visionclaw 0.1.13 → 0.1.14
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.
|
@@ -0,0 +1,63 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Use this skill to transcribe audio files (voice messages, recordings) to text. Supports OGG, MP3, WAV, M4A, and other common audio formats. Uses OpenAI Whisper running locally for free, private transcription.
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
# Transcribe Audio
|
|
6
|
+
|
|
7
|
+
Transcribe audio files to text using OpenAI Whisper (local, free, private).
|
|
8
|
+
|
|
9
|
+
## Prerequisites
|
|
10
|
+
|
|
11
|
+
Whisper and ffmpeg must be installed. If not already installed, run:
|
|
12
|
+
|
|
13
|
+
```bash
|
|
14
|
+
pip3 install openai-whisper
|
|
15
|
+
```
|
|
16
|
+
|
|
17
|
+
ffmpeg is required for audio format conversion. On macOS:
|
|
18
|
+
|
|
19
|
+
```bash
|
|
20
|
+
brew install ffmpeg
|
|
21
|
+
```
|
|
22
|
+
|
|
23
|
+
## Steps
|
|
24
|
+
|
|
25
|
+
1. **Download the audio file** if it's a URL:
|
|
26
|
+
```bash
|
|
27
|
+
curl -s -o /tmp/audio_input.ogg "THE_AUDIO_URL"
|
|
28
|
+
```
|
|
29
|
+
|
|
30
|
+
2. **Convert to WAV** (Whisper works best with WAV):
|
|
31
|
+
```bash
|
|
32
|
+
ffmpeg -y -i /tmp/audio_input.ogg -ar 16000 -ac 1 /tmp/audio_input.wav 2>/dev/null
|
|
33
|
+
```
|
|
34
|
+
|
|
35
|
+
3. **Transcribe with Whisper** using the `base` model (fast, good accuracy):
|
|
36
|
+
```bash
|
|
37
|
+
python3 -c "
|
|
38
|
+
import whisper
|
|
39
|
+
model = whisper.load_model('base')
|
|
40
|
+
result = model.transcribe('/tmp/audio_input.wav')
|
|
41
|
+
print(result['text'])
|
|
42
|
+
"
|
|
43
|
+
```
|
|
44
|
+
|
|
45
|
+
4. **Use the transcription** as needed -- respond to the user, take action, etc.
|
|
46
|
+
|
|
47
|
+
## Notes
|
|
48
|
+
|
|
49
|
+
- The `base` model (~150MB) provides good speed/accuracy balance. Use `small` or `medium` for better accuracy on noisy audio.
|
|
50
|
+
- First run downloads the model (~150MB). Subsequent runs are instant.
|
|
51
|
+
- Supports: OGG, MP3, WAV, M4A, FLAC, WEBM, and most common audio formats.
|
|
52
|
+
- Runs entirely locally -- no API calls, no costs, fully private.
|
|
53
|
+
|
|
54
|
+
## Generating Voice Replies
|
|
55
|
+
|
|
56
|
+
To send a voice message back to the user, use macOS text-to-speech:
|
|
57
|
+
|
|
58
|
+
```bash
|
|
59
|
+
say -o /tmp/reply_voice.aiff "Your reply text here"
|
|
60
|
+
ffmpeg -y -i /tmp/reply_voice.aiff /tmp/reply_voice.ogg 2>/dev/null
|
|
61
|
+
```
|
|
62
|
+
|
|
63
|
+
Then send via notify_user with `file_path: "/tmp/reply_voice.ogg"`.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"install.d.ts","sourceRoot":"","sources":["../../src/skills/install.ts"],"names":[],"mappings":"AAQA;;;;GAIG;AACH,wBAAgB,oBAAoB,CAAC,IAAI,GAAE;IAAE,KAAK,CAAC,EAAE,OAAO,CAAA;CAAO,GAAG,IAAI,
|
|
1
|
+
{"version":3,"file":"install.d.ts","sourceRoot":"","sources":["../../src/skills/install.ts"],"names":[],"mappings":"AAQA;;;;GAIG;AACH,wBAAgB,oBAAoB,CAAC,IAAI,GAAE;IAAE,KAAK,CAAC,EAAE,OAAO,CAAA;CAAO,GAAG,IAAI,CAkFzE"}
|
package/dist/skills/install.js
CHANGED
|
@@ -11,10 +11,12 @@ const __dirname = path.dirname(fileURLToPath(import.meta.url));
|
|
|
11
11
|
*/
|
|
12
12
|
export function installBuiltinSkills(opts = {}) {
|
|
13
13
|
const targetDir = getSkillsDir();
|
|
14
|
+
const builtinAssetDir = path.join(__dirname, "..", "builtin-skills");
|
|
14
15
|
// In dev mode (tsx), __dirname points to src/skills and contains built-in skill folders.
|
|
15
16
|
// In built mode, __dirname points to dist/skills which contains compiled JS only.
|
|
16
17
|
// So we must NOT treat dist/skills as the source.
|
|
17
18
|
const candidateDirs = [
|
|
19
|
+
builtinAssetDir,
|
|
18
20
|
__dirname,
|
|
19
21
|
path.join(__dirname, "..", "..", "src", "skills"),
|
|
20
22
|
];
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"install.js","sourceRoot":"","sources":["../../src/skills/install.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,MAAM,SAAS,CAAC;AACzB,OAAO,IAAI,MAAM,WAAW,CAAC;AAC7B,OAAO,EAAE,aAAa,EAAE,MAAM,UAAU,CAAC;AACzC,OAAO,EAAE,YAAY,EAAE,MAAM,oBAAoB,CAAC;AAClD,OAAO,EAAE,MAAM,EAAE,MAAM,cAAc,CAAC;AAEtC,MAAM,SAAS,GAAG,IAAI,CAAC,OAAO,CAAC,aAAa,CAAC,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC;AAE/D;;;;GAIG;AACH,MAAM,UAAU,oBAAoB,CAAC,OAA4B,EAAE;IACjE,MAAM,SAAS,GAAG,YAAY,EAAE,CAAC;IAEjC,yFAAyF;IACzF,kFAAkF;IAClF,kDAAkD;IAClD,MAAM,aAAa,GAAG;QACpB,SAAS;QACT,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,IAAI,EAAE,IAAI,EAAE,KAAK,EAAE,QAAQ,CAAC;KAClD,CAAC;IAEF,IAAI,SAAS,GAAkB,IAAI,CAAC;IACpC,KAAK,MAAM,GAAG,IAAI,aAAa,EAAE,CAAC;QAChC,IAAI,CAAC,EAAE,CAAC,UAAU,CAAC,GAAG,CAAC;YAAE,SAAS;QAElC,gGAAgG;QAChG,IAAI,CAAC;YACH,MAAM,OAAO,GAAG,EAAE,CAAC,WAAW,CAAC,GAAG,EAAE,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,CAAC;YAC7D,MAAM,iBAAiB,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE;gBAC3C,IAAI,CAAC,CAAC,CAAC,WAAW,EAAE;oBAAE,OAAO,KAAK,CAAC;gBACnC,OAAO,EAAE,CAAC,UAAU,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,EAAE,CAAC,CAAC,IAAI,EAAE,UAAU,CAAC,CAAC,CAAC;YAC3D,CAAC,CAAC,CAAC;YACH,IAAI,CAAC,iBAAiB;gBAAE,SAAS;QACnC,CAAC;QAAC,MAAM,CAAC;YACP,SAAS;QACX,CAAC;QAED,SAAS,GAAG,GAAG,CAAC;QAChB,MAAM;IACR,CAAC;IAED,IAAI,CAAC,SAAS,EAAE,CAAC;QACf,MAAM,CAAC,KAAK,CACV,gDAAgD,aAAa,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,CAC5E,CAAC;QACF,OAAO;IACT,CAAC;IAED,MAAM,CAAC,KAAK,CAAC,iCAAiC,SAAS,EAAE,CAAC,CAAC;IAE3D,IAAI,CAAC,EAAE,CAAC,UAAU,CAAC,SAAS,CAAC,EAAE,CAAC;QAC9B,EAAE,CAAC,SAAS,CAAC,SAAS,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;IAC/C,CAAC;IAED,MAAM,OAAO,GAAG,EAAE,CAAC,WAAW,CAAC,SAAS,EAAE,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,CAAC;IAEnE,KAAK,MAAM,KAAK,IAAI,OAAO,EAAE,CAAC;QAC5B,sDAAsD;QACtD,IAAI,CAAC,KAAK,CAAC,WAAW,EAAE;YAAE,SAAS;QAEnC,MAAM,WAAW,GAAG,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,KAAK,CAAC,IAAI,CAAC,CAAC;QACrD,MAAM,WAAW,GAAG,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,KAAK,CAAC,IAAI,CAAC,CAAC;QACrD,MAAM,SAAS,GAAG,IAAI,CAAC,IAAI,CAAC,WAAW,EAAE,UAAU,CAAC,CAAC;QAErD,mCAAmC;QACnC,IAAI,CAAC,EAAE,CAAC,UAAU,CAAC,SAAS,CAAC;YAAE,SAAS;QAExC,MAAM,aAAa,GAAG,IAAI,CAAC,IAAI,CAAC,WAAW,EAAE,UAAU,CAAC,CAAC;QACzD,IAAI,CAAC,IAAI,CAAC,KAAK,IAAI,EAAE,CAAC,UAAU,CAAC,aAAa,CAAC,EAAE,CAAC;YAChD,MAAM,CAAC,KAAK,CAAC,UAAU,KAAK,CAAC,IAAI,+BAA+B,CAAC,CAAC;YAClE,SAAS;QACX,CAAC;QAED,2BAA2B;QAC3B,IAAI,CAAC,EAAE,CAAC,UAAU,CAAC,WAAW,CAAC,EAAE,CAAC;YAChC,EAAE,CAAC,SAAS,CAAC,WAAW,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;QACjD,CAAC;QAED,MAAM,KAAK,GAAG,EAAE,CAAC,WAAW,CAAC,WAAW,CAAC,CAAC;QAC1C,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;YACzB,MAAM,GAAG,GAAG,IAAI,CAAC,IAAI,CAAC,WAAW,EAAE,IAAI,CAAC,CAAC;YACzC,MAAM,GAAG,GAAG,IAAI,CAAC,IAAI,CAAC,WAAW,EAAE,IAAI,CAAC,CAAC;YACzC,8EAA8E;YAC9E,IAAI,CAAC,IAAI,CAAC,KAAK,IAAI,EAAE,CAAC,UAAU,CAAC,GAAG,CAAC;gBAAE,SAAS;YAChD,EAAE,CAAC,YAAY,CAAC,GAAG,EAAE,GAAG,CAAC,CAAC;QAC5B,CAAC;QAED,MAAM,CAAC,MAAM,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,aAAa,CAAC,CAAC,CAAC,WAAW,oBAAoB,KAAK,CAAC,IAAI,EAAE,CAAC,CAAC;IAC7F,CAAC;AACH,CAAC"}
|
|
1
|
+
{"version":3,"file":"install.js","sourceRoot":"","sources":["../../src/skills/install.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,MAAM,SAAS,CAAC;AACzB,OAAO,IAAI,MAAM,WAAW,CAAC;AAC7B,OAAO,EAAE,aAAa,EAAE,MAAM,UAAU,CAAC;AACzC,OAAO,EAAE,YAAY,EAAE,MAAM,oBAAoB,CAAC;AAClD,OAAO,EAAE,MAAM,EAAE,MAAM,cAAc,CAAC;AAEtC,MAAM,SAAS,GAAG,IAAI,CAAC,OAAO,CAAC,aAAa,CAAC,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC;AAE/D;;;;GAIG;AACH,MAAM,UAAU,oBAAoB,CAAC,OAA4B,EAAE;IACjE,MAAM,SAAS,GAAG,YAAY,EAAE,CAAC;IAEjC,MAAM,eAAe,GAAG,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,IAAI,EAAE,gBAAgB,CAAC,CAAC;IAErE,yFAAyF;IACzF,kFAAkF;IAClF,kDAAkD;IAClD,MAAM,aAAa,GAAG;QACpB,eAAe;QACf,SAAS;QACT,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,IAAI,EAAE,IAAI,EAAE,KAAK,EAAE,QAAQ,CAAC;KAClD,CAAC;IAEF,IAAI,SAAS,GAAkB,IAAI,CAAC;IACpC,KAAK,MAAM,GAAG,IAAI,aAAa,EAAE,CAAC;QAChC,IAAI,CAAC,EAAE,CAAC,UAAU,CAAC,GAAG,CAAC;YAAE,SAAS;QAElC,gGAAgG;QAChG,IAAI,CAAC;YACH,MAAM,OAAO,GAAG,EAAE,CAAC,WAAW,CAAC,GAAG,EAAE,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,CAAC;YAC7D,MAAM,iBAAiB,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE;gBAC3C,IAAI,CAAC,CAAC,CAAC,WAAW,EAAE;oBAAE,OAAO,KAAK,CAAC;gBACnC,OAAO,EAAE,CAAC,UAAU,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,EAAE,CAAC,CAAC,IAAI,EAAE,UAAU,CAAC,CAAC,CAAC;YAC3D,CAAC,CAAC,CAAC;YACH,IAAI,CAAC,iBAAiB;gBAAE,SAAS;QACnC,CAAC;QAAC,MAAM,CAAC;YACP,SAAS;QACX,CAAC;QAED,SAAS,GAAG,GAAG,CAAC;QAChB,MAAM;IACR,CAAC;IAED,IAAI,CAAC,SAAS,EAAE,CAAC;QACf,MAAM,CAAC,KAAK,CACV,gDAAgD,aAAa,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,CAC5E,CAAC;QACF,OAAO;IACT,CAAC;IAED,MAAM,CAAC,KAAK,CAAC,iCAAiC,SAAS,EAAE,CAAC,CAAC;IAE3D,IAAI,CAAC,EAAE,CAAC,UAAU,CAAC,SAAS,CAAC,EAAE,CAAC;QAC9B,EAAE,CAAC,SAAS,CAAC,SAAS,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;IAC/C,CAAC;IAED,MAAM,OAAO,GAAG,EAAE,CAAC,WAAW,CAAC,SAAS,EAAE,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,CAAC;IAEnE,KAAK,MAAM,KAAK,IAAI,OAAO,EAAE,CAAC;QAC5B,sDAAsD;QACtD,IAAI,CAAC,KAAK,CAAC,WAAW,EAAE;YAAE,SAAS;QAEnC,MAAM,WAAW,GAAG,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,KAAK,CAAC,IAAI,CAAC,CAAC;QACrD,MAAM,WAAW,GAAG,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,KAAK,CAAC,IAAI,CAAC,CAAC;QACrD,MAAM,SAAS,GAAG,IAAI,CAAC,IAAI,CAAC,WAAW,EAAE,UAAU,CAAC,CAAC;QAErD,mCAAmC;QACnC,IAAI,CAAC,EAAE,CAAC,UAAU,CAAC,SAAS,CAAC;YAAE,SAAS;QAExC,MAAM,aAAa,GAAG,IAAI,CAAC,IAAI,CAAC,WAAW,EAAE,UAAU,CAAC,CAAC;QACzD,IAAI,CAAC,IAAI,CAAC,KAAK,IAAI,EAAE,CAAC,UAAU,CAAC,aAAa,CAAC,EAAE,CAAC;YAChD,MAAM,CAAC,KAAK,CAAC,UAAU,KAAK,CAAC,IAAI,+BAA+B,CAAC,CAAC;YAClE,SAAS;QACX,CAAC;QAED,2BAA2B;QAC3B,IAAI,CAAC,EAAE,CAAC,UAAU,CAAC,WAAW,CAAC,EAAE,CAAC;YAChC,EAAE,CAAC,SAAS,CAAC,WAAW,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;QACjD,CAAC;QAED,MAAM,KAAK,GAAG,EAAE,CAAC,WAAW,CAAC,WAAW,CAAC,CAAC;QAC1C,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;YACzB,MAAM,GAAG,GAAG,IAAI,CAAC,IAAI,CAAC,WAAW,EAAE,IAAI,CAAC,CAAC;YACzC,MAAM,GAAG,GAAG,IAAI,CAAC,IAAI,CAAC,WAAW,EAAE,IAAI,CAAC,CAAC;YACzC,8EAA8E;YAC9E,IAAI,CAAC,IAAI,CAAC,KAAK,IAAI,EAAE,CAAC,UAAU,CAAC,GAAG,CAAC;gBAAE,SAAS;YAChD,EAAE,CAAC,YAAY,CAAC,GAAG,EAAE,GAAG,CAAC,CAAC;QAC5B,CAAC;QAED,MAAM,CAAC,MAAM,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,aAAa,CAAC,CAAC,CAAC,WAAW,oBAAoB,KAAK,CAAC,IAAI,EAAE,CAAC,CAAC;IAC7F,CAAC;AACH,CAAC"}
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "visionclaw",
|
|
3
|
-
"version": "0.1.
|
|
3
|
+
"version": "0.1.14",
|
|
4
4
|
"description": "A personal assistant agent that runs on your desktop, receives commands from messaging channels, and executes tasks autonomously.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "dist/index.js",
|
|
@@ -9,6 +9,7 @@
|
|
|
9
9
|
},
|
|
10
10
|
"files": [
|
|
11
11
|
"dist/**/*",
|
|
12
|
+
"dist/builtin-skills/**/*",
|
|
12
13
|
"README.md"
|
|
13
14
|
],
|
|
14
15
|
"dependencies": {
|
|
@@ -45,7 +46,7 @@
|
|
|
45
46
|
"node": ">=20.0.0"
|
|
46
47
|
},
|
|
47
48
|
"scripts": {
|
|
48
|
-
"build": "tsc",
|
|
49
|
+
"build": "tsc && node scripts/copy-builtin-skills.mjs",
|
|
49
50
|
"dev": "tsx src/index.ts",
|
|
50
51
|
"start": "node dist/index.js",
|
|
51
52
|
"lint": "eslint src/",
|