voice-mode 4.3.1__py3-none-any.whl → 4.4.0__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_mode/__version__.py +1 -1
- voice_mode/cli.py +3 -2
- voice_mode/cli_commands/claude.py +6 -199
- voice_mode/cli_commands/hook.py +13 -16
- voice_mode/frontend/.next/BUILD_ID +1 -1
- voice_mode/frontend/.next/app-build-manifest.json +5 -5
- voice_mode/frontend/.next/build-manifest.json +3 -3
- voice_mode/frontend/.next/next-minimal-server.js.nft.json +1 -1
- voice_mode/frontend/.next/next-server.js.nft.json +1 -1
- voice_mode/frontend/.next/prerender-manifest.json +1 -1
- voice_mode/frontend/.next/required-server-files.json +1 -1
- voice_mode/frontend/.next/server/app/_not-found/page.js +1 -1
- voice_mode/frontend/.next/server/app/_not-found/page_client-reference-manifest.js +1 -1
- voice_mode/frontend/.next/server/app/_not-found.html +1 -1
- voice_mode/frontend/.next/server/app/_not-found.rsc +1 -1
- voice_mode/frontend/.next/server/app/api/connection-details/route.js +2 -2
- voice_mode/frontend/.next/server/app/favicon.ico/route.js +2 -2
- voice_mode/frontend/.next/server/app/index.html +1 -1
- voice_mode/frontend/.next/server/app/index.rsc +2 -2
- voice_mode/frontend/.next/server/app/page.js +3 -3
- voice_mode/frontend/.next/server/app/page_client-reference-manifest.js +1 -1
- voice_mode/frontend/.next/server/chunks/994.js +1 -1
- voice_mode/frontend/.next/server/middleware-build-manifest.js +1 -1
- voice_mode/frontend/.next/server/next-font-manifest.js +1 -1
- voice_mode/frontend/.next/server/next-font-manifest.json +1 -1
- voice_mode/frontend/.next/server/pages/404.html +1 -1
- voice_mode/frontend/.next/server/pages/500.html +1 -1
- voice_mode/frontend/.next/server/server-reference-manifest.json +1 -1
- voice_mode/frontend/.next/standalone/.next/BUILD_ID +1 -1
- voice_mode/frontend/.next/standalone/.next/app-build-manifest.json +5 -5
- voice_mode/frontend/.next/standalone/.next/build-manifest.json +3 -3
- voice_mode/frontend/.next/standalone/.next/prerender-manifest.json +1 -1
- voice_mode/frontend/.next/standalone/.next/required-server-files.json +1 -1
- voice_mode/frontend/.next/standalone/.next/server/app/_not-found/page.js +1 -1
- voice_mode/frontend/.next/standalone/.next/server/app/_not-found/page_client-reference-manifest.js +1 -1
- voice_mode/frontend/.next/standalone/.next/server/app/_not-found.html +1 -1
- voice_mode/frontend/.next/standalone/.next/server/app/_not-found.rsc +1 -1
- voice_mode/frontend/.next/standalone/.next/server/app/api/connection-details/route.js +2 -2
- voice_mode/frontend/.next/standalone/.next/server/app/favicon.ico/route.js +2 -2
- voice_mode/frontend/.next/standalone/.next/server/app/index.html +1 -1
- voice_mode/frontend/.next/standalone/.next/server/app/index.rsc +2 -2
- voice_mode/frontend/.next/standalone/.next/server/app/page.js +3 -3
- voice_mode/frontend/.next/standalone/.next/server/app/page_client-reference-manifest.js +1 -1
- voice_mode/frontend/.next/standalone/.next/server/chunks/994.js +1 -1
- voice_mode/frontend/.next/standalone/.next/server/middleware-build-manifest.js +1 -1
- voice_mode/frontend/.next/standalone/.next/server/next-font-manifest.js +1 -1
- voice_mode/frontend/.next/standalone/.next/server/next-font-manifest.json +1 -1
- voice_mode/frontend/.next/standalone/.next/server/pages/404.html +1 -1
- voice_mode/frontend/.next/standalone/.next/server/pages/500.html +1 -1
- voice_mode/frontend/.next/standalone/.next/server/server-reference-manifest.json +1 -1
- voice_mode/frontend/.next/standalone/server.js +1 -1
- voice_mode/frontend/.next/static/chunks/app/{layout-b52135f331b36caf.js → layout-917e8410913fe899.js} +1 -1
- voice_mode/frontend/.next/static/chunks/app/{page-43b7b45e01f0aa87.js → page-ae0d14863ed895ea.js} +1 -1
- voice_mode/frontend/.next/static/chunks/{main-app-80dc9078926fc708.js → main-app-836e76fc70b52220.js} +1 -1
- voice_mode/frontend/.next/trace +43 -43
- voice_mode/frontend/.next/types/app/api/connection-details/route.ts +1 -1
- voice_mode/frontend/.next/types/app/layout.ts +1 -1
- voice_mode/frontend/.next/types/app/page.ts +1 -1
- voice_mode/frontend/package-lock.json +9 -9
- voice_mode/statistics_tracking.py +42 -0
- voice_mode/tools/__init__.py +41 -15
- voice_mode/tools/converse.py +1 -1
- voice_mode/tools/statistics.py +0 -33
- {voice_mode-4.3.1.dist-info → voice_mode-4.4.0.dist-info}/METADATA +33 -40
- {voice_mode-4.3.1.dist-info → voice_mode-4.4.0.dist-info}/RECORD +69 -69
- voice_mode/tools/claude_thinking.py +0 -285
- /voice_mode/frontend/.next/static/{uZHYPdRYOObTZ3MQHekp0 → WhZriRkBKVNPSmCnOFRav}/_buildManifest.js +0 -0
- /voice_mode/frontend/.next/static/{uZHYPdRYOObTZ3MQHekp0 → WhZriRkBKVNPSmCnOFRav}/_ssgManifest.js +0 -0
- {voice_mode-4.3.1.dist-info → voice_mode-4.4.0.dist-info}/WHEEL +0 -0
- {voice_mode-4.3.1.dist-info → voice_mode-4.4.0.dist-info}/entry_points.txt +0 -0
@@ -1,4 +1,4 @@
|
|
1
|
-
// File: /tmp/build-via-sdist-
|
1
|
+
// File: /tmp/build-via-sdist-z_iazuah/voice_mode-4.4.0/voice_mode/frontend/app/api/connection-details/route.ts
|
2
2
|
import * as entry from '../../../../../app/api/connection-details/route.js'
|
3
3
|
import type { NextRequest } from 'next/server.js'
|
4
4
|
|
@@ -1,4 +1,4 @@
|
|
1
|
-
// File: /tmp/build-via-sdist-
|
1
|
+
// File: /tmp/build-via-sdist-z_iazuah/voice_mode-4.4.0/voice_mode/frontend/app/layout.tsx
|
2
2
|
import * as entry from '../../../app/layout.js'
|
3
3
|
import type { ResolvingMetadata, ResolvingViewport } from 'next/dist/lib/metadata/types/metadata-interface.js'
|
4
4
|
|
@@ -1,4 +1,4 @@
|
|
1
|
-
// File: /tmp/build-via-sdist-
|
1
|
+
// File: /tmp/build-via-sdist-z_iazuah/voice_mode-4.4.0/voice_mode/frontend/app/page.tsx
|
2
2
|
import * as entry from '../../../app/page.js'
|
3
3
|
import type { ResolvingMetadata, ResolvingViewport } from 'next/dist/lib/metadata/types/metadata-interface.js'
|
4
4
|
|
@@ -1489,9 +1489,9 @@
|
|
1489
1489
|
}
|
1490
1490
|
},
|
1491
1491
|
"node_modules/caniuse-lite": {
|
1492
|
-
"version": "1.0.
|
1493
|
-
"resolved": "https://registry.npmjs.org/caniuse-lite/-/caniuse-lite-1.0.
|
1494
|
-
"integrity": "sha512-
|
1492
|
+
"version": "1.0.30001741",
|
1493
|
+
"resolved": "https://registry.npmjs.org/caniuse-lite/-/caniuse-lite-1.0.30001741.tgz",
|
1494
|
+
"integrity": "sha512-QGUGitqsc8ARjLdgAfxETDhRbJ0REsP6O3I96TAth/mVjh2cYzN2u+3AzPP3aVSm2FehEItaJw1xd+IGBXWeSw==",
|
1495
1495
|
"dev": true,
|
1496
1496
|
"funding": [
|
1497
1497
|
{
|
@@ -1774,9 +1774,9 @@
|
|
1774
1774
|
"license": "MIT"
|
1775
1775
|
},
|
1776
1776
|
"node_modules/electron-to-chromium": {
|
1777
|
-
"version": "1.5.
|
1778
|
-
"resolved": "https://registry.npmjs.org/electron-to-chromium/-/electron-to-chromium-1.5.
|
1779
|
-
"integrity": "sha512-
|
1777
|
+
"version": "1.5.215",
|
1778
|
+
"resolved": "https://registry.npmjs.org/electron-to-chromium/-/electron-to-chromium-1.5.215.tgz",
|
1779
|
+
"integrity": "sha512-TIvGp57UpeNetj/wV/xpFNpWGb0b/ROw372lHPx5Aafx02gjTBtWnEEcaSX3W2dLM3OSdGGyHX/cHl01JQsLaQ==",
|
1780
1780
|
"dev": true,
|
1781
1781
|
"license": "ISC"
|
1782
1782
|
},
|
@@ -3799,9 +3799,9 @@
|
|
3799
3799
|
}
|
3800
3800
|
},
|
3801
3801
|
"node_modules/node-releases": {
|
3802
|
-
"version": "2.0.
|
3803
|
-
"resolved": "https://registry.npmjs.org/node-releases/-/node-releases-2.0.
|
3804
|
-
"integrity": "sha512-
|
3802
|
+
"version": "2.0.20",
|
3803
|
+
"resolved": "https://registry.npmjs.org/node-releases/-/node-releases-2.0.20.tgz",
|
3804
|
+
"integrity": "sha512-7gK6zSXEH6neM212JgfYFXe+GmZQM+fia5SsusuBIUgnPheLFBmIPhtFoAQRj8/7wASYQnbDlHPVwY0BefoFgA==",
|
3805
3805
|
"dev": true,
|
3806
3806
|
"license": "MIT"
|
3807
3807
|
},
|
@@ -0,0 +1,42 @@
|
|
1
|
+
"""Statistics tracking functions used by voice tools.
|
2
|
+
|
3
|
+
This module contains tracking functions that can be imported by tools
|
4
|
+
without causing the statistics tools themselves to be loaded.
|
5
|
+
"""
|
6
|
+
|
7
|
+
from typing import Optional
|
8
|
+
from .statistics import track_conversation
|
9
|
+
from .config import logger
|
10
|
+
|
11
|
+
|
12
|
+
def track_voice_interaction(message: str,
|
13
|
+
response: str,
|
14
|
+
timing_str: Optional[str] = None,
|
15
|
+
transport: Optional[str] = None,
|
16
|
+
voice_provider: Optional[str] = None,
|
17
|
+
voice_name: Optional[str] = None,
|
18
|
+
model: Optional[str] = None,
|
19
|
+
success: bool = True,
|
20
|
+
error_message: Optional[str] = None) -> None:
|
21
|
+
"""
|
22
|
+
Track a voice interaction for statistics.
|
23
|
+
|
24
|
+
This function should be called from conversation tools to record metrics.
|
25
|
+
"""
|
26
|
+
try:
|
27
|
+
track_conversation(
|
28
|
+
message=message,
|
29
|
+
response=response,
|
30
|
+
timing_str=timing_str,
|
31
|
+
transport=transport,
|
32
|
+
voice_provider=voice_provider,
|
33
|
+
voice_name=voice_name,
|
34
|
+
model=model,
|
35
|
+
success=success,
|
36
|
+
error_message=error_message
|
37
|
+
)
|
38
|
+
logger.debug(f"Tracked voice interaction: {len(message)} chars, success={success}")
|
39
|
+
|
40
|
+
except Exception as e:
|
41
|
+
logger.error(f"Error tracking voice interaction: {e}")
|
42
|
+
# Don't raise the error - statistics tracking shouldn't break the main flow
|
voice_mode/tools/__init__.py
CHANGED
@@ -2,23 +2,49 @@
|
|
2
2
|
import os
|
3
3
|
import importlib
|
4
4
|
from pathlib import Path
|
5
|
+
import logging
|
6
|
+
|
7
|
+
logger = logging.getLogger("voice-mode")
|
5
8
|
|
6
9
|
# Get the directory containing this file
|
7
10
|
tools_dir = Path(__file__).parent
|
8
11
|
|
9
|
-
#
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
12
|
+
# Check if we should only load specific tools
|
13
|
+
# This can be set in .voicemode.env, shell environment, or .mcp.json
|
14
|
+
allowed_tools = os.environ.get("VOICEMODE_TOOLS", "").strip()
|
15
|
+
|
16
|
+
if allowed_tools:
|
17
|
+
# Only load specified tools (comma-separated list)
|
18
|
+
tool_list = [t.strip() for t in allowed_tools.split(",")]
|
19
|
+
|
20
|
+
logger.info(f"Selective tool loading enabled. Loading only: {', '.join(tool_list)}")
|
21
|
+
|
22
|
+
for tool_name in tool_list:
|
23
|
+
tool_file = tools_dir / f"{tool_name}.py"
|
24
|
+
if tool_file.exists():
|
25
|
+
logger.debug(f"Loading tool: {tool_name}")
|
26
|
+
importlib.import_module(f".{tool_name}", package=__name__)
|
27
|
+
else:
|
28
|
+
logger.warning(f"Tool module not found: {tool_name}.py")
|
29
|
+
else:
|
30
|
+
# Default behavior: load all tools
|
31
|
+
logger.info("Loading all available tools (set VOICEMODE_TOOLS to limit)")
|
32
|
+
|
33
|
+
# Import all Python files in this directory (except __init__.py)
|
34
|
+
for file in tools_dir.glob("*.py"):
|
35
|
+
if file.name != "__init__.py" and not file.name.startswith("_"):
|
36
|
+
module_name = file.stem
|
37
|
+
logger.debug(f"Loading tool: {module_name}")
|
38
|
+
importlib.import_module(f".{module_name}", package=__name__)
|
14
39
|
|
15
|
-
# Import all service tools from subdirectories
|
16
|
-
services_dir = tools_dir / "services"
|
17
|
-
if services_dir.exists():
|
18
|
-
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
|
23
|
-
|
24
|
-
|
40
|
+
# Import all service tools from subdirectories
|
41
|
+
services_dir = tools_dir / "services"
|
42
|
+
if services_dir.exists():
|
43
|
+
for service_dir in services_dir.iterdir():
|
44
|
+
if service_dir.is_dir() and not service_dir.name.startswith("_"):
|
45
|
+
# Import all Python files in each service directory
|
46
|
+
for file in service_dir.glob("*.py"):
|
47
|
+
if file.name != "__init__.py" and not file.name.startswith("_") and file.name != "helpers.py":
|
48
|
+
module_path = f".services.{service_dir.name}.{file.stem}"
|
49
|
+
logger.debug(f"Loading service tool: {module_path}")
|
50
|
+
importlib.import_module(module_path, package=__name__)
|
voice_mode/tools/converse.py
CHANGED
@@ -75,7 +75,7 @@ from voice_mode.core import (
|
|
75
75
|
play_chime_start,
|
76
76
|
play_chime_end
|
77
77
|
)
|
78
|
-
from voice_mode.
|
78
|
+
from voice_mode.statistics_tracking import track_voice_interaction
|
79
79
|
from voice_mode.utils import (
|
80
80
|
get_event_logger,
|
81
81
|
log_recording_start,
|
voice_mode/tools/statistics.py
CHANGED
@@ -218,36 +218,3 @@ async def voice_statistics_recent(limit: int = 10) -> str:
|
|
218
218
|
logger.error(f"Error showing recent statistics: {e}")
|
219
219
|
return f"Error showing recent statistics: {str(e)}"
|
220
220
|
|
221
|
-
|
222
|
-
# Integration function for conversation tools
|
223
|
-
def track_voice_interaction(message: str,
|
224
|
-
response: str,
|
225
|
-
timing_str: Optional[str] = None,
|
226
|
-
transport: Optional[str] = None,
|
227
|
-
voice_provider: Optional[str] = None,
|
228
|
-
voice_name: Optional[str] = None,
|
229
|
-
model: Optional[str] = None,
|
230
|
-
success: bool = True,
|
231
|
-
error_message: Optional[str] = None) -> None:
|
232
|
-
"""
|
233
|
-
Track a voice interaction for statistics.
|
234
|
-
|
235
|
-
This function should be called from conversation tools to record metrics.
|
236
|
-
"""
|
237
|
-
try:
|
238
|
-
track_conversation(
|
239
|
-
message=message,
|
240
|
-
response=response,
|
241
|
-
timing_str=timing_str,
|
242
|
-
transport=transport,
|
243
|
-
voice_provider=voice_provider,
|
244
|
-
voice_name=voice_name,
|
245
|
-
model=model,
|
246
|
-
success=success,
|
247
|
-
error_message=error_message
|
248
|
-
)
|
249
|
-
logger.debug(f"Tracked voice interaction: {len(message)} chars, success={success}")
|
250
|
-
|
251
|
-
except Exception as e:
|
252
|
-
logger.error(f"Error tracking voice interaction: {e}")
|
253
|
-
# Don't raise the error - statistics tracking shouldn't break the main flow
|
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.4
|
2
2
|
Name: voice-mode
|
3
|
-
Version: 4.
|
3
|
+
Version: 4.4.0
|
4
4
|
Summary: VoiceMode - Voice interaction capabilities for AI assistants (formerly voice-mcp)
|
5
5
|
Project-URL: Homepage, https://github.com/mbailey/voicemode
|
6
6
|
Project-URL: Repository, https://github.com/mbailey/voicemode
|
@@ -33,6 +33,7 @@ Requires-Dist: numpy
|
|
33
33
|
Requires-Dist: openai>=1.0.0
|
34
34
|
Requires-Dist: psutil>=5.9.0
|
35
35
|
Requires-Dist: pydub
|
36
|
+
Requires-Dist: pyyaml>=6.0.0
|
36
37
|
Requires-Dist: scipy
|
37
38
|
Requires-Dist: setuptools
|
38
39
|
Requires-Dist: simpleaudio
|
@@ -77,6 +78,8 @@ Description-Content-Type: text/markdown
|
|
77
78
|
|
78
79
|
# Voice Mode
|
79
80
|
|
81
|
+
mcp-name: com.failmode/voicemode
|
82
|
+
|
80
83
|
> **Install via:** `uvx voice-mode` | `pip install voice-mode` | [getvoicemode.com](https://getvoicemode.com)
|
81
84
|
|
82
85
|
[](https://pepy.tech/project/voice-mode)
|
@@ -112,7 +115,7 @@ Natural voice conversations for AI assistants. Voice Mode brings human-like voic
|
|
112
115
|
|
113
116
|
## Quick Start
|
114
117
|
|
115
|
-
> 📖 **Using a different tool?** See our [
|
118
|
+
> 📖 **Using a different tool?** See our [Getting Started Guide](docs/tutorials/getting-started.md) for setup instructions!
|
116
119
|
|
117
120
|
### Automatic Installation (Recommended)
|
118
121
|
|
@@ -139,7 +142,7 @@ This installer will:
|
|
139
142
|
|
140
143
|
### Manual Installation
|
141
144
|
|
142
|
-
For manual setup steps, see the [
|
145
|
+
For manual setup steps, see the [Getting Started Guide](docs/tutorials/getting-started.md).
|
143
146
|
|
144
147
|
## 🎬 Demo
|
145
148
|
|
@@ -179,16 +182,16 @@ The `converse` function makes voice interactions natural - it automatically wait
|
|
179
182
|
|
180
183
|
Voice Mode works with your favorite AI coding assistants:
|
181
184
|
|
182
|
-
- 🤖 **
|
183
|
-
- 🖥️ **
|
184
|
-
- 🌟 **
|
185
|
-
- ⚡ **
|
186
|
-
- 💻 **
|
187
|
-
- 🦘 **
|
188
|
-
- 🔧 **
|
189
|
-
- ⚡ **
|
190
|
-
- 🏄 **
|
191
|
-
- 🔄 **
|
185
|
+
- 🤖 **Claude Code** - Anthropic's official CLI
|
186
|
+
- 🖥️ **Claude Desktop** - Desktop application
|
187
|
+
- 🌟 **Gemini CLI** - Google's CLI tool
|
188
|
+
- ⚡ **Cursor** - AI-first code editor
|
189
|
+
- 💻 **VS Code** - With MCP preview support
|
190
|
+
- 🦘 **Roo Code** - AI dev team in VS Code
|
191
|
+
- 🔧 **Cline** - Autonomous coding agent
|
192
|
+
- ⚡ **Zed** - High-performance editor
|
193
|
+
- 🏄 **Windsurf** - Agentic IDE by Codeium
|
194
|
+
- 🔄 **Continue** - Open-source AI assistant
|
192
195
|
|
193
196
|
## Installation
|
194
197
|
|
@@ -207,7 +210,7 @@ sudo apt update
|
|
207
210
|
sudo apt install -y python3-dev libasound2-dev libasound2-plugins libportaudio2 portaudio19-dev ffmpeg pulseaudio pulseaudio-utils
|
208
211
|
```
|
209
212
|
|
210
|
-
**Note for WSL2 users**: WSL2 requires additional audio packages (pulseaudio, libasound2-plugins) for microphone access.
|
213
|
+
**Note for WSL2 users**: WSL2 requires additional audio packages (pulseaudio, libasound2-plugins) for microphone access.
|
211
214
|
</details>
|
212
215
|
|
213
216
|
<details>
|
@@ -270,7 +273,7 @@ nix run github:mbailey/voicemode
|
|
270
273
|
|
271
274
|
### Configuration for AI Coding Assistants
|
272
275
|
|
273
|
-
> 📖 **Looking for detailed setup instructions?** Check our comprehensive [
|
276
|
+
> 📖 **Looking for detailed setup instructions?** Check our comprehensive [Getting Started Guide](docs/tutorials/getting-started.md) for step-by-step instructions!
|
274
277
|
|
275
278
|
Below are quick configuration snippets. For full installation and setup instructions, see the integration guides above.
|
276
279
|
|
@@ -548,12 +551,12 @@ nix run github:mbailey/voicemode
|
|
548
551
|
|
549
552
|
**Note:** The `converse` tool is the primary interface for voice interactions, combining speaking and listening in a natural flow.
|
550
553
|
|
551
|
-
**New:** The `install_whisper_cpp` and `install_kokoro_fastapi` tools help you set up free, private, open-source voice services locally.
|
554
|
+
**New:** The `install_whisper_cpp` and `install_kokoro_fastapi` tools help you set up free, private, open-source voice services locally.
|
552
555
|
|
553
556
|
## Configuration
|
554
557
|
|
555
|
-
- 📖 **[
|
556
|
-
- 🔧 **[Configuration Reference](docs/configuration.md)** - All environment variables
|
558
|
+
- 📖 **[Getting Started](docs/tutorials/getting-started.md)** - Step-by-step setup guide
|
559
|
+
- 🔧 **[Configuration Reference](docs/guides/configuration.md)** - All environment variables
|
557
560
|
- 📁 **[Config Examples](config-examples/)** - Ready-to-use configuration files
|
558
561
|
|
559
562
|
### Quick Setup
|
@@ -615,8 +618,8 @@ The audio format is automatically validated against provider capabilities and wi
|
|
615
618
|
|
616
619
|
For privacy-focused or offline usage, Voice Mode supports local speech services:
|
617
620
|
|
618
|
-
- **[Whisper.cpp](docs/whisper.
|
619
|
-
- **[Kokoro](docs/kokoro.md)** - Local text-to-speech with multiple voice options
|
621
|
+
- **[Whisper.cpp](docs/guides/whisper-setup.md)** - Local speech-to-text with OpenAI-compatible API
|
622
|
+
- **[Kokoro](docs/guides/kokoro-setup.md)** - Local text-to-speech with multiple voice options
|
620
623
|
|
621
624
|
These services provide the same API interface as OpenAI, allowing seamless switching between cloud and local processing.
|
622
625
|
|
@@ -662,7 +665,7 @@ The OpenAI SDK handles this automatically - no Voice Mode configuration needed!
|
|
662
665
|
### Common Issues
|
663
666
|
|
664
667
|
- **No microphone access**: Check system permissions for terminal/application
|
665
|
-
- **WSL2 Users**:
|
668
|
+
- **WSL2 Users**: Additional audio packages (pulseaudio, libasound2-plugins) required for microphone access
|
666
669
|
- **UV not found**: Install with `curl -LsSf https://astral.sh/uv/install.sh | sh`
|
667
670
|
- **OpenAI API error**: Verify your `OPENAI_API_KEY` is set correctly
|
668
671
|
- **No audio output**: Check system audio settings and available devices
|
@@ -702,24 +705,17 @@ Audio files are saved to: `~/.voicemode/audio/YYYY/MM/` with timestamps in the f
|
|
702
705
|
📚 **[Read the full documentation at voice-mode.readthedocs.io](https://voice-mode.readthedocs.io)**
|
703
706
|
|
704
707
|
### Getting Started
|
705
|
-
- **[
|
706
|
-
- **[Configuration Guide](docs/configuration.md)** - Complete environment variable reference
|
708
|
+
- **[Getting Started](docs/tutorials/getting-started.md)** - Step-by-step setup for all supported tools
|
709
|
+
- **[Configuration Guide](docs/guides/configuration.md)** - Complete environment variable reference
|
707
710
|
|
708
711
|
### Development
|
709
|
-
- **[
|
710
|
-
- **[Local Development](docs/local-development-uvx.md)** - Development setup guide
|
711
|
-
- **[Audio Formats](docs/audio-format-migration.md)** - Audio format configuration and migration
|
712
|
-
- **[Statistics Dashboard](docs/statistics-dashboard.md)** - Performance monitoring and metrics
|
712
|
+
- **[Development Setup](docs/tutorials/development-setup.md)** - Local development guide
|
713
713
|
|
714
714
|
### Service Guides
|
715
|
-
- **[Whisper.cpp Setup](docs/whisper.
|
716
|
-
- **[Kokoro Setup](docs/kokoro.md)** - Local text-to-speech configuration
|
717
|
-
- **[
|
718
|
-
- **[LiveKit Integration](docs/livekit/README.md)** - Real-time voice communication
|
715
|
+
- **[Whisper.cpp Setup](docs/guides/whisper-setup.md)** - Local speech-to-text configuration
|
716
|
+
- **[Kokoro Setup](docs/guides/kokoro-setup.md)** - Local text-to-speech configuration
|
717
|
+
- **[LiveKit Integration](docs/guides/livekit-setup.md)** - Real-time voice communication
|
719
718
|
|
720
|
-
### Troubleshooting
|
721
|
-
- **[WSL2 Microphone Access](docs/troubleshooting/wsl2-microphone-access.md)** - WSL2 audio setup
|
722
|
-
- **[Migration Guide](docs/migration-guide.md)** - Upgrading from older versions
|
723
719
|
|
724
720
|
## Links
|
725
721
|
|
@@ -737,15 +733,12 @@ Audio files are saved to: `~/.voicemode/audio/YYYY/MM/` with timestamps in the f
|
|
737
733
|
|
738
734
|
## See Also
|
739
735
|
|
740
|
-
- 🚀 [
|
741
|
-
- 🔧 [Configuration Reference](docs/configuration.md) - Environment variables and options
|
742
|
-
- 🎤 [Local Services Setup](docs/kokoro.md) - Run TTS/STT locally for privacy
|
743
|
-
- 🐛 [Troubleshooting](docs/troubleshooting/README.md) - Common issues and solutions
|
736
|
+
- 🚀 [Getting Started](docs/tutorials/getting-started.md) - Setup instructions for all supported tools
|
737
|
+
- 🔧 [Configuration Reference](docs/guides/configuration.md) - Environment variables and options
|
738
|
+
- 🎤 [Local Services Setup](docs/guides/kokoro-setup.md) - Run TTS/STT locally for privacy
|
744
739
|
|
745
740
|
## License
|
746
741
|
|
747
742
|
MIT - A [Failmode](https://failmode.com) Project
|
748
743
|
|
749
744
|
---
|
750
|
-
|
751
|
-
<sub>[Project Statistics](docs/project-stats/README.md)</sub>
|