VoxAI
Local macOS conversation recorder with live AI copilot and speaker-labelled transcripts
Mac-based executives, sales reps, recruiters, and researchers who want local, subscription-free recording plus a live AI copilot and MCP-accessible transcript memory for their own agents.
Windows or mobile users, teams that need a shared library with admin controls, or anyone who wants a Zoom/Meet bot that joins calls on their behalf rather than capturing local audio.
VoxAI is a macOS-native conversation intelligence app that pairs on-device audio capture with live AI assistance. It records any conversation the Mac can hear (video calls, phone audio routed through the machine, in-person meetings via mic, or ambient voice chats), transcribes it in real time with automatic speaker diarisation, and streams the growing transcript to an AI copilot that suggests responses, surfaces context, and flags follow-ups while the discussion is still happening. Four dedicated modes tune the pipeline for meetings, calls, in-person conversations, and voice chats so the transcription and prompting behaviour matches the setting.
After a session ends, VoxAI can generate structured notes, action items, decisions, and summaries, and export the whole conversation as Markdown for pasting into Notion, Obsidian, or a CRM. Recordings and transcripts stay in a permanent local archive on the Mac, which appeals to teams that cannot ship meeting audio to a third-party SaaS. The app exposes its transcript store through a local MCP (Model Context Protocol) server, so any MCP-compatible client — Claude Code, Codex, Cursor, or a custom agent — can query past conversations, pull quotes, and drive downstream automations without a cloud round-trip.
Typical users are executives running back-to-back 1:1s, sales and negotiation professionals who want a live devil's-advocate in their ear, recruiters and interviewers capturing structured notes, researchers doing qualitative interviews, and knowledge workers who simply want searchable memory of every call. Pricing is deliberately unusual for the category: a one-time ~$20 purchase (App Store or direct .dmg) instead of a monthly SaaS seat, with a genuinely usable 10-session free trial that requires no account. That makes it an appealing personal-productivity purchase for individuals who are put off by Otter/Fireflies-style subscriptions, though the trade-off is that some heavy features (post-call AI generation, MCP-driven agents) still lean on external AI providers you configure yourself.
VoxAI is the rare meeting-AI product that respects both your wallet and your hard drive: a flat one-time price, everything stored locally, and an MCP endpoint that turns your conversation history into a data source your own agents can query. It's clearly a solo-developer app rather than an enterprise platform, but for Mac power users already living in Claude Code or Cursor, that's exactly the point.
— The AI Tool Bible editorial team
Pros
- ✅ One-time ~$20 purchase with permanent license for two Macs — no recurring subscription
- ✅ Local-first: recordings and transcripts stay on the Mac in a permanent archive
- ✅ Live AI copilot reads the growing transcript and offers real-time suggestions during the call
- ✅ Automatic speaker diarisation with per-speaker labels
- ✅ Four purpose-built modes for meetings, phone calls, in-person chats, and voice sessions
- ✅ Exposes conversations via a local MCP server so Claude Code, Codex, or Cursor can query them
- ✅ Clean Markdown export for pasting into Notion, Obsidian, or a CRM
- ✅ 10 full-feature sessions free with no signup required
Cons
- ⚠️ macOS only — no Windows, Linux, iOS, web, or mobile client
- ⚠️ Requires wiring up an external AI provider for the copilot and post-call generation
- ⚠️ Solo-app model: no team workspace, shared library, or admin console
- ⚠️ Small indie product from a single developer domain — long-term support is not guaranteed
- ⚠️ MCP integration assumes users are already comfortable with Claude Code / Cursor tooling
- ⚠️ No native CRM, calendar, or Zoom bot integrations — capture is whatever the Mac hears
Use cases
Explore related
Compare with similar tools
All in Audio →
ElevenLabs
FeaturedThe gold standard for AI voice cloning and TTS.

Suno
FeaturedText-to-song AI — full vocal tracks from a prompt.

Udio
Suno's main rival for AI-generated full songs.

AssemblyAI
Speech-to-text API with diarisation, summarisation, and topic detection.

Chorus by ZoomInfo
Enterprise conversation intelligence bundled with ZoomInfo's B2B data graph

Whisper
OpenAI's open-source speech-to-text — the de-facto baseline.