Release Notes
Aivis-Project/AivisSpeech
AivisSpeech の新バージョンリリース時に updateInfos のリリースノートドラフトを作成・更新するスキル。「リリースノート」「updateInfos」「アップデート情報」「リリース準備」などのキーワードが出たら使う。updateInfos.draft.json の作成・更新、エンジン側リリースノートとの統合、漏れチェックまでを包括的にサポートする。
Walks through adding a new text-to-speech engine to Voicebox end to end: dependency audit, backend, frontend wiring, PyInstaller bundling and frozen-build testing.
Install Add TTS Engine to Voicebox
$ npx skills add jamiepine/voicebox --skill add-tts-engine -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jamiepine/voicebox add-tts-engine --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/jamiepine/voicebox.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/add-tts-engine .claude/skills/add-tts-engine && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "add-tts-engine" agent skill from https://github.com/jamiepine/voicebox/tree/main/.agents/skills/add-tts-engine into .claude/skills/add-tts-engine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-tts-engine", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/jamiepine/voicebox/tree/main/.agents/skills/add-tts-engineType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add jamiepine/voicebox --skill add-tts-engine -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jamiepine/voicebox add-tts-engine --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jamiepine/voicebox.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/add-tts-engine .agents/skills/add-tts-engine && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "add-tts-engine" agent skill from https://github.com/jamiepine/voicebox/tree/main/.agents/skills/add-tts-engine into .agents/skills/add-tts-engine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-tts-engine", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jamiepine/voicebox --skill add-tts-engine -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jamiepine/voicebox add-tts-engine --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jamiepine/voicebox.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/add-tts-engine .cursor/skills/add-tts-engine && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "add-tts-engine" agent skill from https://github.com/jamiepine/voicebox/tree/main/.agents/skills/add-tts-engine into .cursor/skills/add-tts-engine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-tts-engine", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/jamiepine/voicebox.git --path .agents/skills/add-tts-engine--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add jamiepine/voicebox --skill add-tts-engine -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jamiepine/voicebox add-tts-engine --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jamiepine/voicebox.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/add-tts-engine .gemini/skills/add-tts-engine && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "add-tts-engine" agent skill from https://github.com/jamiepine/voicebox/tree/main/.agents/skills/add-tts-engine into .gemini/skills/add-tts-engine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-tts-engine", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install jamiepine/voicebox add-tts-engineInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add jamiepine/voicebox --skill add-tts-engine -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jamiepine/voicebox.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/add-tts-engine .github/skills/add-tts-engine && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "add-tts-engine" agent skill from https://github.com/jamiepine/voicebox/tree/main/.agents/skills/add-tts-engine into .github/skills/add-tts-engine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-tts-engine", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jamiepine/voicebox --skill add-tts-engine -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jamiepine/voicebox add-tts-engine --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jamiepine/voicebox.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/add-tts-engine .opencode/skills/add-tts-engine && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "add-tts-engine" agent skill from https://github.com/jamiepine/voicebox/tree/main/.agents/skills/add-tts-engine into .opencode/skills/add-tts-engine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-tts-engine", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
add-tts-engine- GitHub stars
- 57k
- Token cost
- ~1.3k tokens
- SKILL.md length
- 561 words
- Files
- 1
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- MIT
At a glance
Walks through adding a new text-to-speech engine to Voicebox end to end: dependency audit, backend, frontend wiring, PyInstaller bundling and frozen-build testing.
- Works in 6 steps: Read the guide → Dependency research (Phase 0) → Implement (Phases 1–4) → …
- Adding support for a new open-source TTS model to Voicebox
- SKILL.md covers Goal, Reference Doc, Workflow and Key Lessons (from v0.2.3), plus 1 more section
- Calls git and just
What it does
The skill follows a phased guide kept in the Voicebox repository at `docs/content/docs/developer/tts-engines.mdx`, which the agent must read in full first. Phase 0 is mandatory: clone the model library into a throwaway directory, audit it and its transitive dependencies, and write down findings on PyPI versus non-PyPI packages, PyInstaller directives, runtime data files, native library paths, needed monkey-patches, sample rate and the model download method. Model loading and generation are tested on CPU in a throwaway virtual environment before any code is written.
Implementation comes next: a new backend module that implements the `TTSBackend` protocol and is registered in the backends package, an updated model regex, frontend changes such as the engine type and per-engine languages, then dependency files, CI and Docker, and finally PyInstaller bundling and a test of the frozen build. The stated aim is that you only have to test the final build locally. The skill notes that skipping Phase 0 once turned a release into three patch releases.
When your agent uses it
- Adding support for a new open-source TTS model to Voicebox
- Auditing a model library's dependencies before packaging it with PyInstaller
- Wiring a new engine into the Voicebox frontend and language lists
Example prompts
- “Add a new text-to-speech engine to Voicebox, starting with the dependency audit.”
- “Audit the dependencies of this model library before we bundle it with PyInstaller.”
- “Wire the new engine into the frontend language constants and engine type.”
Requirements
- A Voicebox checkout that includes its TTS engine guide
- Python with a throwaway virtual environment for testing the model on CPU
- PyInstaller, to build and check the frozen binary
Workflow steps
6 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 8af7efe. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
gitjust
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Add TTS Engine to Voicebox loads about 1.3k tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 561 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from jamiepine/voicebox at commit 8af7efe, republished under its MIT licence (© jamiepine). 561 words, ~1,340 tokens.
Download SKILL.mdSave it as
.claude/skills/add-tts-engine/SKILL.md (or your agent's skills folder).- name
- add-tts-engine
- description
- Use this skill to add a new TTS engine to Voicebox. It walks through dependency research, backend implementation, frontend wiring, PyInstaller bundling, and frozen-build testing. Always start with Phase 0 (dependency audit) before writing any code.
Add TTS Engine
Goal
Integrate a new text-to-speech engine into Voicebox end-to-end: dependency research, backend protocol implementation, frontend UI wiring, PyInstaller bundling, and frozen-build verification. The user should only need to test the final build locally.
Reference Doc
The full phased guide lives at docs/content/docs/developer/tts-engines.mdx. Read this file in its entirety before starting. It contains:
- Phase 0: Dependency research (mandatory before writing code)
- Phase 1: Backend implementation (
TTSBackendprotocol) - Phase 2: Route and service integration (usually zero changes)
- Phase 3: Frontend integration (5 files)
- Phase 4: Dependencies (
requirements.txt, justfile, CI, Docker) - Phase 5: PyInstaller bundling (
build_binary.py+server.py) - Phase 6: Common upstream workarounds
- Implementation checklist (gate between phases)
Workflow
1. Read the guide
# Read the full TTS engines doc
cat docs/content/docs/developer/tts-engines.mdxInternalize all phases, especially Phase 0 and Phase 5. The v0.2.3 release was three patch releases because Phase 0 was skipped.
2. Dependency research (Phase 0)
Clone the model library into a temporary directory and audit it. Do NOT skip this.
mkdir /tmp/engine-research && cd /tmp/engine-research
git clone <model-library-url>Run the grep searches from Phase 0.2 in the guide against the cloned source and its transitive dependencies. Produce a written dependency audit covering:
- PyPI vs non-PyPI packages
- PyInstaller directives needed (
--collect-all,--copy-metadata,--hidden-import) - Runtime data files that must be bundled
- Native library paths that need env var overrides in frozen builds
- Monkey-patches needed (
torch.load, float64, MPS, HF token) - Sample rate
- Model download method (
from_pretrainedvssnapshot_download+from_local)
Test model loading and generation on CPU in the throwaway venv before proceeding.
3. Implement (Phases 1–4)
Follow the guide's phases in order. Key files to modify:
Backend (Phase 1):
- Create
backend/backends/<engine>_backend.py - Register in
backend/backends/__init__.py(ModelConfig + TTS_ENGINES + factory) - Update regex in
backend/models.py
Frontend (Phase 3):
app/src/lib/api/types.ts— engine union typeapp/src/lib/constants/languages.ts— ENGINE_LANGUAGESapp/src/components/Generation/EngineModelSelector.tsx— ENGINE_OPTIONS, ENGINE_DESCRIPTIONSapp/src/lib/hooks/useGenerationForm.ts— Zod schema, model-name mappingapp/src/components/ServerSettings/ModelManagement.tsx— MODEL_DESCRIPTIONS
Dependencies (Phase 4):
backend/requirements.txtjustfile(setup-python, setup-python-release targets).github/workflows/release.ymlDockerfile(if applicable)
4. PyInstaller bundling (Phase 5)
Register the engine in backend/build_binary.py:
--hidden-importfor the backend module and model package--collect-allfor packages usinginspect.getsource, shipping data files, or native libraries--copy-metadatafor packages usingimportlib.metadata
If the engine has native data paths, add os.environ.setdefault() in backend/server.py inside the if getattr(sys, 'frozen', False): block.
Show full SKILL.md (208 more words)Show less
5. Verify in dev mode
just devTest the full chain: model download → load → generate → voice cloning.
6. Use the checklist
Walk through the Implementation Checklist at the bottom of tts-engines.mdx. Every item must be checked before handing the build to the user.
Key Lessons (from v0.2.3)
These are the most common failure modes. Phase 0 research catches all of them:
| Pattern | Symptom in Frozen Build | Fix |
|---|---|---|
@typechecked / inspect.getsource() | "could not get source code" | --collect-all <package> |
| Package ships pretrained model files | FileNotFoundError for .pth.tar, .yaml | --collect-all <package> |
| C library with hardcoded system paths | FileNotFoundError for /usr/share/... | --collect-all + env var in server.py |
importlib.metadata.version() | "No package metadata found" | --copy-metadata <package> |
torch.load without map_location | CUDA device not available on CPU build | Monkey-patch torch.load |
torch.from_numpy on float64 data | dtype mismatch RuntimeError | Cast to .float() |
token=True in HF download calls | Auth failure without stored HF token | Use snapshot_download(token=None) + from_local() |
Notes
- The route and service layers have zero per-engine dispatch points.
main.pyrequires zero changes. - The model config registry in
backends/__init__.pyhandles all dispatch automatically. - Use
get_torch_device()andmodel_load_progress()frombackends/base.py— don't reimplement device detection or progress tracking. - Always test with a clean HuggingFace cache (no pre-downloaded models from dev).
- Do NOT push or create a release. Hand the build to the user for local testing.
© jamiepine, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/add-tts-engine of jamiepine/voicebox.
Open the folder on GitHubat commit 8af7efe
Compare with similar skills
Add TTS Engine to Voicebox next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Add TTS Engine to Voicebox this skilljamiepine/voicebox | 57k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Release NotesAivis-Project/AivisSpeech | 483 | — | ~745 | Automated safety check: Pass | LGPL-3.0 | |
| Abo Docsjeeftor/audiobook-organizer | 189 | — | ~499 | Automated safety check: Pass | MIT | |
| Abo Featurejeeftor/audiobook-organizer | 189 | — | ~446 | Automated safety check: Pass | MIT | |
| No Commentstellahq/opensession | 392 | — | ~310 | Automated safety check: Pass | MIT | |
| Talking Head Videogooseworks-ai/goose-skills | 1.2k | 1 repos | ~8.4k | Automated safety check: Notes | MIT |
Similar skills
Abo Docs
jeeftor/audiobook-organizer
Update Audiobook Organizer documentation, AGENTS.md, changelog entries, and maintainer-facing workflow notes while keeping repo-local skill references consistent.
Abo Feature
jeeftor/audiobook-organizer
Implement focused Audiobook Organizer features across CLI, organizer core, TUI, web UI, or ABS workflows while following issue, branch, tests, docs, and changelog rules.
No Comments
tellahq/opensession
Review a diff for narration, stale comments, and suppressions that clearer code should replace.
Talking Head Video
gooseworks-ai/goose-skills
Creates talking head videos from any source material (docs, changelogs, blog posts, notes, transcripts).
Dep Updates
trufflesecurity/trufflehog
Plan and apply Go dependency updates, including advisory-driven bumps, Trivy/govulncheck validation, and supply-chain review.
More from jamiepine/voicebox
Draft Release Notes
jamiepine/voicebox
Writes or refreshes the Unreleased section of CHANGELOG.md as a themed narrative built from the commits, PRs and diff since the last version tag.
Release Bump
jamiepine/voicebox
Ends a release cycle by moving the Unreleased changelog notes under a dated version heading, bumping version files with bumpversion and tagging the commit.
Pre-Release PR Triage
jamiepine/voicebox
Sorts a backlog of open pull requests into must-merge, candidate, superseded and deferred, writes a triage doc and works the merge loop before a release.
Related
Categories
Questions about Add TTS Engine to Voicebox
What does Add TTS Engine to Voicebox do?
Walks through adding a new text-to-speech engine to Voicebox end to end: dependency audit, backend, frontend wiring, PyInstaller bundling and frozen-build testing. mdx`, which the agent must read in full first. Phase 0 is mandatory: clone the model library into a throwaway directory, audit it and its transitive dependencies, and write down findings on PyPI versus non-PyPI packages, PyInstaller directives, runtime data files, native library paths, needed monkey-patches, sample rate and the model download method.
When should I use Add TTS Engine to Voicebox?
Add TTS Engine to Voicebox fits situations like: adding support for a new open-source TTS model to Voicebox; auditing a model library's dependencies before packaging it with PyInstaller; wiring a new engine into the Voicebox frontend and language lists.
How do I install Add TTS Engine to Voicebox in Claude Code?
Run `npx skills add jamiepine/voicebox --skill add-tts-engine -a claude-code`. Or copy the skill folder (.agents/skills/add-tts-engine in jamiepine/voicebox) into .claude/skills/add-tts-engine in your project. Claude Code loads it when a task matches its description.
How do I install Add TTS Engine to Voicebox in Codex?
Run `npx skills add jamiepine/voicebox --skill add-tts-engine -a codex`. Or copy the skill folder (.agents/skills/add-tts-engine in jamiepine/voicebox) into .agents/skills/add-tts-engine in your project. Codex loads it when a task matches its description.
Can I use Add TTS Engine to Voicebox in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jamiepine/voicebox --skill add-tts-engine -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/add-tts-engine, .gemini/skills/add-tts-engine, .github/skills/add-tts-engine and .opencode/skills/add-tts-engine in your project.
What does Add TTS Engine to Voicebox need to run?
Going by SKILL.md and its folder, Add TTS Engine to Voicebox needs the command-line tools its instructions call (git and just). Our summary lists: A Voicebox checkout that includes its TTS engine guide; Python with a throwaway virtual environment for testing the model on CPU; PyInstaller, to build and check the frozen binary.
Does Add TTS Engine to Voicebox access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Add TTS Engine to Voicebox safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Add TTS Engine to Voicebox use?
Add TTS Engine to Voicebox is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Add TTS Engine to Voicebox use?
About 1.3k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Add TTS Engine to Voicebox?
Skills that share tags, products or a category with Add TTS Engine to Voicebox: Release Notes (Aivis-Project/AivisSpeech, 483 stars), Abo Docs (jeeftor/audiobook-organizer, 189 stars), Abo Feature (jeeftor/audiobook-organizer, 189 stars) and No Comments (tellahq/opensession, 392 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Add TTS Engine to Voicebox?
jamiepine (a GitHub user) maintains it in jamiepine/voicebox, which has 56,524 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 7, 2026.
Source: jamiepine/voicebox on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.