voice-bird-cli 0.3.1__py3-none-any.whl
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.
- voice_bird_cli/__init__.py +4 -0
- voice_bird_cli/__main__.py +36 -0
- voice_bird_cli-0.3.1.dist-info/METADATA +132 -0
- voice_bird_cli-0.3.1.dist-info/RECORD +8 -0
- voice_bird_cli-0.3.1.dist-info/WHEEL +5 -0
- voice_bird_cli-0.3.1.dist-info/entry_points.txt +2 -0
- voice_bird_cli-0.3.1.dist-info/licenses/LICENSE +21 -0
- voice_bird_cli-0.3.1.dist-info/top_level.txt +1 -0
|
@@ -0,0 +1,36 @@
|
|
|
1
|
+
from __future__ import annotations
|
|
2
|
+
|
|
3
|
+
import os
|
|
4
|
+
import subprocess
|
|
5
|
+
import sys
|
|
6
|
+
from pathlib import Path
|
|
7
|
+
|
|
8
|
+
|
|
9
|
+
def _cargo_bin() -> Path:
|
|
10
|
+
name = "voice-bird-cli.exe" if os.name == "nt" else "voice-bird-cli"
|
|
11
|
+
return Path.home() / ".cargo" / "bin" / name
|
|
12
|
+
|
|
13
|
+
|
|
14
|
+
def main() -> int:
|
|
15
|
+
exe = _cargo_bin()
|
|
16
|
+
if not exe.exists():
|
|
17
|
+
try:
|
|
18
|
+
subprocess.run(
|
|
19
|
+
["cargo", "install", "voice-bird-cli", "--locked"],
|
|
20
|
+
check=True,
|
|
21
|
+
)
|
|
22
|
+
except FileNotFoundError:
|
|
23
|
+
print(
|
|
24
|
+
"voice-bird-cli PyPI package requires Rust Cargo. "
|
|
25
|
+
"Install Rust from https://rustup.rs/ and run this command again.",
|
|
26
|
+
file=sys.stderr,
|
|
27
|
+
)
|
|
28
|
+
return 1
|
|
29
|
+
except subprocess.CalledProcessError as exc:
|
|
30
|
+
return exc.returncode
|
|
31
|
+
|
|
32
|
+
return subprocess.run([str(exe), *sys.argv[1:]]).returncode
|
|
33
|
+
|
|
34
|
+
|
|
35
|
+
if __name__ == "__main__":
|
|
36
|
+
raise SystemExit(main())
|
|
@@ -0,0 +1,132 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: voice-bird-cli
|
|
3
|
+
Version: 0.3.1
|
|
4
|
+
Summary: Voice Bird CLI - local-first voice transcription TUI
|
|
5
|
+
Author: Voice Bird contributors
|
|
6
|
+
License-Expression: MIT
|
|
7
|
+
Project-URL: Homepage, https://github.com/voice-bird/voice-bird-cli
|
|
8
|
+
Project-URL: Repository, https://github.com/voice-bird/voice-bird-cli
|
|
9
|
+
Project-URL: Issues, https://github.com/voice-bird/voice-bird-cli/issues
|
|
10
|
+
Keywords: voice,transcription,whisper,cli,tui
|
|
11
|
+
Classifier: Development Status :: 4 - Beta
|
|
12
|
+
Classifier: Environment :: Console
|
|
13
|
+
Classifier: Intended Audience :: End Users/Desktop
|
|
14
|
+
Classifier: Programming Language :: Rust
|
|
15
|
+
Classifier: Programming Language :: Python :: 3
|
|
16
|
+
Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
|
|
17
|
+
Requires-Python: >=3.9
|
|
18
|
+
Description-Content-Type: text/markdown
|
|
19
|
+
License-File: LICENSE
|
|
20
|
+
Dynamic: license-file
|
|
21
|
+
|
|
22
|
+
# Voice Bird CLI
|
|
23
|
+
|
|
24
|
+
Voice Bird CLI is a terminal voice transcription app. It runs **locally by default** with Whisper models, so local recordings stay on your machine. When you want hosted transcription, you can opt in per source to VoiceBird Web cloud mode.
|
|
25
|
+
|
|
26
|
+

|
|
27
|
+
|
|
28
|
+
## Basic Flow
|
|
29
|
+
|
|
30
|
+
1. Pick a microphone, system-output loopback device, or app audio source.
|
|
31
|
+
2. Choose local or cloud mode for that source.
|
|
32
|
+
3. Press `Enter` to start a transcription slot.
|
|
33
|
+
4. Watch committed and tentative transcript text stream into the TUI.
|
|
34
|
+
5. In local mode, review session files under `~/voice-bird/sessions/<timestamp>-<source>/`.
|
|
35
|
+
|
|
36
|
+
Local sessions contain:
|
|
37
|
+
|
|
38
|
+
| File | Content |
|
|
39
|
+
| --- | --- |
|
|
40
|
+
| `audio.wav` | 16 kHz mono recording |
|
|
41
|
+
| `transcript.jsonl` | Append-only transcript log, useful after crashes |
|
|
42
|
+
| `transcript.json` | Finalized transcript segments and metadata |
|
|
43
|
+
| `transcript.txt` | Plain-text transcript |
|
|
44
|
+
| `meta.json` | Device, source, model, engine, and duration |
|
|
45
|
+
|
|
46
|
+
## Getting Started
|
|
47
|
+
|
|
48
|
+
Install one of the CLI packages, then run:
|
|
49
|
+
|
|
50
|
+
```bash
|
|
51
|
+
voice-bird-cli
|
|
52
|
+
```
|
|
53
|
+
|
|
54
|
+
On first launch, Voice Bird picks a local Whisper model and downloads it into your OS cache directory. The default model is `distil-small.en`. Settings are stored in `~/.config/voice-bird/config.toml` on Linux/macOS and `%APPDATA%\voice-bird\config.toml` on Windows.
|
|
55
|
+
|
|
56
|
+
macOS users may need to grant Screen Recording permission for system or app audio capture. Apple Silicon users can optionally build the WhisperKit sidecar for ANE-accelerated local inference:
|
|
57
|
+
|
|
58
|
+
```bash
|
|
59
|
+
cargo run -p xtask -- build-sidecar
|
|
60
|
+
```
|
|
61
|
+
|
|
62
|
+
Without the sidecar, Voice Bird falls back to `whisper-rs` with whisper.cpp.
|
|
63
|
+
|
|
64
|
+
## Install
|
|
65
|
+
|
|
66
|
+
Cargo installs the native Rust binary directly:
|
|
67
|
+
|
|
68
|
+
```bash
|
|
69
|
+
cargo install voice-bird-cli
|
|
70
|
+
```
|
|
71
|
+
|
|
72
|
+
PyPI installs a small wrapper that installs/runs the Cargo binary:
|
|
73
|
+
|
|
74
|
+
```bash
|
|
75
|
+
pipx install voice-bird-cli
|
|
76
|
+
# or
|
|
77
|
+
pip install voice-bird-cli
|
|
78
|
+
```
|
|
79
|
+
|
|
80
|
+
npm installs a small wrapper that installs/runs the Cargo binary:
|
|
81
|
+
|
|
82
|
+
```bash
|
|
83
|
+
npm install -g voice-bird-cli
|
|
84
|
+
```
|
|
85
|
+
|
|
86
|
+
From source:
|
|
87
|
+
|
|
88
|
+
```bash
|
|
89
|
+
git clone https://github.com/voice-bird/voice-bird-cli.git
|
|
90
|
+
cd voice-bird-cli
|
|
91
|
+
cargo install --path .
|
|
92
|
+
```
|
|
93
|
+
|
|
94
|
+
The npm and PyPI packages require Rust Cargo on the machine. Use the Cargo or source install when you want the simplest path.
|
|
95
|
+
|
|
96
|
+
## Local And Cloud Modes
|
|
97
|
+
|
|
98
|
+
**Free local mode** is the default. It uses local Whisper inference through `whisper-rs`, or WhisperKit on macOS when the sidecar is available. Local mode does not send audio to a server and writes session artifacts to disk. Current local models are English-focused in the app flow.
|
|
99
|
+
|
|
100
|
+
**Cloud mode** streams audio to VoiceBird Web at `wss://voicebird.app/api/audio/stream`. It is opt-in, requires a Voice Bird API key, and is useful when local hardware cannot keep up or when you want cloud language support. Cloud recordings live in your VoiceBird Web account instead of the local sessions folder.
|
|
101
|
+
|
|
102
|
+
Your Voice Bird API key is stored in plaintext in `config.toml`; on Unix the app sets the file to `0600` best-effort.
|
|
103
|
+
|
|
104
|
+
## Usage
|
|
105
|
+
|
|
106
|
+
```bash
|
|
107
|
+
voice-bird-cli # start the TUI
|
|
108
|
+
voice-bird-cli --recover <session-dir> # rebuild transcript.{json,txt} after a crash
|
|
109
|
+
```
|
|
110
|
+
|
|
111
|
+
## Keys
|
|
112
|
+
|
|
113
|
+
| Key | Action |
|
|
114
|
+
| --- | --- |
|
|
115
|
+
| `↑` / `↓` | Select device or app |
|
|
116
|
+
| `←` / `→` | Move between panes |
|
|
117
|
+
| `Enter` | Start the selected source |
|
|
118
|
+
| `Space` | Clear selected app pairing |
|
|
119
|
+
| `Tab` | Move between transcript slots |
|
|
120
|
+
| `r` | Refresh devices and apps |
|
|
121
|
+
| `c` | Toggle cloud mode for the focused source |
|
|
122
|
+
| `l` | Change language for cloud mode |
|
|
123
|
+
| `m` | Change model |
|
|
124
|
+
| `e` | Export the latest local transcript |
|
|
125
|
+
| `p` | Change local session path |
|
|
126
|
+
| `x` | Clear stopped transcript slot |
|
|
127
|
+
| `q` | Quit |
|
|
128
|
+
| `?` | Help |
|
|
129
|
+
|
|
130
|
+
## License
|
|
131
|
+
|
|
132
|
+
MIT
|
|
@@ -0,0 +1,8 @@
|
|
|
1
|
+
voice_bird_cli/__init__.py,sha256=GnhPpd5iCcPsYMYfemeGjWHzpt_8HxKxWVzHZJfY5XQ,106
|
|
2
|
+
voice_bird_cli/__main__.py,sha256=t6wZ_7YQhj5A29exXckw0DA7moUfzoL2Iu5kvMPUE5c,953
|
|
3
|
+
voice_bird_cli-0.3.1.dist-info/licenses/LICENSE,sha256=zAzaev0b27MovZwrIKxX_aZcfQ21msdp44ziY6qrenQ,1080
|
|
4
|
+
voice_bird_cli-0.3.1.dist-info/METADATA,sha256=QfSibmNTEW_j8T59z6joj5rVOQtGBBnIlTLm6XddHSE,4582
|
|
5
|
+
voice_bird_cli-0.3.1.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
|
|
6
|
+
voice_bird_cli-0.3.1.dist-info/entry_points.txt,sha256=tGxMUfUEI9q2JVEqFXJTHkvL7wINtZyqaGhwmifHSmY,64
|
|
7
|
+
voice_bird_cli-0.3.1.dist-info/top_level.txt,sha256=EM9HOTtPsqEQM0dGySWzTmVP8pxrauILSA41t8IZJmo,15
|
|
8
|
+
voice_bird_cli-0.3.1.dist-info/RECORD,,
|
|
@@ -0,0 +1,21 @@
|
|
|
1
|
+
MIT License
|
|
2
|
+
|
|
3
|
+
Copyright (c) 2026 Voice Bird contributors
|
|
4
|
+
|
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
|
7
|
+
in the Software without restriction, including without limitation the rights
|
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
|
10
|
+
furnished to do so, subject to the following conditions:
|
|
11
|
+
|
|
12
|
+
The above copyright notice and this permission notice shall be included in all
|
|
13
|
+
copies or substantial portions of the Software.
|
|
14
|
+
|
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
|
21
|
+
SOFTWARE.
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
voice_bird_cli
|