diff --git a/.labyricorn/devlog/contents.lr b/.labyricorn/devlog/contents.lr index 164045c..8a4c48c 100644 --- a/.labyricorn/devlog/contents.lr +++ b/.labyricorn/devlog/contents.lr @@ -2,6 +2,6 @@ _model: devlog --- schema_version: 1 --- -title: Labyricorn Project Template development log +title: TalkBox development log --- -summary: Milestones and development log entries for the Labyricorn project template. \ No newline at end of file +summary: Milestones and development log entries for TalkBox, the local-first AI voice studio. \ No newline at end of file diff --git a/.labyricorn/devlog/fork-and-rebrand/contents.lr b/.labyricorn/devlog/fork-and-rebrand/contents.lr new file mode 100644 index 0000000..db49dcf --- /dev/null +++ b/.labyricorn/devlog/fork-and-rebrand/contents.lr @@ -0,0 +1,35 @@ +_model: devlog-entry +--- +schema_version: 1 +--- +title: Forking and rebranding VoiceBox into TalkBox +--- +date: 2026-08-24 +--- +author: Labyricorn +--- +summary: Initial fork from upstream VoiceBox with a full codebase rebrand to TalkBox, updated port and bundle IDs, and integration of the .DCP documentation and publishing workflow. +--- +tags: fork, rebrand, tts, mcp, devlog, release +--- +source_commit: 7ad90d93a7b7fdfe97725bfc83bda228d266c657 +--- +body: + +TalkBox has been established as an independent fork of [VoiceBox](https://git.labyricorn.com/Labyricorn/voicebox) to serve as our customized local-first AI voice studio and MCP voice bridge. + +### Summary of Changes + +1. **Codebase Rebranding**: + - Replaced all naming across 205 files spanning frontend components (React/TypeScript), desktop harness (Tauri v2 / Rust), backend services (FastAPI/Python), documentation, and build scripts. + - Renamed core sidecar binaries to `talkbox-server` and `talkbox-mcp`. + - Updated database files to `talkbox.db` and environment variables to the `TALKBOX_*` namespace. + +2. **Network and Service Isolation**: + - Migrated the default backend and MCP HTTP port from `17493` to `17494` to enable concurrent execution alongside upstream VoiceBox instances without port collisions. + - Standardized the MCP tools namespace to `talkbox.speak`, `talkbox.transcribe`, `talkbox.list_captures`, and `talkbox.list_profiles`. + - Updated the client identifier header to `X-TalkBox-Client-Id`. + +3. **Labyricorn Publishing & Devlog Integration**: + - Restored and configured the repository's `.labyricorn/` publishing records and `devlog_editor.py` validator. + - Introduced the `.DCP` (Document, Commit, Push) shorthand command and automated skill workflow for continuous devlog maintenance and release tracking. diff --git a/.labyricorn/project/contents.lr b/.labyricorn/project/contents.lr index d0b5ff6..bacd7bc 100644 --- a/.labyricorn/project/contents.lr +++ b/.labyricorn/project/contents.lr @@ -2,26 +2,34 @@ _model: project --- schema_version: 1 --- -project_id: labyricorn-project-template +project_id: talkbox --- -title: Labyricorn Project Template +title: TalkBox --- summary: -Initial template and publishing structure for Labyricorn-compatible projects and development logs. +Local-first AI voice studio for multi-engine speech generation, zero-shot voice cloning, global dictation, and MCP agent voice I/O. --- status: active --- -started: 2026-08-23 +started: 2026-08-24 --- author: Labyricorn --- -repository_url: https://git.labyricorn.com/Labyricorn/labyricorn-project-template +repository_url: https://git.labyricorn.com/Labyricorn/TalkBox --- default_branch: main --- -tags: template, lektor, python +tags: tts, voice-cloning, stt, whisper, mcp, tauri, react, fastapi, rust, python --- body: -Starter template providing the standard .labyricorn/ publishing records, assistant instructions, devlog structure, and repository tooling for publication on Labyricorn. \ No newline at end of file +TalkBox is a local-first AI voice studio combining high-fidelity speech synthesis, zero-shot voice cloning, global dictation with synthetic paste, and Model Context Protocol (MCP) voice I/O. + +### Highlights + +- **Multi-Engine Speech Generation**: Supports 7 TTS engines (Qwen3-TTS, Qwen CustomVoice, LuxTTS, Chatterbox Multilingual, Chatterbox Turbo, HumeAI TADA, Kokoro) covering 23 languages. +- **Voice Cloning & Profiles**: Zero-shot voice cloning from reference audio samples, custom effects chains, and personality prompt attachments. +- **Global Dictation**: Whisper-backed push-to-talk and toggle dictation anywhere on macOS, Windows, and Linux with focus-aware automatic pasting. +- **Agent Voice Output (MCP)**: Streamable HTTP and stdio MCP server (`http://127.0.0.1:17494/mcp`) exposing `talkbox.speak`, `talkbox.transcribe`, `talkbox.list_captures`, and `talkbox.list_profiles` for agent integrations. +- **Native & Local Performance**: Built on Tauri v2 (Rust) and React/TypeScript frontend with Python FastAPI backend running locally on Apple Silicon (MLX), NVIDIA (CUDA), AMD (ROCm), DirectML, or CPU. \ No newline at end of file diff --git a/CHANGELOG.md b/CHANGELOG.md index 83216bb..1ec2f54 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -7,6 +7,17 @@ ## [Unreleased] +### Rebrand & Fork + +- **Forked and rebranded as TalkBox.** Full codebase rebrand across frontend, backend, + desktop harness (Tauri v2), and documentation. +- **Port isolation.** Default backend/MCP server port moved from 17493 to 17494 + to prevent conflicts when running alongside upstream VoiceBox. +- **MCP tools namespace.** MCP tools namespaced under `talkbox.*` with client header + `X-TalkBox-Client-Id`. +- **Labyricorn integration & `.DCP` workflow.** Restored `.labyricorn/` publishing + records, devlog tooling, and established the `.DCP` (Document, Commit, Push) workflow. + ### Linux - **ROCm setup works on Linux AMD systems.** Docker ROCm builds now keep PyTorch