Orkas-VideoStudio

Name: Orkas-VideoStudio
Author: Orkas-AI

390stars16forks

How to install Orkas-VideoStudio?

orkas-ai/orkas-videostudio

$git clone https://github.com/Orkas-AI/Orkas-VideoStudio

Installs into the current project.

Summary

> Drive video composition, generation, and editing — and a fully automatic end-to-end > pipeline — from your coding agent. Claude Code, Codex, Cursor: any agent that can run a > shell or speak MCP can use it.

Files · 1

View on GitHub

README.md

1	# OrkasVideoStudio
2
3	> Drive video composition, generation, and editing — and a fully **automatic end-to-end
4	> pipeline** — from your coding agent. Claude Code, Codex, Cursor: any agent that can run a
5	> shell or speak MCP can use it.
6
7	https://github.com/user-attachments/assets/13411470-06da-4f64-9bc1-fa52fe27216b
8
9	OrkasVideoStudio is not a black-box video agent. A video is expressed as a readable,
10	diffable, re-renderable plan (`plan.json`) that your agent — and you — can edit; change one
11	line and only that piece re-renders. The agent is the brain; this project ships the
12	knowledge (what makes a good video, and which production line to take), the
13	deterministic capabilities (render / edit / transcribe / generate — thin wrappers over
14	[`hyperframes`](https://github.com/heygen-com/hyperframes), `ffmpeg`, and `whisper.cpp`), and
15	that editable IR.
16
17	You talk to your agent in plain language — *"make a 60-second vertical explainer on vector
18	databases with a Chinese voiceover and captions"* — and it reads the material, writes the
19	timeline, and produces the file.
20
21	---
22
23	## The four production lines
24
25	Three orthogonal capability axes, plus an automatic pipeline that weaves them together:
26
27	- Compose — script → designed HTML motion graphics → mp4. Explainers, kinetic typography,
28	lower-thirds, data viz, title cards, transitions. No paid keys.
29	- Edit — cut / join / trim-silence / de-filler / mix / burn-in subtitles / dub / localize
30	real footage you supply, plus highlight selection over long recordings. No paid keys.
31	- Generate — talking-head or cinematic AI footage and imagery via your own provider
32	keys (BYO — OpenAI, Gemini, Doubao; no managed backend, no lock-in).
33	- Auto (end-to-end) — when a deliverable needs more than one axis, the agent routes to a
34	single cross-modal `plan.json`: `stage-plan` builds the EDL, `stage-assemble` walks it and
35	delegates each segment back to compose / generate / edit, and a deterministic
36	delivery guard (`ovs plan promise-check`) verifies the finished cut keeps its promise
37	(e.g. real motion, not a silent slideshow) before anything ships.
38
39	The plan is the contract: *"the footage in the middle, generate an opener, compose the stats,
40	one voiceover over all of it"* becomes one editable file where every segment, caption, and
41	narration line is independently re-renderable.
42
43	---
44
45	## Relationship to Orkas
46
47	OrkasVideoStudio began life as the built-in video agent inside [Orkas](https://orkas.ai) —
48	the AI-team desktop app — where it was validated end-to-end, then extracted into this
49	agent-agnostic, MIT-licensed toolkit.
50
51	- Inside Orkas it ships as a built-in agent — no separate install; the zero-key trunk
52	works out of the box.
53	- Everywhere else you install it into your own coding agent (below) and get the same
54	capabilities via the `ovs` CLI and MCP server.
55
56	Links: [orkas.ai](https://orkas.ai) (website) · [github.com/Orkas-AI](https://github.com/Orkas-AI)
57	(open-source projects) · [this repo](https://github.com/Orkas-AI/Orkas-VideoStudio).
58
59	---
60
61	## Use cases
62
63	Each is a real prompt you'd give your agent; the router picks the line for you.
64
65	\| You say… \| Line \| What happens \|
66	\|---\|---\|---\|
67	\| "Make a 60s vertical explainer on what a vector DB is, Chinese voiceover + captions." \| Compose \| HTML motion-graphic scenes → narration (BYO TTS) → burned-in captions → mp4. \|
68	\| "Turn this 1-hour screen recording into three 30s highlight clips with captions." \| Edit \| `scenes`/`quality` find the good parts, `rank-takes` picks, `trim-silence`/`remove-fillers` tighten, subtitles burned in. \|
69	\| "Add an English voiceover + subtitles to product-demo.mp4 and normalize the loudness." \| Edit \| transcribe → localize → `speak` → `mix` → `burnsubs` → loudness pass. \|
70	\| "Clean the silences and 'um's out of my webcam take and tighten it." \| Edit \| deterministic jump-cut with an auditable evidence trail. \|
71	\| *"Generate a 5s cinematic shot of a city at dawn fo

People who liked this also viewed

6 picks

Type

Orkas-VideoStudio

390stars16forks

View on GitHub

How to install Orkas-VideoStudio?

orkas-ai/orkas-videostudio

$git clone https://github.com/Orkas-AI/Orkas-VideoStudio

Installs into the current project.

Summary

Files · 1

View on GitHub

README.md

1	# OrkasVideoStudio
2
3	> Drive video composition, generation, and editing — and a fully **automatic end-to-end
4	> pipeline** — from your coding agent. Claude Code, Codex, Cursor: any agent that can run a
5	> shell or speak MCP can use it.
6
7	https://github.com/user-attachments/assets/13411470-06da-4f64-9bc1-fa52fe27216b
8
9	OrkasVideoStudio is not a black-box video agent. A video is expressed as a readable,
10	diffable, re-renderable plan (`plan.json`) that your agent — and you — can edit; change one
11	line and only that piece re-renders. The agent is the brain; this project ships the
12	knowledge (what makes a good video, and which production line to take), the
13	deterministic capabilities (render / edit / transcribe / generate — thin wrappers over
14	[`hyperframes`](https://github.com/heygen-com/hyperframes), `ffmpeg`, and `whisper.cpp`), and
15	that editable IR.
16
17	You talk to your agent in plain language — *"make a 60-second vertical explainer on vector
18	databases with a Chinese voiceover and captions"* — and it reads the material, writes the
19	timeline, and produces the file.
20
21	---
22
23	## The four production lines
24
25	Three orthogonal capability axes, plus an automatic pipeline that weaves them together:
26
27	- Compose — script → designed HTML motion graphics → mp4. Explainers, kinetic typography,
28	lower-thirds, data viz, title cards, transitions. No paid keys.
29	- Edit — cut / join / trim-silence / de-filler / mix / burn-in subtitles / dub / localize
30	real footage you supply, plus highlight selection over long recordings. No paid keys.
31	- Generate — talking-head or cinematic AI footage and imagery via your own provider
32	keys (BYO — OpenAI, Gemini, Doubao; no managed backend, no lock-in).
33	- Auto (end-to-end) — when a deliverable needs more than one axis, the agent routes to a
34	single cross-modal `plan.json`: `stage-plan` builds the EDL, `stage-assemble` walks it and
35	delegates each segment back to compose / generate / edit, and a deterministic
36	delivery guard (`ovs plan promise-check`) verifies the finished cut keeps its promise
37	(e.g. real motion, not a silent slideshow) before anything ships.
38
39	The plan is the contract: *"the footage in the middle, generate an opener, compose the stats,
40	one voiceover over all of it"* becomes one editable file where every segment, caption, and
41	narration line is independently re-renderable.
42
43	---
44
45	## Relationship to Orkas
46
47	OrkasVideoStudio began life as the built-in video agent inside [Orkas](https://orkas.ai) —
48	the AI-team desktop app — where it was validated end-to-end, then extracted into this
49	agent-agnostic, MIT-licensed toolkit.
50
51	- Inside Orkas it ships as a built-in agent — no separate install; the zero-key trunk
52	works out of the box.
53	- Everywhere else you install it into your own coding agent (below) and get the same
54	capabilities via the `ovs` CLI and MCP server.
55
56	Links: [orkas.ai](https://orkas.ai) (website) · [github.com/Orkas-AI](https://github.com/Orkas-AI)
57	(open-source projects) · [this repo](https://github.com/Orkas-AI/Orkas-VideoStudio).
58
59	---
60
61	## Use cases
62
63	Each is a real prompt you'd give your agent; the router picks the line for you.
64
65	\| You say… \| Line \| What happens \|
66	\|---\|---\|---\|
67	\| "Make a 60s vertical explainer on what a vector DB is, Chinese voiceover + captions." \| Compose \| HTML motion-graphic scenes → narration (BYO TTS) → burned-in captions → mp4. \|
68	\| "Turn this 1-hour screen recording into three 30s highlight clips with captions." \| Edit \| `scenes`/`quality` find the good parts, `rank-takes` picks, `trim-silence`/`remove-fillers` tighten, subtitles burned in. \|
69	\| "Add an English voiceover + subtitles to product-demo.mp4 and normalize the loudness." \| Edit \| transcribe → localize → `speak` → `mix` → `burnsubs` → loudness pass. \|
70	\| "Clean the silences and 'um's out of my webcam take and tighten it." \| Edit \| deterministic jump-cut with an auditable evidence trail. \|
71	\| *"Generate a 5s cinematic shot of a city at dawn fo

People who liked this also viewed

6 picks

Type