#speech

HyNote for Mac

Records and transcribes every meeting, audio file, or video straight on your Mac — no bot joining your Zoom call, no audio leaving your machine — then turns the transcript into a structured summary with action items, for free.

Elispeak

Practice speaking English for a real situation — a job interview, a work meeting, moving to a new country — with an AI tutor that gives instant feedback, instead of generic vocabulary drills.

SKI

A voice interface that lets developers talk to AI coding assistants like Claude Code or Cursor instead of typing, with all speech processing done locally on your machine.

Input 0

Hold a keyboard shortcut, speak instead of type, and get back clean text with filler words and stumbles removed automatically — processed entirely on your own Mac, so nothing you say gets sent to a company's server.

Speechingly

Type text and get back a spoken voiceover that actually sounds happy, sad, excited or calm depending on what you pick, in over 120 languages, instead of the flat robotic tone most free text-to-speech tools produce.

Minnarone

A free Python framework for building AI agents that watch and react to live audio and video in real time, like monitoring a livestream or a meeting.

Voicebox

A free, open-source desktop app that clones voices and turns text into natural-sounding speech, running entirely on your own computer with no subscription.

Moonshine

An open-source toolkit for building voice AI that runs fully on-device — no internet connection, no per-request API bill.

KittenTTS

A tiny, open-source text-to-speech library (as small as 25MB) that produces natural-sounding voices on ordinary CPUs — no GPU required.

Shadow

A bot-free AI meeting assistant for Mac that listens to your calls and writes the notes, without ever showing up as a visible participant.

Mispher

A free, open-source Mac app that turns your voice into text and can run simple AI agent tasks, all without touching the internet.

HeyMilo

An AI platform that conducts adaptive voice and video job interviews at scale and scores candidates automatically.

Wispr Flow

An app that turns your spoken words into clean, properly punctuated text in any app you're typing into — like having a fast, tidy typist sitting next to you all day.

Ringly.io

An AI phone agent that answers a Shopify store's inbound support calls 24/7 — handling 'where's my order', returns and product questions so a human team doesn't have to.

Vapi

Developer platform that wires together speech recognition, an AI model and speech generation into a working phone-answering voice agent.

Rime

Text-to-speech API built by linguists for hundreds of natural-sounding voices across 50+ languages, tuned for real conversation, not audiobooks.

Retell AI

No-code-friendly platform for building AI phone agents that handle customer service and sales calls, with drag-and-drop configuration.

Deepgram

Speech recognition and voice-generation API that lets developers add accurate, fast transcription and natural-sounding speech to any app.

Cartesia

Real-time voice AI models built for near-instant, natural-sounding speech — the audio layer behind voice agents that need to feel like a real conversation.

Interfaze

AI model purpose-built for tasks that need a consistent, reliable answer every time — reading documents, classifying content, transcribing speech.