Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Local TTS — Offline Text-to-Speech · jeremylongshore | DecimalAI

design mediaby jeremylongshore

Local TTS — Offline Text-to-Speech

jeremylongshore/local-tts

Source jeremylongshore/claude-code-plugins-plus-skills ↗License MIT

Generate speech locally from text using VoxCPM2 (2B params, Apache-2.0). 30 languages, voice design (describe a voice), voice cloning (from 3-10s reference). Runs 100% offline on Apple Silicon via Metal (MPS). Zero API calls, zero cost.

SkillScore87Maintained

Automatic

AI Engineer packttsvoiceaudio

Last verified 8/31/2026

What it changes

Passed 19 of 22 test cases with the skill, and 3 of 22 without it.

Without skill13%

With skill87%

Checks it passed that the model alone missed

specifies the output file path using --out
specifies a recommendation of 16 GB system RAM
passes --out /tmp/build_status.wav for output location

and 22 more in the full report

17 fixed3 passed either way3 still failing0 broke

Pass-rate lift: +74 pp
Tokens: +33%
Agent turns: 0%
Response time: -40%

Model gemini-3.6-flashMeasured 8/31/2026v120 of 23 cases passed with skill · 22 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/jeremylongshore-local-tts/SKILL.md https://app.decimal.ai/s/jeremylongshore-local-tts/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add jeremylongshore-local-tts, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/jeremylongshore-local-tts/ and pins it in .decimal/skills.lock

decimalai skills add jeremylongshore-local-tts

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/jeremylongshore-local-tts/SKILL.md https://app.decimal.ai/s/jeremylongshore-local-tts/SKILL.md

Raw file: /s/jeremylongshore-local-tts/SKILL.md ↗ · machine-readable summary at /s/jeremylongshore-local-tts.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 17 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 17

Prompt

What is the complete command line syntax to generate audio for 'The build succeeded in 42 seconds' using the default voice to output path `/tmp/build_status.wav`?

What was checked, without and with the skill
Checked	Without skill	With skill
invokes the generator script with --text setting the input sentence	Missed	Passed
passes --out /tmp/build_status.wav for output location	Missed	Passed

case-18 · gemini-3.6-flash · 8/31/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md183 linessingle file

Local TTS — Offline Text-to-Speech

Generate speech from text using VoxCPM2 locally. 30 languages, voice design, voice cloning. Runs on Apple Silicon via Metal. Apache-2.0, zero cost.

Overview

This skill wraps VoxCPM2 (OpenBMB, Apache-2.0) for local text-to-speech. It supports three modes:

Default voice — just feed text, get natural speech in 30 languages (auto-detected)
Voice Design — describe the voice in a parenthetical prefix, get matching speech
Voice Cloning — provide a 3-10s reference clip, the output mimics the voice

All processing happens on-device. No API keys. No network calls after the initial model download. Output is 48 kHz WAV ready for any use (Telegram voice messages, podcasts, video narration).

Prerequisites

Python 3.10+ (3.12 recommended)
macOS with Apple Silicon preferred (M1/M2/M3/M4). Linux with CUDA also works.
~10 GB disk space for model weights (downloaded once on first use)
~16 GB RAM recommended

The skill expects a Python venv at ~/.local-tts/venv with the voxcpm package installed. If missing, create it:

mkdir -p ~/.local-tts
python3.12 -m venv ~/.local-tts/venv
~/.local-tts/venv/bin/pip install --upgrade pip voxcpm

First generation downloads ~10 GB of model weights to ~/.cache/huggingface/. Subsequent runs load the cache in ~30s.

Instructions

Step 1 — Verify the environment

ls ~/.local-tts/venv/bin/python && echo "venv OK" || echo "Run setup first"

If the venv is missing, guide the user through the setup commands above.

Track record

Benchmark

19 / 22

test cases passed, vs 3 / 22 without

Adoption

Users: 2
Times used: 35

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

jeremylongshore / claude-code-plugins-plus-skills

skills/.curated/local-tts/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/10/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Local TTS — Offline Text-to-Speech

Overview

Prerequisites

Instructions

Step 1 — Verify the environment

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills