A collection of small, fast, open-source audio models — speech-to-text, text-to-speech, voice activity detection, language identification — packaged as CLI tools and an OpenClaw skill for LLM agents. One 20MB binary. No Python. No ffmpeg.
$ bun install -g @drakulavich/kesha-voice-kit
Capabilities
Four pipelines, one binary. Pick what you need; the rest stays out of your way.
25 languages via NVIDIA Parakeet TDT. ~15× faster than Whisper on Apple Silicon, ~2.5× on CPU. Auto language detection, optional VAD for long audio, plain text or LLM-friendly TOON output.
Kokoro-82M for English, Vosk-TTS for Russian, plus ~180 macOS system voices. Auto-routes by detected language. SSML preview supported.
SpeechBrain ECAPA-TDNN identifies 107 languages from audio. Apple NLLanguageRecognizer handles text. Both run locally.
Silero VAD v5 trims silence on long, sparse recordings. Auto-enabled past 120 seconds of audio.
A single 20MB binary running FluidAudio (CoreML) on Apple Silicon and ort (ONNX) on everything else. Audio decoded by Symphonia: WAV, MP3, OGG/Opus, FLAC, AAC, M4A. No ffmpeg. No Python. No native Node addons.
Plug straight into your LLM agent as a voice-processing skill. Give Claude (or any agent) ears and a voice in one install.
Performance
Compared against Whisper large-v3-turbo across Russian and English
clips — every engine left to auto-detect language. CoreML on M3 Pro lands at roughly
15× real-time; the ONNX path on x86 still beats Whisper by ~2.5×.
Quick start
Requires Bun ≥ 1.3 on macOS arm64 or Linux x64.
Skip if you already have it.
$ curl -fsSL https://bun.sh/install | bashPulls the engine and base STT models.
$ bun install -g @drakulavich/kesha-voice-kit
$ kesha installPipe-friendly. Stdout = transcript, stderr = errors.
$ kesha audio.ogg
Свободу попугаям! Свободу!# Plain transcript
$ kesha audio.ogg
# Text + language/confidence
$ kesha --format transcript audio.ogg
# Full JSON with lang fields
$ kesha --format json audio.ogg
# Compact, LLM-friendly TOON
$ kesha --toon audio.ogg
# Long / silence-heavy audio (auto past 120s)
$ kesha --vad lecture.m4a
# Warn if detected language differs
$ kesha --lang en interview.wav# Opt-in TTS pack: Kokoro (EN) + Vosk-TTS (RU), ~990MB
$ kesha install --tts
# Speak — voice auto-picks from text language
$ kesha say "Hello, world" > hello.wav
$ kesha say "Привет, мир" > privet.wav
# Use a macOS system voice
$ kesha say --voice Milena "Чао!"import { transcribe, downloadModel } from "@drakulavich/kesha-voice-kit/core";
// One-time install
await downloadModel();
// Transcribe a file
const text = await transcribe("audio.ogg");
// With detection metadata
const result = await transcribe("audio.ogg", { format: "json" });
console.log(result.language, result.confidence);# Multiple files — headers per file, like `head`
$ kesha freedom.ogg tahiti.ogg
=== freedom.ogg ===
Свободу попугаям! Свободу!
=== tahiti.ogg ===
Таити, Таити! Не были мы ни в какой Таити! Нас и тут неплохо кормят.
# Pipe transcripts into your favorite LLM
$ kesha --toon meeting.m4a | llm "Summarize action items"
# Status of installed engine + models
$ kesha statusWhat's inside
Each model is best-in-class for its task and runs through
kesha-engine — Rust, with CoreML on Apple Silicon and ONNX everywhere
else.
Audio decoding via Symphonia — WAV, MP3, OGG/Opus, FLAC, AAC, M4A.
Languages
Need detection only? VoxLingua107 covers 107 languages.
Integrations
Give your LLM agent ears. Voice-processing skill, pre-wired.
Setup guide →
macOS launcher commands: transcribe selected audio, speak the clipboard. From the
raycast/ directory.
Import transcribe() and downloadModel() directly into any
Bun/Node project.
Behind a corporate proxy or fully offline? Point Kesha at your model mirror.
Mirror docs →Open source, MIT licensed, and improving every week. Star the repo or jump straight to the install.