Labyricorn/TalkBox
1
0
Fork 0
generated from Labyricorn/labyricorn-project-template
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

rebrand: rename VoiceBox to TalkBox throughout codebase
CI / frontend-quality (push) Canceled after 0s
Details

Browse Source 
- All 'voicebox'/'Voicebox'/'VOICEBOX' strings replaced with 'talkbox'/'TalkBox'/'TALKBOX'
- Port changed from 17493 to 17494 (avoids conflict with upstream VoiceBox)
- MCP tool namespace: voicebox.* -> talkbox.*
- App bundle ID: sh.voicebox.app -> com.talkbox.app
- Binary names: voicebox-server -> talkbox-server, voicebox-mcp -> talkbox-mcp
- Docker user/group: voicebox -> talkbox
- Database: voicebox.db -> talkbox.db
- Env vars: VOICEBOX_* -> TALKBOX_*
- Asset files renamed: voicebox-logo.* -> talkbox-logo.*, etc.
- External binaries in tauri.conf.json updated to talkbox-server/talkbox-mcp
This commit is contained in:
Labyricorn
2026-08-24 19:45:56 -07:00
parent eaef8dd838
commit b8815e94ea
205 changed files with 1593 additions and 1593 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/mcp_server/README.md
+22 -22
View File
@@ -1,10 +1,10 @@
# Voicebox MCP server
# TalkBox MCP server
Local **Model Context Protocol** server — lets any MCP-aware agent
(Claude Code, Cursor, Windsurf, VS Code MCP extensions, etc.) speak text
in your cloned voices, transcribe audio, and browse captures.
The server runs inside the same `uvicorn` process as the rest of Voicebox
The server runs inside the same `uvicorn` process as the rest of TalkBox
and is mounted at `/mcp` (Streamable HTTP transport).
## Install into your agent
@@ -14,23 +14,23 @@ Preferred — direct HTTP:
```json
{
"mcpServers": {
"voicebox": {
"url": "http://127.0.0.1:17493/mcp",
"headers": { "X-Voicebox-Client-Id": "claude-code" }
"talkbox": {
"url": "http://127.0.0.1:17494/mcp",
"headers": { "X-TalkBox-Client-Id": "claude-code" }
}
}
}
```
Fallback — stdio shim (when the client doesn't speak HTTP MCP). The
`voicebox-mcp` binary ships inside the Voicebox.app bundle:
`talkbox-mcp` binary ships inside the TalkBox.app bundle:
```json
{
"mcpServers": {
"voicebox": {
"command": "/Applications/Voicebox.app/Contents/MacOS/voicebox-mcp",
"env": { "VOICEBOX_CLIENT_ID": "claude-code" }
"talkbox": {
"command": "/Applications/TalkBox.app/Contents/MacOS/talkbox-mcp",
"env": { "TALKBOX_CLIENT_ID": "claude-code" }
}
}
}
@@ -39,25 +39,25 @@ Fallback — stdio shim (when the client doesn't speak HTTP MCP). The
Claude Code one-liner:
```
claude mcp add voicebox \
claude mcp add talkbox \
--transport http \
--url http://127.0.0.1:17493/mcp \
--header "X-Voicebox-Client-Id: claude-code"
--url http://127.0.0.1:17494/mcp \
--header "X-TalkBox-Client-Id: claude-code"
```
## Tools
| Name | Purpose |
|---|---|
| `voicebox.speak` | Speak text in a voice profile. Returns a generation id you can poll. |
| `voicebox.transcribe` | Whisper transcription of a base64 blob or an absolute local path. |
| `voicebox.list_captures` | Recent captures (dictation / recording / file) with transcripts. |
| `voicebox.list_profiles` | Available voice profiles (cloned + preset). |
| `talkbox.speak` | Speak text in a voice profile. Returns a generation id you can poll. |
| `talkbox.transcribe` | Whisper transcription of a base64 blob or an absolute local path. |
| `talkbox.list_captures` | Recent captures (dictation / recording / file) with transcripts. |
| `talkbox.list_profiles` | Available voice profiles (cloned + preset). |
All tools resolve voice profiles in this precedence:
1. Explicit `profile` arg (name or id — case-insensitive)
2. Per-client binding keyed by `X-Voicebox-Client-Id`
2. Per-client binding keyed by `X-TalkBox-Client-Id`
3. `capture_settings.default_playback_voice_id` (global default)
Bindings are managed via `GET|PUT /mcp/bindings` or in the app under
@@ -66,11 +66,11 @@ Settings → MCP.
## Debug with MCP Inspector
```
npx @modelcontextprotocol/inspector http://127.0.0.1:17493/mcp
npx @modelcontextprotocol/inspector http://127.0.0.1:17494/mcp
```
Point it at the URL, hit "List tools," call `voicebox.list_profiles`
first to confirm wiring, then `voicebox.speak` for end-to-end.
Point it at the URL, hit "List tools," call `talkbox.list_profiles`
first to confirm wiring, then `talkbox.speak` for end-to-end.
## Non-MCP REST surface
@@ -78,9 +78,9 @@ first to confirm wiring, then `voicebox.speak` for end-to-end.
don't speak MCP (shell scripts, ACP, A2A):
```
curl -X POST http://127.0.0.1:17493/speak \
curl -X POST http://127.0.0.1:17494/speak \
-H 'Content-Type: application/json' \
-H 'X-Voicebox-Client-Id: claude-code' \
-H 'X-TalkBox-Client-Id: claude-code' \
-d '{"text":"Build complete.","profile":"Morgan"}'
```