design

speech-swift: AI Speech

Name: speech-swift: AI Speech
Author: soniqo

Get AI speech toolkit for Apple Silicon with ASR, TTS, and more for iOS, macOS.

1,126 stars149 forksSwiftGuide quality 8/10Updated 8/19/2026100% free · open source

What it does

Speech-swift is an AI speech toolkit for Apple Silicon that enables automatic speech recognition, text-to-speech, speech-to-speech, voice activity detection, and diarization in iOS and macOS applications

When to use it

•Building a voice-controlled iOS app that needs to transcribe user speech
•Creating a macOS application that requires text-to-speech functionality
•Developing a speech-to-speech translation app for Apple devices

Ready-to-paste prompt

let recognizer = SpeechRecognizer(); recognizer.transcribe(audioFile: AudioFile(url: URL(string: "https://example.com/audio.mp3")!))

Heads up: The speech-swift toolkit requires Apple Silicon (M1 or later) and Xcode 13 or later to build and run, due to its dependency on MLX and CoreML

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/speech-swift && curl -fsSL https://workflowstacks.com/api/skills/speech-swift/claude-skill -o ~/.claude/skills/speech-swift/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How speech-swift: AI Speech works

Codeflow

Free to inspect

Speech-swift: AI Speech is a very large Swift project (~168k lines across 632 code files, plus 270 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size

Very large codebase

~168k lines · 632 code files · days to read — use, don't read

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Swift

No API keys detected

Swift 98%Python 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
AGENTS.md
The instructions the AI actually follows
3
Examples/DictateDemo/DictateDemo/DictateDemo.entitlements
A worked example — copy this to get going

What's in each folder

docs/Documentation98 files

Examples/Examples you can copy62 files

Sources/Folder590 files

scripts/Helper scripts14 files

Tests/Tests — proof it works298 files

.github/CI / automation (GitHub Actions)5 files

.codex/Tool / agent settings4 files

.claude/Editor / agent settings3 files

READMEHas testsDocumentedCI checksExamples includedApache-2.0 licenseUpdated this month