needs a Google Colab account)

An open-weight video model that generates on the Colab GPU of your own Google account. The narration recording drives the host, so the lips follow it, and the prompt can make the person gesture, walk while talking, or film a handheld selfie vlog. It can also generate shots and extend them. Script2Film cuts the narration into parts of 15 s or less, writes the host prompts, checks which country the machine is in before booting, and puts the results back on the timeline.

Runs on
The Colab GPU of your own Google account; your computer needs no graphics card
Cost
Needs Google AI Pro (it includes Colab compute units). Measured on an L4: a 12 s host part takes about 4 minutes; a dozen test clips used about 2 units
License
The open-weight license does not cover the United States, the European Union, the United Kingdom or South Korea; it cannot be used there
Swap for
VideoExpress or TalkingPhotos above, or any tool whose results can be put back under the expected file names
How to connect MiniMax H3
Music and songs

MiniMax Music 3 (needs a Google Colab account)

An open-weight music model. Give it lyrics and a description of the style, and it makes a song with vocals or an instrumental; it can sing in Taiwanese Hokkien and Mandarin. Script2Film writes the job, boots the GPU, generates, downloads and releases the machine, then sets the WAV as the film's background music; you can also paste the code into a Colab notebook yourself.

Runs on
The Colab GPU of your own Google account; your computer needs no graphics card
Cost
Needs Google AI Pro (it includes Colab compute units). Measured on an L4: a 60 s song takes about 5 minutes; booting and one song use about 0.3 to 0.5 units
License
No territory limits; the lyrics must be your own, and published work must be labelled as AI-generated
Swap for
The program-composed music above, or any music you have a license for
How to use MiniMax Music 3

Disclosure: the VideoExpress and TalkingPhotos buttons, and the CloneVoice.ai link in the narration card above, are referral links. The author uses VideoExpress and TalkingPhotos every week. If you buy through a link the author receives a small commission, and the price you pay is the same (prices as of November 2026). The core flow works fully without either.

Optional

Want to write better storyboards and prompts

If you want to get better at writing for video, try writing by hand with this small tool that comes with the project.

Writing and prompts

Prompt Studio

Helps you expand an idea into a storyboard and prompts, for practice or to compare with a storyboard an agent wrote. Its patterns are tuned for VideoExpress. How to split shots, describe characters and write dialogue is worth a look with other AI video tools, but none of it has been tested on any other platform.

Runs on
Your browser (a single HTML file)
Cost
Free, included with the project (MIT)
Swap for
Letting the agent write the storyboard (a separate rule set)
About Prompt Studio
Optional

An editor, and publishing

Overlays, still editable

Concat

A free, open-source video editor. Script2Film writes an edit plan and sends it straight into Concat: the host frame, keywords, chapter labels and music are all on the timeline, and you can keep adjusting.

Runs on
Your computer
Cost
Free, open source, and scriptable over MCP
Swap for
You get a finished film without it
Publishing

YouTube API

Upload, scheduling, thumbnail, description and the altered-content label. You complete the authorization yourself in the browser, and whether to upload and when to publish is entirely up to you.

Runs on
Google's service
Cost
Free (needs your own Google Cloud project)
Swap for
Uploading by hand

What each stage reads and writes, and how to name files when you use another platform, is in the flow document. The license of every package and asset is listed in the notice file.