You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+40-24Lines changed: 40 additions & 24 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -5,8 +5,29 @@
5
5
6
6
## Description
7
7
8
-
Wave is a lightweight, native macOS dictation app focused on fast voice-to-text workflows with local transcription and minimal UI overhead. Speak with a global shortcut, transcribe locally with Whisper, and paste instantly into the active app.
8
+
Wave is a lightweight, native macOS dictation app focused on fast voice-to-text workflows with minimal UI overhead. Press a shortcut, speak, and your words are instantly pasted at the cursor. Supports on-device transcription via Whisper and cloud transcription via Groq, plus an AI Mode that sends your voice to an LLM and pastes the response directly.
9
9
10
+
## Features
11
+
12
+
-**Dictation** — global shortcut triggers recording; transcription is pasted at the active cursor
13
+
-**Push to Talk or Toggle** — hold to record and release, or press once to start and again to stop
14
+
-**Local transcription** — on-device Whisper inference, no internet required
15
+
-**Groq cloud transcription** — faster cloud-based transcription via the Groq API
16
+
-**AI Mode** — separate shortcut sends your voice to an LLM and pastes a direct answer
17
+
-**Snippets** — save reusable text snippets; AI Mode is aware of them
18
+
-**Dictation history** — recent transcriptions with right-click copy
19
+
-**Language selection** — auto-detect or set a specific language (ISO 639-1)
20
+
-**Custom vocabulary** — bias the model toward specific words and names
21
+
-**Microphone selection** — choose any input device or use the system default
22
+
23
+
## Default shortcuts
24
+
25
+
| Action | Default |
26
+
|---|---|
27
+
| Dictation |`Fn`|
28
+
| AI Mode |`Right Option`|
29
+
30
+
Both shortcuts are fully customizable in Settings → Shortcut.
10
31
11
32
## Quick start
12
33
@@ -23,46 +44,41 @@ Download the latest DMG from [Releases](https://github.com/mxvsh/wave/releases/l
23
44
24
45
## Build from source
25
46
26
-
Build the app:
27
-
28
47
```bash
29
48
make build
30
49
```
31
50
32
-
Open:
33
51
```bash
34
52
open build/Build/Products/Release/Wave.app
35
53
```
36
54
37
-
Or launch from Xcode:
38
-
- Open `Wave.xcodeproj`
39
-
- Select scheme `Wave`
40
-
- Run
55
+
Or launch from Xcode — open `Wave.xcodeproj`, select the `Wave` scheme, and run.
41
56
42
57
## Roadmap
43
58
44
-
-[x] Toggle-style recording mode from settings
45
-
-[x] Local/offline transcription with Whisper models
46
-
-[x] Add optional text cleanup modes (punctuation, capitalization, concise cleanup)
47
-
-[x] Add support for custom dictionary words
48
-
-[ ] Add app-specific behavior profiles (different formatting for IDE/chat/docs)
49
-
-[ ] Add recent dictation history with one-click reinsert/copy
50
-
-[ ] Add quality presets for speed vs accuracy
51
-
-[ ] Add AI agent mode: speak natural-language instructions to write or edit selected text
59
+
-[x] Toggle and Push to Talk recording modes
60
+
-[x] Local offline transcription with Whisper
61
+
-[x] Groq cloud transcription
62
+
-[x] AI Mode with LLM response via Groq
63
+
-[x] Custom dictionary / vocabulary
64
+
-[x] Language selection
65
+
-[x] Dictation history with copy
66
+
-[x] Snippets with AI awareness
67
+
-[x] Microphone selection
68
+
-[ ] App-specific behavior profiles
69
+
-[ ] Quality presets for speed vs accuracy
52
70
53
71
## Support
54
72
55
-
For any feedback or assistance, join the [Discord](https://discord.gg/6YznRVc23J) community.
56
-
For feature requests, bug reports, or help, you can also create a GitHub issue.
73
+
Join the [Discord](https://discord.gg/6YznRVc23J) community for feedback and help.
74
+
For bug reports and feature requests, open a GitHub issue.
57
75
58
76
## Credits
59
77
60
-
-[whisper.cpp](https://github.com/ggml-org/whisper.cpp)for local speech-to-text inference
61
-
-[Sparkle](https://sparkle-project.org/)for macOS update framework support
62
-
-Apple SwiftUI/AppKit ecosystem for native macOS app foundations
78
+
-[whisper.cpp](https://github.com/ggml-org/whisper.cpp)— local speech-to-text inference
0 commit comments