@drakulavich/kesha-voice-kit 1.0.9 → 1.0.10
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/README.md +19 -17
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -37,34 +37,36 @@ bun add -g @drakulavich/kesha-voice-kit
|
|
|
37
37
|
kesha install
|
|
38
38
|
```
|
|
39
39
|
|
|
40
|
-
**Then
|
|
40
|
+
**Then configure OpenClaw to use Kesha for audio transcription:**
|
|
41
41
|
|
|
42
42
|
```bash
|
|
43
43
|
openclaw plugins install @drakulavich/kesha-voice-kit
|
|
44
|
+
openclaw config set tools.media.audio.models \
|
|
45
|
+
'[{"type":"cli","command":"kesha","args":["--format","transcript","{{MediaPath}}"],"timeoutSeconds":15}]'
|
|
46
|
+
openclaw config set tools.media.audio.enabled true
|
|
47
|
+
openclaw gateway restart
|
|
44
48
|
```
|
|
45
49
|
|
|
46
|
-
|
|
50
|
+
Your agent receives a voice message in Telegram/WhatsApp/Slack, Kesha transcribes it locally, and the agent sees enriched context:
|
|
47
51
|
|
|
48
|
-
Manage the plugin afterwards with `openclaw plugins list`, `openclaw plugins disable kesha-voice-kit`, or `openclaw plugins uninstall kesha-voice-kit`.
|
|
49
|
-
|
|
50
|
-
Your agent receives a voice message in Telegram/WhatsApp/Slack, Kesha transcribes it locally, and the transcript flows back into the agent loop:
|
|
51
|
-
|
|
52
|
-
```json
|
|
53
|
-
{
|
|
54
|
-
"text": "Привет, как дела?",
|
|
55
|
-
"model": "parakeet-tdt-0.6b-v3"
|
|
56
|
-
}
|
|
57
52
|
```
|
|
53
|
+
Привет, как дела?
|
|
54
|
+
[lang: ru, confidence: 1.00]
|
|
55
|
+
```
|
|
56
|
+
|
|
57
|
+
Manage the plugin with `openclaw plugins list`, `openclaw plugins disable kesha-voice-kit`, or `openclaw plugins uninstall kesha-voice-kit`.
|
|
58
58
|
|
|
59
59
|
## CLI Tools
|
|
60
60
|
|
|
61
61
|
```bash
|
|
62
|
-
kesha install
|
|
63
|
-
kesha audio.ogg
|
|
64
|
-
kesha --
|
|
65
|
-
kesha --
|
|
66
|
-
kesha --
|
|
67
|
-
kesha
|
|
62
|
+
kesha install # download engine and models
|
|
63
|
+
kesha audio.ogg # transcribe (plain text)
|
|
64
|
+
kesha --format transcript audio.ogg # text + language/confidence
|
|
65
|
+
kesha --format json audio.ogg # full JSON with lang fields
|
|
66
|
+
kesha --json audio.ogg # alias for --format json
|
|
67
|
+
kesha --verbose audio.ogg # show language detection details
|
|
68
|
+
kesha --lang en audio.ogg # warn if detected language differs
|
|
69
|
+
kesha status # show installed backend info
|
|
68
70
|
```
|
|
69
71
|
|
|
70
72
|
Stdout: transcript. Stderr: errors. Pipe-friendly.
|