video-to-context 0.5.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- video_to_context-0.5.0/.env.example +37 -0
- video_to_context-0.5.0/.gitignore +55 -0
- video_to_context-0.5.0/LICENSE +202 -0
- video_to_context-0.5.0/NOTICE +2 -0
- video_to_context-0.5.0/PKG-INFO +362 -0
- video_to_context-0.5.0/README.md +321 -0
- video_to_context-0.5.0/pyproject.toml +65 -0
- video_to_context-0.5.0/requirements.txt +24 -0
- video_to_context-0.5.0/tests/__init__.py +0 -0
- video_to_context-0.5.0/tests/test_mcp_server.py +151 -0
- video_to_context-0.5.0/tests/test_pipeline.py +428 -0
- video_to_context-0.5.0/video_to_context/__init__.py +10 -0
- video_to_context-0.5.0/video_to_context/audio.py +149 -0
- video_to_context-0.5.0/video_to_context/config.py +48 -0
- video_to_context-0.5.0/video_to_context/evaluate.py +94 -0
- video_to_context-0.5.0/video_to_context/fetch.py +75 -0
- video_to_context-0.5.0/video_to_context/hashing.py +12 -0
- video_to_context-0.5.0/video_to_context/mcp_server.py +412 -0
- video_to_context-0.5.0/video_to_context/merge.py +186 -0
- video_to_context-0.5.0/video_to_context/models.py +129 -0
- video_to_context-0.5.0/video_to_context/paths.py +19 -0
- video_to_context-0.5.0/video_to_context/probe.py +77 -0
- video_to_context-0.5.0/video_to_context/run.py +251 -0
- video_to_context-0.5.0/video_to_context/vision.py +480 -0
- video_to_context-0.5.0/video_to_context/visual.py +267 -0
|
@@ -0,0 +1,37 @@
|
|
|
1
|
+
# Copy this file to .env and choose ONE option. The tool still runs with none,
|
|
2
|
+
# using local OCR for on-screen text but without visual analysis.
|
|
3
|
+
|
|
4
|
+
# Option 1: Claude (default model: claude-haiku-5-5)
|
|
5
|
+
# ANTHROPIC_API_KEY=
|
|
6
|
+
|
|
7
|
+
# Option 2: Gemini
|
|
8
|
+
# VISION_BASE_URL=https://generativelanguage.googleapis.com/v1beta/openai/
|
|
9
|
+
# VISION_API_KEY=
|
|
10
|
+
# VISION_MODEL=gemini-3.8-flash
|
|
11
|
+
|
|
12
|
+
# Option 3: OpenAI
|
|
13
|
+
# VISION_BASE_URL=https://api.openai.com/v1
|
|
14
|
+
# VISION_API_KEY=
|
|
15
|
+
# VISION_MODEL=gpt-5.4-mini
|
|
16
|
+
|
|
17
|
+
# Option 4: OpenRouter (use a vision model from openrouter.ai/models)
|
|
18
|
+
# VISION_BASE_URL=https://openrouter.ai/api/v1
|
|
19
|
+
# VISION_API_KEY=
|
|
20
|
+
# VISION_MODEL=
|
|
21
|
+
|
|
22
|
+
# Option 5: Ollama, free and on your own machine (no API key)
|
|
23
|
+
# VISION_BASE_URL=http://localhost:11434/v1
|
|
24
|
+
# VISION_MODEL=gemma4:12b
|
|
25
|
+
# VISION_MAX_FRAMES=12
|
|
26
|
+
# VISION_REASONING_EFFORT=none
|
|
27
|
+
# VISION_TIMEOUT_S=600
|
|
28
|
+
|
|
29
|
+
# Optional: limit how many frames are sent to the model (default 90).
|
|
30
|
+
# VISION_MAX_FRAMES=30
|
|
31
|
+
|
|
32
|
+
# MCP server: folders AI tools may read videos from. Local files are off until this is set.
|
|
33
|
+
# Separate folders with ":" on macOS and Linux, or ";" on Windows.
|
|
34
|
+
# VIDEO_TEXT_ALLOWED_DIRS=/Users/you/Videos
|
|
35
|
+
|
|
36
|
+
# MCP server: where results are stored (default: store/ in this project).
|
|
37
|
+
# VIDEO_TEXT_STORE=/Users/you/video-text-store
|
|
@@ -0,0 +1,55 @@
|
|
|
1
|
+
# Python environments
|
|
2
|
+
.venv/
|
|
3
|
+
venv/
|
|
4
|
+
env/
|
|
5
|
+
.conda/
|
|
6
|
+
|
|
7
|
+
# Python build and cache files
|
|
8
|
+
__pycache__/
|
|
9
|
+
*.py[cod]
|
|
10
|
+
*.egg-info/
|
|
11
|
+
build/
|
|
12
|
+
dist/
|
|
13
|
+
.pytest_cache/
|
|
14
|
+
.mypy_cache/
|
|
15
|
+
.ruff_cache/
|
|
16
|
+
.coverage
|
|
17
|
+
htmlcov/
|
|
18
|
+
.ipynb_checkpoints/
|
|
19
|
+
|
|
20
|
+
# Secrets and local settings
|
|
21
|
+
.env
|
|
22
|
+
.env.*
|
|
23
|
+
!.env.example
|
|
24
|
+
.claude/settings.local.json
|
|
25
|
+
|
|
26
|
+
# Pipeline output and input media
|
|
27
|
+
store/
|
|
28
|
+
data/
|
|
29
|
+
tests/samples/*
|
|
30
|
+
!tests/samples/.gitkeep
|
|
31
|
+
*.mp4
|
|
32
|
+
*.mov
|
|
33
|
+
*.mkv
|
|
34
|
+
*.webm
|
|
35
|
+
*.m4a
|
|
36
|
+
*.wav
|
|
37
|
+
*.mp3
|
|
38
|
+
|
|
39
|
+
# Downloaded model weights
|
|
40
|
+
*.pt
|
|
41
|
+
*.pth
|
|
42
|
+
*.onnx
|
|
43
|
+
*.safetensors
|
|
44
|
+
*.gguf
|
|
45
|
+
|
|
46
|
+
# Logs and temporary files
|
|
47
|
+
*.log
|
|
48
|
+
*.tmp
|
|
49
|
+
|
|
50
|
+
# Editors and operating systems
|
|
51
|
+
.vscode/
|
|
52
|
+
.idea/
|
|
53
|
+
*.swp
|
|
54
|
+
.DS_Store
|
|
55
|
+
Thumbs.db
|
|
@@ -0,0 +1,202 @@
|
|
|
1
|
+
|
|
2
|
+
Apache License
|
|
3
|
+
Version 2.0, January 2004
|
|
4
|
+
http://www.apache.org/licenses/
|
|
5
|
+
|
|
6
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
7
|
+
|
|
8
|
+
1. Definitions.
|
|
9
|
+
|
|
10
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
11
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
12
|
+
|
|
13
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
14
|
+
the copyright owner that is granting the License.
|
|
15
|
+
|
|
16
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
17
|
+
other entities that control, are controlled by, or are under common
|
|
18
|
+
control with that entity. For the purposes of this definition,
|
|
19
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
20
|
+
direction or management of such entity, whether by contract or
|
|
21
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
22
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
23
|
+
|
|
24
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
25
|
+
exercising permissions granted by this License.
|
|
26
|
+
|
|
27
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
28
|
+
including but not limited to software source code, documentation
|
|
29
|
+
source, and configuration files.
|
|
30
|
+
|
|
31
|
+
"Object" form shall mean any form resulting from mechanical
|
|
32
|
+
transformation or translation of a Source form, including but
|
|
33
|
+
not limited to compiled object code, generated documentation,
|
|
34
|
+
and conversions to other media types.
|
|
35
|
+
|
|
36
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
37
|
+
Object form, made available under the License, as indicated by a
|
|
38
|
+
copyright notice that is included in or attached to the work
|
|
39
|
+
(an example is provided in the Appendix below).
|
|
40
|
+
|
|
41
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
42
|
+
form, that is based on (or derived from) the Work and for which the
|
|
43
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
44
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
45
|
+
of this License, Derivative Works shall not include works that remain
|
|
46
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
47
|
+
the Work and Derivative Works thereof.
|
|
48
|
+
|
|
49
|
+
"Contribution" shall mean any work of authorship, including
|
|
50
|
+
the original version of the Work and any modifications or additions
|
|
51
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
52
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
53
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
54
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
55
|
+
means any form of electronic, verbal, or written communication sent
|
|
56
|
+
to the Licensor or its representatives, including but not limited to
|
|
57
|
+
communication on electronic mailing lists, source code control systems,
|
|
58
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
59
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
60
|
+
excluding communication that is conspicuously marked or otherwise
|
|
61
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
62
|
+
|
|
63
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
64
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
65
|
+
subsequently incorporated within the Work.
|
|
66
|
+
|
|
67
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
68
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
69
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
70
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
71
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
72
|
+
Work and such Derivative Works in Source or Object form.
|
|
73
|
+
|
|
74
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
75
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
76
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
77
|
+
(except as stated in this section) patent license to make, have made,
|
|
78
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
79
|
+
where such license applies only to those patent claims licensable
|
|
80
|
+
by such Contributor that are necessarily infringed by their
|
|
81
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
82
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
83
|
+
institute patent litigation against any entity (including a
|
|
84
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
85
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
86
|
+
or contributory patent infringement, then any patent licenses
|
|
87
|
+
granted to You under this License for that Work shall terminate
|
|
88
|
+
as of the date such litigation is filed.
|
|
89
|
+
|
|
90
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
91
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
92
|
+
modifications, and in Source or Object form, provided that You
|
|
93
|
+
meet the following conditions:
|
|
94
|
+
|
|
95
|
+
(a) You must give any other recipients of the Work or
|
|
96
|
+
Derivative Works a copy of this License; and
|
|
97
|
+
|
|
98
|
+
(b) You must cause any modified files to carry prominent notices
|
|
99
|
+
stating that You changed the files; and
|
|
100
|
+
|
|
101
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
102
|
+
that You distribute, all copyright, patent, trademark, and
|
|
103
|
+
attribution notices from the Source form of the Work,
|
|
104
|
+
excluding those notices that do not pertain to any part of
|
|
105
|
+
the Derivative Works; and
|
|
106
|
+
|
|
107
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
108
|
+
distribution, then any Derivative Works that You distribute must
|
|
109
|
+
include a readable copy of the attribution notices contained
|
|
110
|
+
within such NOTICE file, excluding those notices that do not
|
|
111
|
+
pertain to any part of the Derivative Works, in at least one
|
|
112
|
+
of the following places: within a NOTICE text file distributed
|
|
113
|
+
as part of the Derivative Works; within the Source form or
|
|
114
|
+
documentation, if provided along with the Derivative Works; or,
|
|
115
|
+
within a display generated by the Derivative Works, if and
|
|
116
|
+
wherever such third-party notices normally appear. The contents
|
|
117
|
+
of the NOTICE file are for informational purposes only and
|
|
118
|
+
do not modify the License. You may add Your own attribution
|
|
119
|
+
notices within Derivative Works that You distribute, alongside
|
|
120
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
121
|
+
that such additional attribution notices cannot be construed
|
|
122
|
+
as modifying the License.
|
|
123
|
+
|
|
124
|
+
You may add Your own copyright statement to Your modifications and
|
|
125
|
+
may provide additional or different license terms and conditions
|
|
126
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
127
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
128
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
129
|
+
the conditions stated in this License.
|
|
130
|
+
|
|
131
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
132
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
133
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
134
|
+
this License, without any additional terms or conditions.
|
|
135
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
136
|
+
the terms of any separate license agreement you may have executed
|
|
137
|
+
with Licensor regarding such Contributions.
|
|
138
|
+
|
|
139
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
140
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
141
|
+
except as required for reasonable and customary use in describing the
|
|
142
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
143
|
+
|
|
144
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
145
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
146
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
147
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
148
|
+
implied, including, without limitation, any warranties or conditions
|
|
149
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
150
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
151
|
+
appropriateness of using or redistributing the Work and assume any
|
|
152
|
+
risks associated with Your exercise of permissions under this License.
|
|
153
|
+
|
|
154
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
155
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
156
|
+
unless required by applicable law (such as deliberate and grossly
|
|
157
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
158
|
+
liable to You for damages, including any direct, indirect, special,
|
|
159
|
+
incidental, or consequential damages of any character arising as a
|
|
160
|
+
result of this License or out of the use or inability to use the
|
|
161
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
162
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
163
|
+
other commercial damages or losses), even if such Contributor
|
|
164
|
+
has been advised of the possibility of such damages.
|
|
165
|
+
|
|
166
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
167
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
168
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
169
|
+
or other liability obligations and/or rights consistent with this
|
|
170
|
+
License. However, in accepting such obligations, You may act only
|
|
171
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
172
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
173
|
+
defend, and hold each Contributor harmless for any liability
|
|
174
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
175
|
+
of your accepting any such warranty or additional liability.
|
|
176
|
+
|
|
177
|
+
END OF TERMS AND CONDITIONS
|
|
178
|
+
|
|
179
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
180
|
+
|
|
181
|
+
To apply the Apache License to your work, attach the following
|
|
182
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
183
|
+
replaced with your own identifying information. (Don't include
|
|
184
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
185
|
+
comment syntax for the file format. We also recommend that a
|
|
186
|
+
file or class name and description of purpose be included on the
|
|
187
|
+
same "printed page" as the copyright notice for easier
|
|
188
|
+
identification within third-party archives.
|
|
189
|
+
|
|
190
|
+
Copyright [yyyy] [name of copyright owner]
|
|
191
|
+
|
|
192
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
193
|
+
you may not use this file except in compliance with the License.
|
|
194
|
+
You may obtain a copy of the License at
|
|
195
|
+
|
|
196
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
197
|
+
|
|
198
|
+
Unless required by applicable law or agreed to in writing, software
|
|
199
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
200
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
201
|
+
See the License for the specific language governing permissions and
|
|
202
|
+
limitations under the License.
|
|
@@ -0,0 +1,362 @@
|
|
|
1
|
+
Metadata-Version: 2.5
|
|
2
|
+
Name: video-to-context
|
|
3
|
+
Version: 0.5.0
|
|
4
|
+
Summary: Turn short videos into structured, timestamped text for LLMs: speech, on-screen text, and visual context.
|
|
5
|
+
Project-URL: Homepage, https://github.com/wani-ham/youtube-shorts-to-text-context
|
|
6
|
+
Project-URL: Repository, https://github.com/wani-ham/youtube-shorts-to-text-context
|
|
7
|
+
Project-URL: Issues, https://github.com/wani-ham/youtube-shorts-to-text-context/issues
|
|
8
|
+
Author: Taewan Ham
|
|
9
|
+
License-Expression: Apache-2.0
|
|
10
|
+
License-File: LICENSE
|
|
11
|
+
License-File: NOTICE
|
|
12
|
+
Keywords: llm,mcp,multimodal,ocr,rag,speech-to-text,video-to-text,whisper,youtube-shorts
|
|
13
|
+
Classifier: Development Status :: 4 - Beta
|
|
14
|
+
Classifier: Environment :: Console
|
|
15
|
+
Classifier: Intended Audience :: Developers
|
|
16
|
+
Classifier: Operating System :: MacOS
|
|
17
|
+
Classifier: Operating System :: POSIX :: Linux
|
|
18
|
+
Classifier: Programming Language :: Python :: 3
|
|
19
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
20
|
+
Classifier: Topic :: Multimedia :: Video
|
|
21
|
+
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
|
|
22
|
+
Requires-Python: >=3.12
|
|
23
|
+
Requires-Dist: anthropic<3,>=2.12
|
|
24
|
+
Requires-Dist: easyocr<2,>=1.7.2
|
|
25
|
+
Requires-Dist: faster-whisper<2,>=1.2.1
|
|
26
|
+
Requires-Dist: imagehash<5,>=4.3.2
|
|
27
|
+
Requires-Dist: mcp<3,>=2.3
|
|
28
|
+
Requires-Dist: numpy<3,>=2.5
|
|
29
|
+
Requires-Dist: openai<4,>=3.57
|
|
30
|
+
Requires-Dist: pillow<14,>=13
|
|
31
|
+
Requires-Dist: pydantic<3,>=2.14
|
|
32
|
+
Requires-Dist: python-dotenv<2,>=1.2
|
|
33
|
+
Requires-Dist: rapidfuzz<4,>=3.14
|
|
34
|
+
Requires-Dist: scenedetect<0.8,>=0.7.3
|
|
35
|
+
Requires-Dist: torch<3,>=2.15
|
|
36
|
+
Requires-Dist: yt-dlp>=2026.10.26
|
|
37
|
+
Provides-Extra: dev
|
|
38
|
+
Requires-Dist: jiwer<5,>=4; extra == 'dev'
|
|
39
|
+
Requires-Dist: pytest<10,>=9; extra == 'dev'
|
|
40
|
+
Description-Content-Type: text/markdown
|
|
41
|
+
|
|
42
|
+
# Generate Text Contexts from Youtube Shorts
|
|
43
|
+
|
|
44
|
+
Turn a short-form Youtube video into structured, timestamped context in a text format. It includes both audio and visual context.
|
|
45
|
+
|
|
46
|
+
Most language models can't watch a video. This tool gives them a faithful text version of one: what was **said**, what was **written on screen**, and what was **shown**, with every item labelled by source and time.
|
|
47
|
+
|
|
48
|
+
```text
|
|
49
|
+
[ON-SCREEN:LOGO 00:00–00:16] EXAMPLE CHANNEL
|
|
50
|
+
[AUDIO 00:07–00:11] Today we're testing three ways to brew coffee at home.
|
|
51
|
+
[ON-SCREEN 00:08–00:10] 3 WAYS TO BREW COFFEE
|
|
52
|
+
[VISUAL 00:07–00:16] A person in an apron pours hot water into a glass coffee maker in a bright kitchen.
|
|
53
|
+
```
|
|
54
|
+
|
|
55
|
+
Use the output as the input to summarisation, search, fact-checking, content moderation, RAG, or your own agents.
|
|
56
|
+
|
|
57
|
+
## Contents
|
|
58
|
+
|
|
59
|
+
- [How it works](#how-it-works)
|
|
60
|
+
- [Quick start](#quick-start)
|
|
61
|
+
- [Choosing a vision model](#choosing-a-vision-model)
|
|
62
|
+
- [Usage](#usage)
|
|
63
|
+
- [Use it from AI tools (MCP)](#use-it-from-ai-tools-mcp)
|
|
64
|
+
- [Output](#output)
|
|
65
|
+
- [Troubleshooting](#troubleshooting)
|
|
66
|
+
- [Privacy and responsible use](#privacy-and-responsible-use)
|
|
67
|
+
- [Development](#development)
|
|
68
|
+
- [License](#license)
|
|
69
|
+
|
|
70
|
+
## How it works
|
|
71
|
+
|
|
72
|
+
```text
|
|
73
|
+
YouTube link or video file
|
|
74
|
+
│
|
|
75
|
+
download and check
|
|
76
|
+
│
|
|
77
|
+
├── audio ──► speech-to-text (Whisper, runs locally)
|
|
78
|
+
│
|
|
79
|
+
└── frames ─► vision model: on-screen text, scenes, settings, editing
|
|
80
|
+
│
|
|
81
|
+
record.json + record.md
|
|
82
|
+
```
|
|
83
|
+
|
|
84
|
+
## Quick start
|
|
85
|
+
|
|
86
|
+
### 1. Install the requirements
|
|
87
|
+
|
|
88
|
+
You need [uv](https://docs.astral.sh/uv/), **ffmpeg**, and about 5 GB of free disk space. uv installs the right Python version for you.
|
|
89
|
+
|
|
90
|
+
| System | Install command |
|
|
91
|
+
| --- | --- |
|
|
92
|
+
| macOS | `brew install uv ffmpeg` |
|
|
93
|
+
| Ubuntu or Debian | `sudo apt install ffmpeg && curl -LsSf https://astral.sh/uv/install.sh \| sh` |
|
|
94
|
+
|
|
95
|
+
### 2. Install video-to-context
|
|
96
|
+
|
|
97
|
+
```bash
|
|
98
|
+
uv tool install --python 3.12 video-to-context
|
|
99
|
+
```
|
|
100
|
+
|
|
101
|
+
If the command isn't found afterwards, run `uv tool update-shell` and open a new terminal. You can also use `pip install video-to-context` inside a Python 3.12 environment.
|
|
102
|
+
|
|
103
|
+
### 3. Choose a vision model (optional)
|
|
104
|
+
|
|
105
|
+
Download the settings template:
|
|
106
|
+
|
|
107
|
+
```bash
|
|
108
|
+
mkdir -p ~/.video-to-context
|
|
109
|
+
curl -o ~/.video-to-context/.env https://raw.githubusercontent.com/wani-ham/youtube-shorts-to-text-context/main/.env.example
|
|
110
|
+
```
|
|
111
|
+
|
|
112
|
+
Open `~/.video-to-context/.env` and uncomment one option from the next section. Without one, the tool still produces the transcript and reads on-screen text locally, but it won't include visual analysis.
|
|
113
|
+
|
|
114
|
+
### 4. Run it
|
|
115
|
+
|
|
116
|
+
```bash
|
|
117
|
+
video-to-context "https://www.youtube.com/shorts/VIDEO_ID"
|
|
118
|
+
```
|
|
119
|
+
|
|
120
|
+
The first run is slower because it downloads the speech and OCR models. When it finishes, it prints the path to your result in a `store/` folder inside your current directory.
|
|
121
|
+
|
|
122
|
+
## Choosing a vision model
|
|
123
|
+
|
|
124
|
+
You don't need Claude. Any service with an OpenAI-compatible API and image support will work.
|
|
125
|
+
|
|
126
|
+
| Option | Cost | Your frames go to | Best for |
|
|
127
|
+
| --- | --- | --- | --- |
|
|
128
|
+
| **Claude Haiku 5.5** | About 1 cent per video (estimate) | Anthropic | Tested default |
|
|
129
|
+
| **Gemini** | Free tier available | Google | Trying it at no cost |
|
|
130
|
+
| **OpenAI** | Paid | OpenAI | Existing OpenAI users |
|
|
131
|
+
| **OpenRouter** | Free and paid models | The selected provider | Comparing models |
|
|
132
|
+
| **Ollama** | Free | **Nowhere, runs locally** | Private text extraction, no account |
|
|
133
|
+
| **None** | Free | Nowhere | Transcript and text only |
|
|
134
|
+
|
|
135
|
+
> **Status:** Claude has been tested on real videos. Ollama with Gemma 4 12B has been tested on one real video: it read on-screen text well, but its scene descriptions were unreliable. Gemini, OpenAI, and OpenRouter use the same connection as Ollama but haven't been tested with their real services.
|
|
136
|
+
|
|
137
|
+
### Claude
|
|
138
|
+
|
|
139
|
+
Create a key in the [Claude Console](https://platform.claude.com/). API usage is billed separately from Claude Pro and Max plans.
|
|
140
|
+
|
|
141
|
+
```bash
|
|
142
|
+
ANTHROPIC_API_KEY=your-key
|
|
143
|
+
```
|
|
144
|
+
|
|
145
|
+
### Gemini
|
|
146
|
+
|
|
147
|
+
Create a key in [Google AI Studio](https://aistudio.google.com/). Free-tier content may be used to improve Google's products, so avoid private videos on that tier.
|
|
148
|
+
|
|
149
|
+
```bash
|
|
150
|
+
VISION_BASE_URL=https://generativelanguage.googleapis.com/v1beta/openai/
|
|
151
|
+
VISION_API_KEY=your-key
|
|
152
|
+
VISION_MODEL=gemini-3.8-flash
|
|
153
|
+
```
|
|
154
|
+
|
|
155
|
+
### OpenAI
|
|
156
|
+
|
|
157
|
+
```bash
|
|
158
|
+
VISION_BASE_URL=https://api.openai.com/v1
|
|
159
|
+
VISION_API_KEY=your-key
|
|
160
|
+
VISION_MODEL=gpt-5.4-mini
|
|
161
|
+
```
|
|
162
|
+
|
|
163
|
+
### OpenRouter
|
|
164
|
+
|
|
165
|
+
Choose a model that accepts images from [openrouter.ai/models](https://openrouter.ai/models).
|
|
166
|
+
|
|
167
|
+
```bash
|
|
168
|
+
VISION_BASE_URL=https://openrouter.ai/api/v1
|
|
169
|
+
VISION_API_KEY=your-key
|
|
170
|
+
VISION_MODEL=provider/model-name
|
|
171
|
+
```
|
|
172
|
+
|
|
173
|
+
### Ollama (free and local)
|
|
174
|
+
|
|
175
|
+
Install [Ollama](https://ollama.com/), then download a vision model. Allow about 8 GB of disk space and at least 16 GB of memory, and close other heavy apps.
|
|
176
|
+
|
|
177
|
+
```bash
|
|
178
|
+
ollama pull gemma4:12b
|
|
179
|
+
```
|
|
180
|
+
|
|
181
|
+
Start Ollama with a larger context. Its default is too small for this prompt and the images:
|
|
182
|
+
|
|
183
|
+
```bash
|
|
184
|
+
OLLAMA_CONTEXT_LENGTH=16384 ollama serve
|
|
185
|
+
```
|
|
186
|
+
|
|
187
|
+
If Ollama is already running in the background, quit it first. Then add this to `.env`:
|
|
188
|
+
|
|
189
|
+
```bash
|
|
190
|
+
VISION_BASE_URL=http://localhost:11434/v1
|
|
191
|
+
VISION_MODEL=gemma4:12b
|
|
192
|
+
VISION_MAX_FRAMES=12
|
|
193
|
+
VISION_REASONING_EFFORT=none
|
|
194
|
+
VISION_TIMEOUT_S=600
|
|
195
|
+
```
|
|
196
|
+
|
|
197
|
+
- `VISION_MAX_FRAMES` limits how many images are sent per video. Fewer frames use less memory but can miss short captions.
|
|
198
|
+
- `VISION_REASONING_EFFORT=none` turns off model thinking. On a 16 GB Apple Silicon Mac, one request took about 78 seconds this way and about 250 seconds with thinking, which gave somewhat better scene descriptions.
|
|
199
|
+
- `VISION_TIMEOUT_S` gives slower local models enough time to answer.
|
|
200
|
+
|
|
201
|
+
Model names change often. If one is rejected, check your provider's current model list.
|
|
202
|
+
|
|
203
|
+
## Usage
|
|
204
|
+
|
|
205
|
+
```bash
|
|
206
|
+
# A YouTube video or Short
|
|
207
|
+
video-to-context "https://www.youtube.com/shorts/VIDEO_ID"
|
|
208
|
+
|
|
209
|
+
# A video file on your computer
|
|
210
|
+
video-to-context --file path/to/video.mp4
|
|
211
|
+
|
|
212
|
+
# A file with details about where it came from
|
|
213
|
+
video-to-context --file ad.mp4 --sponsor "Brand" --date 2026-11-02 --caption "Post text"
|
|
214
|
+
|
|
215
|
+
# Process a video again, ignoring the saved result
|
|
216
|
+
video-to-context "https://youtu.be/VIDEO_ID" --force
|
|
217
|
+
```
|
|
218
|
+
|
|
219
|
+
Videos can be up to 5 minutes and 200 MB. To change these limits, edit [config.py](https://github.com/wani-ham/youtube-shorts-to-text-context/blob/main/video_to_context/config.py) in a source install.
|
|
220
|
+
|
|
221
|
+
The command exits with `0` for a complete record, `1` for a partial record, and `2` for a rejected input.
|
|
222
|
+
|
|
223
|
+
### Use it from Python
|
|
224
|
+
|
|
225
|
+
```python
|
|
226
|
+
from dotenv import load_dotenv
|
|
227
|
+
from video_to_context.run import process
|
|
228
|
+
|
|
229
|
+
load_dotenv()
|
|
230
|
+
record = process(url="https://www.youtube.com/shorts/VIDEO_ID", out="store")
|
|
231
|
+
|
|
232
|
+
print(record.llm_document)
|
|
233
|
+
print(record.visual_context.summary if record.visual_context else "No visual analysis")
|
|
234
|
+
```
|
|
235
|
+
|
|
236
|
+
## Use it from AI tools (MCP)
|
|
237
|
+
|
|
238
|
+
The included [MCP](https://modelcontextprotocol.io/) server lets AI tools analyse a video when you ask, for example: *"Summarise this Short and tell me what its on-screen text claims."*
|
|
239
|
+
|
|
240
|
+
Finish the [Quick start](#quick-start) first. The server reads your settings from `~/.video-to-context/.env` and stores results in `~/.video-to-context/store`.
|
|
241
|
+
|
|
242
|
+
### Claude Code
|
|
243
|
+
|
|
244
|
+
```bash
|
|
245
|
+
claude mcp add --scope user video-to-text -- "$(command -v video-to-context-mcp)"
|
|
246
|
+
```
|
|
247
|
+
|
|
248
|
+
### Cursor, Claude Desktop, and other clients
|
|
249
|
+
|
|
250
|
+
Find the full command path with `command -v video-to-context-mcp`, then add it to the client's MCP configuration. For Cursor, that's `~/.cursor/mcp.json`.
|
|
251
|
+
|
|
252
|
+
```json
|
|
253
|
+
{
|
|
254
|
+
"mcpServers": {
|
|
255
|
+
"video-to-text": {
|
|
256
|
+
"command": "/absolute/path/to/video-to-context-mcp"
|
|
257
|
+
}
|
|
258
|
+
}
|
|
259
|
+
}
|
|
260
|
+
```
|
|
261
|
+
|
|
262
|
+
### Tools
|
|
263
|
+
|
|
264
|
+
| Tool | What it does |
|
|
265
|
+
| --- | --- |
|
|
266
|
+
| `start_video_analysis` | Starts a background job for a YouTube link or allowed local file |
|
|
267
|
+
| `get_analysis_status` | Reports whether the job is queued, running, or finished |
|
|
268
|
+
| `get_video_text` | Returns the finished result as Markdown or JSON |
|
|
269
|
+
| `list_analyzed_videos` | Lists videos that already have results |
|
|
270
|
+
| `check_setup` | Checks ffmpeg, the vision model, and file access |
|
|
271
|
+
|
|
272
|
+
Videos run one at a time in the background, because processing takes longer than most tools wait for a single call.
|
|
273
|
+
|
|
274
|
+
### Security
|
|
275
|
+
|
|
276
|
+
- **Local files are off by default.** To allow them, list specific folders in `VIDEO_TEXT_ALLOWED_DIRS` in `~/.video-to-context/.env`.
|
|
277
|
+
- **URLs are limited to YouTube.**
|
|
278
|
+
- **The server runs locally over stdio** and opens no network port.
|
|
279
|
+
- **Video text is untrusted.** A caption could try to manipulate your AI tool, so be careful when that tool can also run commands or edit files.
|
|
280
|
+
|
|
281
|
+
## Output
|
|
282
|
+
|
|
283
|
+
Each video gets its own folder, named after a hash of the file, so the same file is never processed twice:
|
|
284
|
+
|
|
285
|
+
```text
|
|
286
|
+
store/<sha256>/
|
|
287
|
+
├── record.md Document for LLMs and people
|
|
288
|
+
├── record.json Full structured data for code
|
|
289
|
+
├── video.mp4 The video
|
|
290
|
+
├── frames/ Keyframes referenced by the record
|
|
291
|
+
└── info.json YouTube metadata (for YouTube links)
|
|
292
|
+
```
|
|
293
|
+
|
|
294
|
+
### `record.md`
|
|
295
|
+
|
|
296
|
+
Pass this file directly to a language model. It contains:
|
|
297
|
+
|
|
298
|
+
- **YAML metadata:** source, duration, language, footage type, status, and models used.
|
|
299
|
+
- **Quality notes:** anything downstream services should be careful about.
|
|
300
|
+
- **Visual analysis:** a summary, the distinct settings, editing techniques, and shots.
|
|
301
|
+
- **Timeline:** everything in time order, labelled by source.
|
|
302
|
+
|
|
303
|
+
| Label | Meaning | Safe to quote as the video's content? |
|
|
304
|
+
| --- | --- | --- |
|
|
305
|
+
| `AUDIO` | Transcribed speech | Yes, but it may have recognition errors |
|
|
306
|
+
| `ON-SCREEN` | Captions and text in the frame | Yes |
|
|
307
|
+
| `ON-SCREEN:HEADLINE`, `:WATERMARK`, `:LOGO`, `:OTHER` | Text or marks that stay on screen | Yes |
|
|
308
|
+
| `VISUAL` | A model's description of a scene | **No, it is an interpretation** |
|
|
309
|
+
|
|
310
|
+
Video text is untrusted input. It's kept inside code blocks so that your prompt can treat it as data, but a caption could still contain text written to manipulate a model. Tell your downstream model not to follow instructions found in it.
|
|
311
|
+
|
|
312
|
+
### `record.json`
|
|
313
|
+
|
|
314
|
+
The same information as structured fields, including `transcript`, `on_screen_text`, `visual_context`, `visual_descriptions`, `keyframes`, `flags`, and `errors`. Suspected invented speech is moved to `transcript.removed_segments` so you can review it.
|
|
315
|
+
|
|
316
|
+
If one stage fails, the others still finish and the record is marked `partial`.
|
|
317
|
+
|
|
318
|
+
## Troubleshooting
|
|
319
|
+
|
|
320
|
+
| What you see | What to do |
|
|
321
|
+
| --- | --- |
|
|
322
|
+
| `fetch_failed` | The video may be private, removed, or age-restricted, or YouTube may be blocking the download. Download limits are stricter on cloud servers. Use `--file` instead. |
|
|
323
|
+
| `vision_not_configured` in `flags` | No vision model is set. Check that `~/.video-to-context/.env` exists and an option is uncommented. |
|
|
324
|
+
| `vision_auth_failed` | The API key is wrong or expired. |
|
|
325
|
+
| `vision_invalid_output` | The model didn't return usable JSON. Try a more capable model. |
|
|
326
|
+
| Out of memory with Ollama | Lower `VISION_MAX_FRAMES` or use a smaller model. |
|
|
327
|
+
| MCP tools don't appear | Use the full path from `command -v video-to-context-mcp`, then restart the client. |
|
|
328
|
+
| `vision_timeout` | Raise `VISION_TIMEOUT_S`, or set `VISION_REASONING_EFFORT=none`. |
|
|
329
|
+
| `objc: Class AVF... is implemented in both` | A harmless macOS warning from two video libraries. |
|
|
330
|
+
| `ffmpeg` not found | Install ffmpeg (step 1), then open a new terminal. |
|
|
331
|
+
| It's slow | Speech-to-text runs on CPU unless you have an NVIDIA GPU. Expect a few minutes for a 2-minute video. |
|
|
332
|
+
|
|
333
|
+
## Privacy and responsible use
|
|
334
|
+
|
|
335
|
+
- Unless you use Ollama or no vision model, video frames are sent to the provider you choose. Check its data retention and training terms.
|
|
336
|
+
- Videos contain people's faces and voices. The vision prompt tells the model not to identify people, and you shouldn't add face or voice identification without legal review.
|
|
337
|
+
- YouTube's terms restrict downloading. Make sure you have the right to process a video, especially for commercial or public use.
|
|
338
|
+
- `.env`, `store/`, and media files are ignored by git. Never commit API keys.
|
|
339
|
+
|
|
340
|
+
## Development
|
|
341
|
+
|
|
342
|
+
```bash
|
|
343
|
+
git clone https://github.com/wani-ham/youtube-shorts-to-text-context.git
|
|
344
|
+
cd youtube-shorts-to-text-context
|
|
345
|
+
python3.12 -m venv .venv
|
|
346
|
+
.venv/bin/pip install -e ".[dev]"
|
|
347
|
+
cp .env.example .env
|
|
348
|
+
.venv/bin/python -m pytest
|
|
349
|
+
.venv/bin/python -m video_to_context.evaluate
|
|
350
|
+
```
|
|
351
|
+
|
|
352
|
+
In a source checkout, settings come from the project's `.env`, and the MCP server stores results in the project's `store/` folder.
|
|
353
|
+
|
|
354
|
+
To score accuracy on your own test set, put each video in `tests/samples/<name>.mp4` and its hand-written labels in `tests/expected/<name>.json`:
|
|
355
|
+
|
|
356
|
+
```json
|
|
357
|
+
{"transcript": "…", "on_screen": ["…"], "no_speech": false, "rejected": null}
|
|
358
|
+
```
|
|
359
|
+
|
|
360
|
+
## License
|
|
361
|
+
|
|
362
|
+
Licensed under the [Apache License 2.0](https://github.com/wani-ham/youtube-shorts-to-text-context/blob/main/LICENSE). See [NOTICE](https://github.com/wani-ham/youtube-shorts-to-text-context/blob/main/NOTICE) for copyright details.
|