@vargai/sdk 0.1.1 → 0.2.0
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.
- package/.github/workflows/ci.yml +23 -0
- package/.husky/README.md +102 -0
- package/.husky/commit-msg +9 -0
- package/.husky/pre-commit +12 -0
- package/.husky/pre-push +9 -0
- package/.size-limit.json +8 -0
- package/.test-hooks.ts +5 -0
- package/CONTRIBUTING.md +150 -0
- package/LICENSE.md +53 -0
- package/README.md +7 -0
- package/action/captions/index.ts +202 -12
- package/action/captions/tiktok.ts +538 -0
- package/action/cut/index.ts +119 -0
- package/action/fade/index.ts +116 -0
- package/action/merge/index.ts +177 -0
- package/action/remove/index.ts +184 -0
- package/action/split/index.ts +133 -0
- package/action/transition/index.ts +154 -0
- package/action/trim/index.ts +117 -0
- package/bun.lock +299 -8
- package/cli/commands/upload.ts +215 -0
- package/cli/index.ts +3 -1
- package/commitlint.config.js +22 -0
- package/index.ts +12 -0
- package/lib/ass.ts +547 -0
- package/lib/fal.ts +75 -1
- package/lib/ffmpeg.ts +400 -0
- package/lib/higgsfield/example.ts +22 -29
- package/lib/higgsfield/index.ts +3 -2
- package/lib/higgsfield/soul.ts +0 -5
- package/lib/remotion/SKILL.md +240 -21
- package/lib/remotion/cli.ts +34 -0
- package/package.json +20 -3
- package/pipeline/cookbooks/scripts/animate-frames-parallel.ts +83 -0
- package/pipeline/cookbooks/scripts/combine-scenes.sh +53 -0
- package/pipeline/cookbooks/scripts/generate-frames-parallel.ts +98 -0
- package/pipeline/cookbooks/scripts/still-to-video.sh +37 -0
- package/pipeline/cookbooks/text-to-tiktok.md +669 -0
- package/scripts/.gitkeep +0 -0
- package/service/music/index.ts +29 -14
- package/tsconfig.json +1 -1
- package/utilities/s3.ts +2 -2
- package/HIGGSFIELD_REWRITE_SUMMARY.md +0 -300
- package/TEST_RESULTS.md +0 -122
- package/output.txt +0 -1
- package/scripts/produce-menopause-campaign.sh +0 -202
- package/test-import.ts +0 -7
- package/test-services.ts +0 -97
|
@@ -0,0 +1,23 @@
|
|
|
1
|
+
name: CI
|
|
2
|
+
|
|
3
|
+
on:
|
|
4
|
+
push:
|
|
5
|
+
branches: [main]
|
|
6
|
+
pull_request:
|
|
7
|
+
branches: [main]
|
|
8
|
+
|
|
9
|
+
jobs:
|
|
10
|
+
lint-and-format:
|
|
11
|
+
runs-on: ubuntu-latest
|
|
12
|
+
steps:
|
|
13
|
+
- uses: actions/checkout@v4
|
|
14
|
+
|
|
15
|
+
- uses: oven-sh/setup-bun@v2
|
|
16
|
+
with:
|
|
17
|
+
bun-version: latest
|
|
18
|
+
|
|
19
|
+
- name: Install dependencies
|
|
20
|
+
run: bun install
|
|
21
|
+
|
|
22
|
+
- name: Check
|
|
23
|
+
run: bun run check
|
package/.husky/README.md
ADDED
|
@@ -0,0 +1,102 @@
|
|
|
1
|
+
# Git Hooks Configuration
|
|
2
|
+
|
|
3
|
+
This project uses [Husky](https://typicode.github.io/husky/) to manage Git hooks for maintaining code quality and security.
|
|
4
|
+
|
|
5
|
+
## Installed Hooks
|
|
6
|
+
|
|
7
|
+
### `pre-commit`
|
|
8
|
+
Runs before each commit:
|
|
9
|
+
- **Gitleaks** - Scans staged files for secrets and credentials
|
|
10
|
+
- **Lint-staged** - Runs Biome linter/formatter on staged files
|
|
11
|
+
|
|
12
|
+
### `commit-msg`
|
|
13
|
+
Validates commit messages:
|
|
14
|
+
- **Commitlint** - Enforces [Conventional Commits](https://www.conventionalcommits.org/) format
|
|
15
|
+
|
|
16
|
+
### `pre-push`
|
|
17
|
+
Runs before pushing to remote:
|
|
18
|
+
- **TypeScript type checking** - Ensures no type errors before push
|
|
19
|
+
|
|
20
|
+
## Commit Message Format
|
|
21
|
+
|
|
22
|
+
Follow the Conventional Commits specification:
|
|
23
|
+
|
|
24
|
+
```
|
|
25
|
+
<type>(<scope>): <subject>
|
|
26
|
+
|
|
27
|
+
<body>
|
|
28
|
+
|
|
29
|
+
<footer>
|
|
30
|
+
```
|
|
31
|
+
|
|
32
|
+
### Types
|
|
33
|
+
- `feat`: New feature
|
|
34
|
+
- `fix`: Bug fix
|
|
35
|
+
- `docs`: Documentation changes
|
|
36
|
+
- `style`: Code style changes (formatting, etc)
|
|
37
|
+
- `refactor`: Code refactoring
|
|
38
|
+
- `perf`: Performance improvements
|
|
39
|
+
- `test`: Test changes
|
|
40
|
+
- `build`: Build system changes
|
|
41
|
+
- `ci`: CI/CD changes
|
|
42
|
+
- `chore`: Other changes
|
|
43
|
+
- `revert`: Revert previous commit
|
|
44
|
+
|
|
45
|
+
### Examples
|
|
46
|
+
```bash
|
|
47
|
+
feat: add video generation API
|
|
48
|
+
fix(transcribe): handle empty audio files
|
|
49
|
+
docs: update installation guide
|
|
50
|
+
refactor: simplify audio processing pipeline
|
|
51
|
+
```
|
|
52
|
+
|
|
53
|
+
## Available Scripts
|
|
54
|
+
|
|
55
|
+
```bash
|
|
56
|
+
# Run linter
|
|
57
|
+
bun run lint
|
|
58
|
+
|
|
59
|
+
# Format code
|
|
60
|
+
bun run format
|
|
61
|
+
|
|
62
|
+
# Type check
|
|
63
|
+
bun run type-check
|
|
64
|
+
|
|
65
|
+
# Check bundle size
|
|
66
|
+
bun run size
|
|
67
|
+
```
|
|
68
|
+
|
|
69
|
+
## Bypassing Hooks
|
|
70
|
+
|
|
71
|
+
⚠️ **Not recommended** - Only use when absolutely necessary:
|
|
72
|
+
|
|
73
|
+
```bash
|
|
74
|
+
# Skip all hooks
|
|
75
|
+
git commit --no-verify -m "emergency fix"
|
|
76
|
+
|
|
77
|
+
# Skip specific checks by setting env vars
|
|
78
|
+
HUSKY=0 git commit -m "skip all hooks"
|
|
79
|
+
```
|
|
80
|
+
|
|
81
|
+
## Troubleshooting
|
|
82
|
+
|
|
83
|
+
If hooks aren't running:
|
|
84
|
+
|
|
85
|
+
```bash
|
|
86
|
+
# Reinstall hooks
|
|
87
|
+
rm -rf .husky/_
|
|
88
|
+
bun run prepare
|
|
89
|
+
chmod +x .husky/pre-commit .husky/commit-msg .husky/pre-push
|
|
90
|
+
```
|
|
91
|
+
|
|
92
|
+
## Size Limits
|
|
93
|
+
|
|
94
|
+
Bundle size limits are defined in `.size-limit.json`. Check size before publishing:
|
|
95
|
+
|
|
96
|
+
```bash
|
|
97
|
+
bun run size
|
|
98
|
+
```
|
|
99
|
+
|
|
100
|
+
|
|
101
|
+
|
|
102
|
+
|
package/.husky/pre-push
ADDED
package/.size-limit.json
ADDED
package/.test-hooks.ts
ADDED
package/CONTRIBUTING.md
ADDED
|
@@ -0,0 +1,150 @@
|
|
|
1
|
+
# Contributing to @vargai/sdk
|
|
2
|
+
|
|
3
|
+
## Development Setup
|
|
4
|
+
|
|
5
|
+
This project uses **Bun** as the runtime and package manager.
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
# Install dependencies
|
|
9
|
+
bun install
|
|
10
|
+
|
|
11
|
+
# Run linter
|
|
12
|
+
bun run lint
|
|
13
|
+
|
|
14
|
+
# Format code
|
|
15
|
+
bun run format
|
|
16
|
+
|
|
17
|
+
# Type check
|
|
18
|
+
bun run type-check
|
|
19
|
+
|
|
20
|
+
# Check bundle size
|
|
21
|
+
bun run size
|
|
22
|
+
```
|
|
23
|
+
|
|
24
|
+
## Git Workflow
|
|
25
|
+
|
|
26
|
+
This project uses automated Git hooks powered by [Husky](https://typicode.github.io/husky/) to maintain code quality and security.
|
|
27
|
+
|
|
28
|
+
### Automated Checks
|
|
29
|
+
|
|
30
|
+
#### Before Commit (`pre-commit`)
|
|
31
|
+
1. **Gitleaks** - Scans for secrets, API keys, and credentials
|
|
32
|
+
2. **Biome** - Lints and formats staged files automatically
|
|
33
|
+
|
|
34
|
+
#### Commit Message (`commit-msg`)
|
|
35
|
+
3. **Commitlint** - Validates commit message format
|
|
36
|
+
|
|
37
|
+
#### Before Push (`pre-push`)
|
|
38
|
+
4. **TypeScript** - Type checking to catch errors early
|
|
39
|
+
|
|
40
|
+
### Commit Message Format
|
|
41
|
+
|
|
42
|
+
We follow [Conventional Commits](https://www.conventionalcommits.org/) specification:
|
|
43
|
+
|
|
44
|
+
```
|
|
45
|
+
<type>(<scope>): <subject>
|
|
46
|
+
```
|
|
47
|
+
|
|
48
|
+
**Available types:**
|
|
49
|
+
- `feat`: New feature
|
|
50
|
+
- `fix`: Bug fix
|
|
51
|
+
- `docs`: Documentation only changes
|
|
52
|
+
- `style`: Code style changes (formatting, missing semi colons, etc)
|
|
53
|
+
- `refactor`: Code change that neither fixes a bug nor adds a feature
|
|
54
|
+
- `perf`: Performance improvements
|
|
55
|
+
- `test`: Adding or updating tests
|
|
56
|
+
- `build`: Changes to build system or dependencies
|
|
57
|
+
- `ci`: CI/CD configuration changes
|
|
58
|
+
- `chore`: Other changes that don't modify src or test files
|
|
59
|
+
- `revert`: Reverts a previous commit
|
|
60
|
+
|
|
61
|
+
**Examples:**
|
|
62
|
+
```bash
|
|
63
|
+
feat: add voice cloning endpoint
|
|
64
|
+
feat(video): implement background removal
|
|
65
|
+
fix: handle null pointer in transcription
|
|
66
|
+
fix(captions): correct timestamp alignment
|
|
67
|
+
docs: update API documentation
|
|
68
|
+
refactor: simplify audio processing pipeline
|
|
69
|
+
perf(image): optimize memory usage
|
|
70
|
+
chore: update dependencies
|
|
71
|
+
```
|
|
72
|
+
|
|
73
|
+
### Code Style
|
|
74
|
+
|
|
75
|
+
We use [Biome](https://biomejs.dev/) for linting and formatting:
|
|
76
|
+
|
|
77
|
+
- **Automatic formatting** on commit via lint-staged
|
|
78
|
+
- **Manual formatting**: `bun run format`
|
|
79
|
+
- **Manual linting**: `bun run lint`
|
|
80
|
+
|
|
81
|
+
### Bundle Size
|
|
82
|
+
|
|
83
|
+
SDK bundle size is monitored via size-limit:
|
|
84
|
+
|
|
85
|
+
```bash
|
|
86
|
+
bun run size
|
|
87
|
+
```
|
|
88
|
+
|
|
89
|
+
Current limits are defined in `.size-limit.json`.
|
|
90
|
+
|
|
91
|
+
## Pull Request Process
|
|
92
|
+
|
|
93
|
+
1. Fork the repository
|
|
94
|
+
2. Create a feature branch: `git checkout -b feat/amazing-feature`
|
|
95
|
+
3. Make your changes
|
|
96
|
+
4. Commit with conventional format: `git commit -m "feat: add amazing feature"`
|
|
97
|
+
5. Push to your fork: `git push origin feat/amazing-feature`
|
|
98
|
+
6. Open a Pull Request
|
|
99
|
+
|
|
100
|
+
### PR Guidelines
|
|
101
|
+
|
|
102
|
+
- ✅ All automated checks must pass
|
|
103
|
+
- ✅ Follow conventional commits format
|
|
104
|
+
- ✅ Update documentation if needed
|
|
105
|
+
- ✅ Add tests for new features
|
|
106
|
+
- ✅ Keep bundle size within limits
|
|
107
|
+
|
|
108
|
+
## Bypassing Hooks
|
|
109
|
+
|
|
110
|
+
⚠️ **Only in emergencies:**
|
|
111
|
+
|
|
112
|
+
```bash
|
|
113
|
+
# Skip all hooks (not recommended)
|
|
114
|
+
git commit --no-verify -m "emergency fix"
|
|
115
|
+
```
|
|
116
|
+
|
|
117
|
+
## Troubleshooting
|
|
118
|
+
|
|
119
|
+
### Hooks not running?
|
|
120
|
+
|
|
121
|
+
```bash
|
|
122
|
+
# Reinstall hooks
|
|
123
|
+
bun run prepare
|
|
124
|
+
chmod +x .husky/*
|
|
125
|
+
```
|
|
126
|
+
|
|
127
|
+
### Type errors?
|
|
128
|
+
|
|
129
|
+
```bash
|
|
130
|
+
bun run type-check
|
|
131
|
+
```
|
|
132
|
+
|
|
133
|
+
### Format issues?
|
|
134
|
+
|
|
135
|
+
```bash
|
|
136
|
+
bun run format
|
|
137
|
+
```
|
|
138
|
+
|
|
139
|
+
### Secrets detected?
|
|
140
|
+
|
|
141
|
+
If gitleaks detects secrets:
|
|
142
|
+
1. **DO NOT** bypass the hook
|
|
143
|
+
2. Remove the secret from your code
|
|
144
|
+
3. Use environment variables instead
|
|
145
|
+
4. If already committed, rotate the exposed credentials
|
|
146
|
+
|
|
147
|
+
## Questions?
|
|
148
|
+
|
|
149
|
+
Open an issue or reach out to the maintainers.
|
|
150
|
+
|
package/LICENSE.md
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
1
|
+
LICENSE
|
|
2
|
+
|
|
3
|
+
Apache License
|
|
4
|
+
Version 2.0, January 2004
|
|
5
|
+
http://www.apache.org/licenses/
|
|
6
|
+
|
|
7
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
8
|
+
|
|
9
|
+
1. Definitions.
|
|
10
|
+
|
|
11
|
+
"License" shall mean the terms and conditions for use, reproduction, and distribution as defined by Sections 1 through 9 of this document.
|
|
12
|
+
|
|
13
|
+
"Licensor" shall mean the copyright owner or entity authorized by the copyright owner that is granting the License.
|
|
14
|
+
|
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity.
|
|
16
|
+
|
|
17
|
+
"You" (or "Your") shall mean an individual or Legal Entity exercising permissions granted by this License.
|
|
18
|
+
|
|
19
|
+
"Source" form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files.
|
|
20
|
+
|
|
21
|
+
"Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types.
|
|
22
|
+
|
|
23
|
+
"Work" shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work (an example is provided in the Appendix below).
|
|
24
|
+
|
|
25
|
+
"Derivative Works" shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof.
|
|
26
|
+
|
|
27
|
+
"Contribution" shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution."
|
|
28
|
+
|
|
29
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Work.
|
|
30
|
+
|
|
31
|
+
2. Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form.
|
|
32
|
+
|
|
33
|
+
3. Grant of Patent License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed.
|
|
34
|
+
|
|
35
|
+
4. Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions:
|
|
36
|
+
|
|
37
|
+
You must give any other recipients of the Work or Derivative Works a copy of this License; and
|
|
38
|
+
You must cause any modified files to carry prominent notices stating that You changed the files; and
|
|
39
|
+
You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and
|
|
40
|
+
If the Work includes a "NOTICE" text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License.
|
|
41
|
+
You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License.
|
|
42
|
+
|
|
43
|
+
5. Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions.
|
|
44
|
+
|
|
45
|
+
6. Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except as required for reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file.
|
|
46
|
+
|
|
47
|
+
7. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Work and assume any risks associated with Your exercise of permissions under this License.
|
|
48
|
+
|
|
49
|
+
8. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages.
|
|
50
|
+
|
|
51
|
+
9. Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability.
|
|
52
|
+
|
|
53
|
+
END OF TERMS AND CONDITIONS
|
package/README.md
CHANGED
|
@@ -229,3 +229,10 @@ fal.ai automatically filters content that may be nsfw:
|
|
|
229
229
|
- ❌ "athletic wear" (vague, may trigger filter)
|
|
230
230
|
- add "professional", "modest", "appropriate" to prompts
|
|
231
231
|
- always check file sizes after batch generation (< 10KB = filtered)
|
|
232
|
+
|
|
233
|
+
|
|
234
|
+
## License
|
|
235
|
+
|
|
236
|
+
Copyright © 2025 vargai Inc. and contributors
|
|
237
|
+
Licensed under the Apache License, Version 2.0.
|
|
238
|
+
See the [LICENSE](./LICENSE) file for details.
|
package/action/captions/index.ts
CHANGED
|
@@ -4,17 +4,26 @@
|
|
|
4
4
|
* video captioning service
|
|
5
5
|
* generates and overlays subtitles on videos using ffmpeg
|
|
6
6
|
* supports auto-generation via groq/fireworks or custom srt files
|
|
7
|
+
*
|
|
8
|
+
* modes:
|
|
9
|
+
* - basic: standard SRT subtitles with customizable style
|
|
10
|
+
* - tiktok: word-by-word animated captions with bounce effects
|
|
7
11
|
*/
|
|
8
12
|
|
|
9
13
|
import { existsSync } from "node:fs";
|
|
10
14
|
import ffmpeg from "fluent-ffmpeg";
|
|
11
15
|
import type { ActionMeta } from "../../cli/types";
|
|
12
16
|
import { transcribe } from "../transcribe";
|
|
17
|
+
import {
|
|
18
|
+
addTikTokCaptions,
|
|
19
|
+
type TikTokCaptionItem,
|
|
20
|
+
type TikTokWordStyle,
|
|
21
|
+
} from "./tiktok";
|
|
13
22
|
|
|
14
23
|
export const meta: ActionMeta = {
|
|
15
24
|
name: "captions",
|
|
16
25
|
type: "action",
|
|
17
|
-
description: "add subtitles to video",
|
|
26
|
+
description: "add subtitles to video (basic or tiktok-style)",
|
|
18
27
|
inputType: "video",
|
|
19
28
|
outputType: "video",
|
|
20
29
|
schema: {
|
|
@@ -32,10 +41,18 @@ export const meta: ActionMeta = {
|
|
|
32
41
|
format: "file-path",
|
|
33
42
|
description: "output video path",
|
|
34
43
|
},
|
|
44
|
+
mode: {
|
|
45
|
+
type: "string",
|
|
46
|
+
enum: ["basic", "tiktok"],
|
|
47
|
+
default: "basic",
|
|
48
|
+
description:
|
|
49
|
+
"caption mode: basic (SRT) or tiktok (word-by-word animated)",
|
|
50
|
+
},
|
|
35
51
|
srt: {
|
|
36
52
|
type: "string",
|
|
37
53
|
format: "file-path",
|
|
38
|
-
description:
|
|
54
|
+
description:
|
|
55
|
+
"existing srt file (basic mode, auto-generates if not provided)",
|
|
39
56
|
},
|
|
40
57
|
provider: {
|
|
41
58
|
type: "string",
|
|
@@ -43,28 +60,88 @@ export const meta: ActionMeta = {
|
|
|
43
60
|
default: "fireworks",
|
|
44
61
|
description: "transcription provider for auto-generation",
|
|
45
62
|
},
|
|
63
|
+
// TikTok mode options
|
|
64
|
+
position: {
|
|
65
|
+
type: "string",
|
|
66
|
+
enum: ["upper-middle", "middle", "lower-middle", "top", "bottom"],
|
|
67
|
+
default: "upper-middle",
|
|
68
|
+
description: "tiktok: caption position on screen",
|
|
69
|
+
},
|
|
70
|
+
bounce: {
|
|
71
|
+
type: "number",
|
|
72
|
+
default: 1.12,
|
|
73
|
+
description: "tiktok: bounce scale for active word (1.0-1.5)",
|
|
74
|
+
},
|
|
75
|
+
noBounce: {
|
|
76
|
+
type: "boolean",
|
|
77
|
+
default: false,
|
|
78
|
+
description: "tiktok: disable bounce animation",
|
|
79
|
+
},
|
|
46
80
|
},
|
|
47
81
|
},
|
|
48
82
|
output: { type: "string", format: "file-path", description: "video path" },
|
|
49
83
|
},
|
|
50
84
|
async run(options) {
|
|
51
|
-
const { video, output, srt, provider
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
|
|
55
|
-
|
|
56
|
-
|
|
57
|
-
|
|
85
|
+
const { video, output, srt, provider, mode, position, bounce, noBounce } =
|
|
86
|
+
options as {
|
|
87
|
+
video: string;
|
|
88
|
+
output: string;
|
|
89
|
+
srt?: string;
|
|
90
|
+
provider?: "groq" | "fireworks";
|
|
91
|
+
mode?: "basic" | "tiktok";
|
|
92
|
+
position?:
|
|
93
|
+
| "upper-middle"
|
|
94
|
+
| "middle"
|
|
95
|
+
| "lower-middle"
|
|
96
|
+
| "top"
|
|
97
|
+
| "bottom";
|
|
98
|
+
bounce?: number;
|
|
99
|
+
noBounce?: boolean;
|
|
100
|
+
};
|
|
101
|
+
|
|
102
|
+
const tiktokStyle: TikTokWordStyle | undefined =
|
|
103
|
+
mode === "tiktok"
|
|
104
|
+
? {
|
|
105
|
+
position: position || "upper-middle",
|
|
106
|
+
bounceScale: bounce || 1.12,
|
|
107
|
+
useBounce: !noBounce,
|
|
108
|
+
}
|
|
109
|
+
: undefined;
|
|
110
|
+
|
|
111
|
+
return addCaptions({
|
|
112
|
+
videoPath: video,
|
|
113
|
+
output,
|
|
114
|
+
srtPath: srt,
|
|
115
|
+
provider,
|
|
116
|
+
mode,
|
|
117
|
+
tiktokStyle,
|
|
118
|
+
});
|
|
58
119
|
},
|
|
59
120
|
};
|
|
60
121
|
|
|
122
|
+
// re-export tiktok types for convenience
|
|
123
|
+
export {
|
|
124
|
+
addTikTokCaptions,
|
|
125
|
+
type TikTokCaptionItem,
|
|
126
|
+
type TikTokWordStyle,
|
|
127
|
+
} from "./tiktok";
|
|
128
|
+
|
|
61
129
|
// types
|
|
62
130
|
export interface AddCaptionsOptions {
|
|
63
131
|
videoPath: string;
|
|
64
|
-
srtPath?: string; // optional existing srt file
|
|
65
132
|
output: string;
|
|
66
|
-
|
|
133
|
+
/** Caption mode: basic (SRT) or tiktok (word-by-word animated) */
|
|
134
|
+
mode?: "basic" | "tiktok";
|
|
135
|
+
/** Existing srt file (auto-generates if not provided) - basic mode only */
|
|
136
|
+
srtPath?: string;
|
|
137
|
+
/** Transcription provider for auto-generation */
|
|
138
|
+
provider?: "groq" | "fireworks";
|
|
139
|
+
/** Style for basic mode */
|
|
67
140
|
style?: SubtitleStyle;
|
|
141
|
+
/** Captions with word timings for tiktok mode (auto-generates from transcription if not provided) */
|
|
142
|
+
tiktokCaptions?: TikTokCaptionItem[];
|
|
143
|
+
/** Style for tiktok mode */
|
|
144
|
+
tiktokStyle?: TikTokWordStyle;
|
|
68
145
|
}
|
|
69
146
|
|
|
70
147
|
export interface SubtitleStyle {
|
|
@@ -92,7 +169,16 @@ const DEFAULT_STYLE: Required<SubtitleStyle> = {
|
|
|
92
169
|
export async function addCaptions(
|
|
93
170
|
options: AddCaptionsOptions,
|
|
94
171
|
): Promise<string> {
|
|
95
|
-
const {
|
|
172
|
+
const {
|
|
173
|
+
videoPath,
|
|
174
|
+
srtPath,
|
|
175
|
+
output,
|
|
176
|
+
provider = "fireworks",
|
|
177
|
+
style,
|
|
178
|
+
mode = "basic",
|
|
179
|
+
tiktokCaptions,
|
|
180
|
+
tiktokStyle,
|
|
181
|
+
} = options;
|
|
96
182
|
|
|
97
183
|
if (!videoPath) {
|
|
98
184
|
throw new Error("videoPath is required");
|
|
@@ -104,6 +190,54 @@ export async function addCaptions(
|
|
|
104
190
|
throw new Error(`video file not found: ${videoPath}`);
|
|
105
191
|
}
|
|
106
192
|
|
|
193
|
+
// TikTok mode: use word-by-word animated captions
|
|
194
|
+
if (mode === "tiktok") {
|
|
195
|
+
console.log("[captions] using TikTok mode (word-by-word animated)...");
|
|
196
|
+
|
|
197
|
+
// If captions provided, use them directly
|
|
198
|
+
if (tiktokCaptions && tiktokCaptions.length > 0) {
|
|
199
|
+
return addTikTokCaptions({
|
|
200
|
+
videoPath,
|
|
201
|
+
output,
|
|
202
|
+
captions: tiktokCaptions,
|
|
203
|
+
style: tiktokStyle,
|
|
204
|
+
});
|
|
205
|
+
}
|
|
206
|
+
|
|
207
|
+
// Otherwise, auto-generate from transcription
|
|
208
|
+
console.log(`[captions] auto-generating word timings with ${provider}...`);
|
|
209
|
+
|
|
210
|
+
// Fireworks provides word-level timestamps, groq doesn't
|
|
211
|
+
if (provider === "groq") {
|
|
212
|
+
console.warn(
|
|
213
|
+
"[captions] warning: groq doesn't provide word-level timestamps, using fireworks instead",
|
|
214
|
+
);
|
|
215
|
+
}
|
|
216
|
+
|
|
217
|
+
// Import fireworks directly for word-level data
|
|
218
|
+
const { transcribeWithFireworks } = await import("../../lib/fireworks");
|
|
219
|
+
|
|
220
|
+
const data = await transcribeWithFireworks({ audioPath: videoPath });
|
|
221
|
+
|
|
222
|
+
if (!data.words || data.words.length === 0) {
|
|
223
|
+
throw new Error("transcription returned no word data");
|
|
224
|
+
}
|
|
225
|
+
|
|
226
|
+
// Convert fireworks words to tiktok captions
|
|
227
|
+
// Group words into phrases (max ~5-7 words per phrase)
|
|
228
|
+
const phrases = groupWordsIntoPhrases(data.words, 6);
|
|
229
|
+
|
|
230
|
+
console.log(`[captions] generated ${phrases.length} caption phrases`);
|
|
231
|
+
|
|
232
|
+
return addTikTokCaptions({
|
|
233
|
+
videoPath,
|
|
234
|
+
output,
|
|
235
|
+
captions: phrases,
|
|
236
|
+
style: tiktokStyle,
|
|
237
|
+
});
|
|
238
|
+
}
|
|
239
|
+
|
|
240
|
+
// Basic mode: use SRT subtitles
|
|
107
241
|
console.log("[captions] adding captions to video...");
|
|
108
242
|
|
|
109
243
|
// determine srt file path
|
|
@@ -162,6 +296,62 @@ export async function addCaptions(
|
|
|
162
296
|
});
|
|
163
297
|
}
|
|
164
298
|
|
|
299
|
+
/**
|
|
300
|
+
* Group words into phrases for TikTok captions
|
|
301
|
+
*/
|
|
302
|
+
function groupWordsIntoPhrases(
|
|
303
|
+
words: Array<{ word: string; start: number; end: number }>,
|
|
304
|
+
maxWordsPerPhrase: number,
|
|
305
|
+
): TikTokCaptionItem[] {
|
|
306
|
+
const phrases: TikTokCaptionItem[] = [];
|
|
307
|
+
let currentPhrase: Array<{ word: string; start: number; end: number }> = [];
|
|
308
|
+
|
|
309
|
+
for (const word of words) {
|
|
310
|
+
currentPhrase.push(word);
|
|
311
|
+
|
|
312
|
+
// Start new phrase after reaching max words or at sentence boundaries
|
|
313
|
+
const endsWithPunctuation = /[.!?]$/.test(word.word);
|
|
314
|
+
|
|
315
|
+
if (currentPhrase.length >= maxWordsPerPhrase || endsWithPunctuation) {
|
|
316
|
+
const first = currentPhrase[0];
|
|
317
|
+
const last = currentPhrase[currentPhrase.length - 1];
|
|
318
|
+
if (first && last) {
|
|
319
|
+
phrases.push({
|
|
320
|
+
text: currentPhrase.map((w) => w.word).join(" "),
|
|
321
|
+
start: first.start,
|
|
322
|
+
end: last.end,
|
|
323
|
+
words: currentPhrase.map((w) => ({
|
|
324
|
+
word: w.word,
|
|
325
|
+
start: w.start,
|
|
326
|
+
end: w.end,
|
|
327
|
+
})),
|
|
328
|
+
});
|
|
329
|
+
}
|
|
330
|
+
currentPhrase = [];
|
|
331
|
+
}
|
|
332
|
+
}
|
|
333
|
+
|
|
334
|
+
// Add remaining words
|
|
335
|
+
if (currentPhrase.length > 0) {
|
|
336
|
+
const first = currentPhrase[0];
|
|
337
|
+
const last = currentPhrase[currentPhrase.length - 1];
|
|
338
|
+
if (first && last) {
|
|
339
|
+
phrases.push({
|
|
340
|
+
text: currentPhrase.map((w) => w.word).join(" "),
|
|
341
|
+
start: first.start,
|
|
342
|
+
end: last.end,
|
|
343
|
+
words: currentPhrase.map((w) => ({
|
|
344
|
+
word: w.word,
|
|
345
|
+
start: w.start,
|
|
346
|
+
end: w.end,
|
|
347
|
+
})),
|
|
348
|
+
});
|
|
349
|
+
}
|
|
350
|
+
}
|
|
351
|
+
|
|
352
|
+
return phrases;
|
|
353
|
+
}
|
|
354
|
+
|
|
165
355
|
// cli
|
|
166
356
|
if (import.meta.main) {
|
|
167
357
|
const { runCli } = await import("../../cli/runner");
|