Speech Swift is a collection of Apple Silicon speech tools for recognizing, generating, transforming, and analyzing audio locally with MLX Swift and CoreML. It is for Mac and iOS applications that need on-device speech features such as transcription, voice agents, synthesis, and speaker identification; the catalogue entries provide instructions and skills for using it.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/soniqo/speech-swift/testnpx skills add soniqo/speech-swift --skill testgit clone --depth 1 https://github.com/soniqo/speech-swiftWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/soniqo/speech-swift/test)<a href="https://agentmods.dev/skills/soniqo/speech-swift/test"><img src="https://agentmods.dev/badge/skills/soniqo/speech-swift/test.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00388 |
| Opus 5 | $0.00000 | $0.00194 |
| Sonnet 5 | $0.00000 | $0.00078 |
| Haiku 4.5 | $0.00000 | $0.00039 |
Grade A, and why
test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Test
Run unit and/or E2E tests.
unit(default): Quick tests, no model downloads. CI-safe.e2e: Full pipeline tests with real models, viascripts/test_e2e_isolated.sh— one process per E2E suite. Never use plainswift testfor the full E2E suite: models accumulate in a single xctest process and can exhaust system memory (observed: machine reboot).all: Both unit and E2E (unit phase once, then isolated E2E suites).- Any other argument: passed as
--filterto swift test.
arg="${ARGUMENTS:-unit}"
case "$arg" in
unit) swift test --skip E2E 2>&1 | tail -20 ;;
e2e) swift build --build-tests --disable-sandbox && ./scripts/build_mlx_metallib.sh debug && E2E_SKIP_UNIT=1 scripts/test_e2e_isolated.sh 2>&1 | tail -40 ;;
all) swift build --build-tests --disable-sandbox && ./scripts/build_mlx_metallib.sh debug && scripts/test_e2e_isolated.sh 2>&1 | tail -40 ;;
*) swift test --filter "$arg" 2>&1 | tail -20 ;;
esac
E2E test classes MUST be prefixed with E2E. Unit test classes must NOT contain E2E.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 32 lines · 0 tokens per session scan A c63027b3a243
test is a skill published in the GitHub repository soniqo/speech-swift (1,165 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 388 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
vocello-design
Use this skill to generate well-branded interfaces and assets for Vocello (a local-first, Apple-native macOS voice-generation app — formerly QwenVoice). Contains essential design guidelines, colors, type, fonts, assets, and a Mac-app UI kit for prototyping voice-studio interfaces, marketing surfaces, and slides.
kesha-voice-kit
Local multilingual voice toolkit — speech-to-text (STT), text-to-speech (TTS), speaker diarization, and language detection, over a CLI or an MCP server. Runs entirely offline on Apple Silicon, Linux, and Windows. No API keys, no cloud. NVIDIA Parakeet TDT for STT across 25 European languages, Kokoro-82M + Vosk-TTS for…
release-cli
Cuts a STABLE CLI release (vX.Y.Z-cli marker tag; not for beta or alpha markers, which this lane silently skips while burning the tag) — the 🚀 Release (CLI) lane builds the Linux packages, publishes the marker release, and dispatches npm publish with provenance. Covers version alignment across package.json and…
release-engine
Cuts a kesha-engine release (bare vX.Y.Z tag) per CLAUDE.md rules — pre-flight audits, engine-only version bump, annotated tag carrying the notes, draft validation with authenticated download, publish, then verify. Refuses to auto-run; user must explicitly invoke. Knows the workflow-frozen-at-the-tag trap, the gh-cli…
tts-internals
Use when working on kesha TTS internals — voice routing and which engine serves which voice-id prefix, Kokoro/Vosk ONNX I/O shapes, the CharsiuG2P vs FluidAudio G2P split, SSML handling, multilingual behaviour (es/fr/it/pt on ONNX, hi/ja/zh on darwin-arm64), or the KESHA TTS environment variables. Explains why…
vox-voice-alerts
Speak a short spoken alert to the user via the vox text-to-speech CLI whenever you hand the turn back to them — a task finished (pass or fail, however long it took), you're blocked and need input/a decision/approval, something broke, or you're about to go quiet on a long job. Assume the user is NOT watching the…