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 instructions/soniqo/speech-swift/agents-mdgit 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/instructions/soniqo/speech-swift/agents-md)<a href="https://agentmods.dev/instructions/soniqo/speech-swift/agents-md"><img src="https://agentmods.dev/badge/instructions/soniqo/speech-swift/agents-md.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 | $0.05053 | $0.05053 |
| Opus 5 | $0.02527 | $0.02527 |
| Sonnet 5 | $0.01011 | $0.01011 |
| Haiku 4.5 | $0.00505 | $0.00505 |
Grade A, and why
speech-swift AGENTS.md 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
AI speech models for Apple Silicon (MLX Swift). ASR, TTS, speech-to-speech, VAD, diarization, speech enhancement.
Communication Style
- Communicate at the conceptual level first: what changed, why it matters, risk, tests, and recommendation.
- Keep status updates short and understandable. Do not dump command logs, low-level mechanics, or long implementation detail unless directly asked.
- For PRs and fixes, default to this summary shape: what changed, architecture fit, regression risk, tests run or needed, and recommendation.
- If there are bugs, blockers, or regression risks, lead with them clearly and briefly.
- When the user asks a direct question, answer it directly before adding supporting detail.
Workflow
- Always work in a separate git worktree so concurrent agents don't fight over the same working directory. Create one with
git worktree add ../speech-swift-<task> <branch>, do all edits there, push from there. Multiple agents may be running against this repo at the same time — checking out branches in the shared working copy clobbers their state and silently loses WIP files. Delete the worktree (git worktree remove) when the task is done. - Never commit, push, or comment on GitHub without explicit user confirmation. Draft first, ask to confirm, then execute.
- Every README.md change must update all 13 translations (
README_zh.md,README_ja.md,README_ko.md,README_es.md,README_de.md,README_fr.md,README_hi.md,README_pt.md,README_ru.md,README_ar.md,README_th.md,README_tr.md,README_vi.md). No exceptions. - Keep docs and comments scoped to this package. Model docs, code comments, and PR descriptions describe this package's models, APIs, and formats only — never downstream consumer apps or their integration rules.
Running Tests and Benchmarks — Sequential and Memory-Aware
Heavy operations in this repo load multi-gigabyte CoreML/MLX models. Run them strictly one at a time — overlapping them has exhausted memory and rebooted development machines.
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.
- today Changed · +2 lines · +52 tokens per session 98fa682ddd2b
- 5d ago First seen · 357 lines · 5,001 tokens per session scan A cf8fe40d6906
speech-swift AGENTS.md is an instructions file published in the GitHub repository soniqo/speech-swift (1,165 stars, last pushed today), licensed Apache-2.0. It adds 5,053 tokens to every session, about $0.0253 per session on Opus 5. 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 instructions, from other repositories
FluidAudio CLAUDE.md
Claude Code instructions for FluidInference/FluidAudio, covering claude.md, project overview, critical development rules, never use @unchecked sendable and never create dummy models or synthetic data.
FluidAudio copilot-instructions.md
Copilot instructions for FluidInference/FluidAudio, covering fluidaudio - agent development guide, build & test commands, architecture, critical rules and code style (swift-format config).
Vocello AGENTS.md
AGENTS.md instructions for PowerBeef/Vocello, covering agents.md — vocello (qwenvoice), product and authority, start and resume work, hard invariants and domain routing.
Logue CLAUDE.md
Instructions for bitwize-ai/Logue, covering logue — development guidelines, project overview, running the build you just made, where documentation goes and dependencies.
localvoxtral AGENTS.md
AGENTS.md instructions for T0mSIlver/localvoxtral, covering localvoxtral — agent guide, build & test — read this first on a non-mac dev box, proof culture — non-negotiable, test tiers — the short version and ci / shipping.
OpenSuperMLX AGENTS.md
AGENTS.md instructions for axot/OpenSuperMLX, covering agents.md — opensupermlx, agent behavioral guidelines, 1. think before coding, 2. simplicity first and 3. surgical changes.