@luxass/pi-voice 0.0.0 → 0.1.0
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/README.md +29 -0
- package/package.json +9 -2
package/README.md
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
1
|
+
# @luxass/pi-voice
|
|
2
|
+
|
|
3
|
+
Record speech and paste the transcription into [Pi](https://github.com/badlogic/pi-mono)'s composer.
|
|
4
|
+
|
|
5
|
+
## Install
|
|
6
|
+
|
|
7
|
+
```sh
|
|
8
|
+
pi install npm:@luxass/pi-voice
|
|
9
|
+
```
|
|
10
|
+
|
|
11
|
+
Recording requires `sox` on your `PATH`. For local transcription, you also need `whisper-cli` and a compatible Whisper model. Alternatively, add an API transcription profile; that does not require a local Whisper installation.
|
|
12
|
+
|
|
13
|
+
## Use
|
|
14
|
+
|
|
15
|
+
Press **Ctrl+Shift+V** or run `/voice-record` to start recording. Press it again to stop, transcribe, and paste the result into the composer. The extension does not send your message for you.
|
|
16
|
+
|
|
17
|
+
| Command | Purpose |
|
|
18
|
+
| ---------------------- | ----------------------------------------------- |
|
|
19
|
+
| `/voice-record` | Start or stop recording and transcribe on stop. |
|
|
20
|
+
| `/voice-cancel` | Discard the current recording. |
|
|
21
|
+
| `/voice-device` | Choose an input device or the system default. |
|
|
22
|
+
| `/voice-profile add` | Create a local or API transcription profile. |
|
|
23
|
+
| `/voice-profile` | Switch between saved profiles. |
|
|
24
|
+
| `/voice-profile model` | Change the active API profile's model. |
|
|
25
|
+
| `/voice-status` | Show the current profile and input device. |
|
|
26
|
+
|
|
27
|
+
Without a saved profile, transcription uses automatic local model discovery. For API transcription, `/voice-profile add` asks for the endpoint, model, request format, and **name of an environment variable** holding the API key. Keep the key in your environment, not in the settings file.
|
|
28
|
+
|
|
29
|
+
Settings are saved to Pi's agent directory as `voice-settings.json`. Set `AGENT_VOICE_SETTINGS` to use a different settings file.
|
package/package.json
CHANGED
|
@@ -1,11 +1,18 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@luxass/pi-voice",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.1.0",
|
|
4
|
+
"description": "Voice recording and transcription for Pi",
|
|
4
5
|
"keywords": [
|
|
5
6
|
"pi-package"
|
|
6
7
|
],
|
|
8
|
+
"repository": {
|
|
9
|
+
"type": "git",
|
|
10
|
+
"url": "https://github.com/luxass/pi-extensions",
|
|
11
|
+
"directory": "packages/pi-voice"
|
|
12
|
+
},
|
|
7
13
|
"files": [
|
|
8
|
-
"src"
|
|
14
|
+
"src",
|
|
15
|
+
"README.md"
|
|
9
16
|
],
|
|
10
17
|
"type": "module",
|
|
11
18
|
"publishConfig": {
|