Skip to main content

Beatoven — painting a portrait

Beatoven

PyPI Python

Compose hierarchical animation & simulation plans, generate full library-backed code, play it back, and inline-edit with .edit.

Beatoven turns a prompt into a playable AnimationObject:

  • Imports full capability surfaces for GSAP, Anime.js, Motion, Theatre.js, Typed.js, Three.js, Lottie, Manim, MoviePy, Textual, Bevy, Unity, libGDX, and more
  • SLM / cloud guided compose binds real library APIs (not a tiny subset) via heuristic, local Qwen, or OpenAI/Claude/Grok
  • Builds a hierarchy plan: scene → acts → shots → layers → tracks → keyframes
  • Supports draft → finalize and Deep Mode cinematic enhancement
  • Returns runnable code (not stubs) plus a built-in web player
  • anim.edit(...) / anim.deep(...) for inline revisions and capability-max enhancements
  • Optional Hugging Face SLM (hardware-sized Qwen) or cloud providers when API keys are set

Install

From PyPI (recommended)

pip install beatoven pulls the full dependency stack — play (Pillow), video (MoviePy / imageio-ffmpeg), cloud clients (OpenAI + Anthropic), and local SLM (torch / transformers / accelerate / huggingface_hub):

pip install beatoven
pip install -U beatoven
beatoven --help
python -c "from beatoven import compose; print(compose('Type Hi', provider='heuristic').summary())"
pip install "beatoven[dev]"   # pytest, ruff, build, twine

Package: https://pypi.org/project/beatoven/

From source (development)

git clone https://github.com/ehallford11714/beatoven.git
cd beatoven
python -m venv .venv
.\.venv\Scripts\pip install -e ".[dev]"
python -m pytest -q

Quick start

from beatoven import compose

anim = compose(
    "Type 'Beatoven' letter-by-letter, then drop a rubber ball in a Three.js room",
    languages=["javascript", "python"],
    provider="heuristic",  # or auto / local / openai / claude / grok
)

print(anim.plan.summary())
print(anim.code["javascript"][:400])

anim.play()  # opens browser player

anim.edit("make the title blue and stagger faster")
anim.edit(path="scene/act1/shot1/title", props={"text": "Beatoven Live"})
anim.export("out/index.html")

Draft + edit

anim = compose("Type 'Draft Scene' + bouncing ball", draft=True)
anim.edit("use Typed.js style typing; title color cyan")
anim.finalize()
anim.play()

Grounded iterative satisfaction

Compose now verifies the plan/code against the prompt using a documentation contract (libraries, physics, engines, typing) and iteratively repairs gaps until the threshold is met (default on):

anim = compose(
    "Type 'Nova' then drop a rubber ball in a Babylon physics room",
    provider="heuristic",
    grounded=True,              # default
    max_ground_iters=3,
    satisfaction_threshold=0.85,
)
print(anim.verify().summary())  # [PASS] score=...
anim.ground(max_iters=2)        # force another grounded repair loop

Direct object playback (showWhenDone)

Playback is no longer HTML-only. You get a live Python / JS / IR player object:

anim = compose("Type 'Beatoven' then bounce a ball", provider="heuristic")

# Python player object — samples IR, shows native window when done
player = anim.play(runtime="python", show_when_done=True)
print(player.sample(1.0))

# JavaScript-facing object (dict) for hosts / notebooks
js = anim.to_js_object(show_when_done=True)
print(js["type"], js["duration"])

# Force classic HTML file preview
anim.play(runtime="web", object_playback=False, show_when_done=True)

Deep Mode + multicascade

Deep Mode expands capability coverage. Cascade runs multi-pass SLM/heuristic refinement (structure → physics → cinematography → detail → engine bind) for Babylon / Unity / Bevy / Three complex scenes:

anim = compose(
    "Babylon physics room with stacked boxes and a bouncing ball",
    provider="auto",
    cascade=True,
    cascade_passes=4,
)
print(anim.plan.enhancements["cascade"])
anim.play(runtime="python", show_when_done=True)

anim.deep("more cinematic camera and bloom")
anim.cascade("richer multi-body physics", passes=3)

CLI

python -m beatoven compose --prompt "Type 'Hello' then bounce a ball" --lang javascript,python --play
python -m beatoven compose --prompt "..." --deep --play
python -m beatoven compose --prompt "Babylon physics stack" --cascade --cascade-passes 4 --play
python -m beatoven compose --prompt "..." --draft --out out
python -m beatoven edit out/beat.json --instruction "make the title blue and stagger faster"
python -m beatoven deep out/beat.json --instruction "cinematic bloom + dolly" --play
python -m beatoven cascade out/beat.json --passes 4 --play
python -m beatoven play out/beat.json --runtime python
python -m beatoven play out/beat.json --runtime web --html
python -m beatoven export out/beat.json --out out/clip.html
python -m beatoven catalog --domain text_ui
python -m beatoven probe

Providers

Value Behavior
auto Cloud if API key present → else local Qwen when configured → else heuristic
openai / claude / grok Cloud APIs
openai_compatible BEATOVEN_LLM_BASE_URL + key + model
local On-device Qwen/HF sized via hardware probe
heuristic Offline catalog + hierarchy planner

Environment: OPENAI_API_KEY, ANTHROPIC_API_KEY, XAI_API_KEY / GROK_API_KEY, BEATOVEN_LLM_API_KEY, BEATOVEN_LLM_BASE_URL, BEATOVEN_LLM_MODEL, BEATOVEN_PROVIDER, BEATOVEN_LOCAL_MODEL.

Documentation

Doc Description
docs/INDEX.md Docs home
docs/TUTORIAL.md Step-by-step tutorial
docs/API.md Public API reference
docs/COMPONENTS.md Every module explained
docs/CLI.md CLI reference
docs/LIBRARIES.md Capability pack catalog
docs/ARCHITECTURE.md Pipeline & Deep Mode

Example prompts

See examples/prompts.md. Runnable scripts:

  • examples/text_typing_web.py
  • examples/draft_and_edit.py
  • examples/threejs_physics_scene.py
  • examples/deep_mode_demo.py

Layout

src/beatoven/     # library
  capabilities/   # full API surfaces per library
  generators/     # JS / Python / Rust / C# / Java
  runtime/        # play + export
  providers/      # heuristic / local / cloud
tests/
examples/
docs/             # tutorial, API, components, CLI, libraries

License

MIT

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

beatoven-0.5.0.tar.gz (68.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

beatoven-0.5.0-py3-none-any.whl (77.5 kB view details)

Uploaded Python 3

File details

Details for the file beatoven-0.5.0.tar.gz.

File metadata

  • Download URL: beatoven-0.5.0.tar.gz
  • Upload date:
  • Size: 68.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.11.3

File hashes

Hashes for beatoven-0.5.0.tar.gz
Algorithm Hash digest
SHA256 f62a02ca0245500d447a6c3a6e3d4bce7dfaa822ba96e5a71c7b5d5c26cea814
MD5 6ffa065d7f7b0df817cbda36353f7ae2
BLAKE2b-256 29134d4a4c34fbf79082794d570bb98d02d0b28b083d013dabef38af39a6a95e

See more details on using hashes here.

File details

Details for the file beatoven-0.5.0-py3-none-any.whl.

File metadata

  • Download URL: beatoven-0.5.0-py3-none-any.whl
  • Upload date:
  • Size: 77.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.11.3

File hashes

Hashes for beatoven-0.5.0-py3-none-any.whl
Algorithm Hash digest
SHA256 a8a1b07117a2652c25dc993e604dd6a6184cf1e7bee756e480f4125af6d4808b
MD5 2e69824619ebb879417e51b1ea9ec3bf
BLAKE2b-256 7a637645dc8b3ce0d302011b07f1c16d803d8a9c0a76c8d789804f687f852a6d

See more details on using hashes here.

Release history Release notifications | RSS feed

0.12.1

2 files

0.12.0

2 files

0.9.0

2 files

0.8.0

2 files

0.7.0

2 files

0.6.0

2 files

This release

0.5.0 This release

2 files

0.4.0

2 files

0.3.0

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page