| .. |
|
__init__.py
|
Initial release — OpenMontage: the first open-source agentic video production system
|
2026-03-29 08:25:17 -07:00 |
|
audio_energy.py
|
Animation pipeline: AnimeScene engine, Ghibli-style compositions, audio energy tool, and README showcase
|
2026-03-31 17:40:50 -07:00 |
|
audio_probe.py
|
One-key formula: AI images, TTS narration, auto music, subtitles, and self-review pipeline
|
2026-03-30 16:54:13 -07:00 |
|
azure_stt.py
|
feat(stt): add Azure AI Speech as an optional cloud speech-to-text provider
|
2026-07-10 23:30:19 +05:30 |
|
composition_validator.py
|
hyperframes: add HTML/CSS/GSAP as a parallel composition runtime
|
2026-04-18 18:37:00 -07:00 |
|
dashscope_asr.py
|
dashscope: fix multi-image download and complete idempotency keys
|
2026-07-02 00:37:51 +08:00 |
|
face_tracker.py
|
Talking-head pipeline: 8 new tools, Remotion TalkingHead composition, and skill rewrites
|
2026-04-01 10:00:15 -07:00 |
|
frame_sampler.py
|
Add reference video input analysis workflow
|
2026-04-04 10:01:11 -07:00 |
|
scene_detect.py
|
fix: preserve subprocess error type in tool runner
|
2026-07-03 22:00:38 +08:00 |
|
transcriber.py
|
fix: recover bounded defects from PR backlog
|
2026-08-03 02:14:01 -07:00 |
|
transcript_fetcher.py
|
Add reference video input analysis workflow
|
2026-04-04 10:01:11 -07:00 |
|
video_analyzer.py
|
Add per-scene motion classification to video analyzer
|
2026-04-04 11:33:33 -07:00 |
|
video_downloader.py
|
Add reference video input analysis workflow
|
2026-04-04 10:01:11 -07:00 |
|
video_understand.py
|
Initial release — OpenMontage: the first open-source agentic video production system
|
2026-03-29 08:25:17 -07:00 |
|
visual_qa.py
|
Harden talking-head pipeline: Watch & Propose creative overlays, fix Round 1 gaps
|
2026-04-01 11:03:15 -07:00 |
9482eddeff