Multi-speaker recording with live speaker labels
Your AI checks in by name and drops color-coded notes while you talk — follow-ups, risks, strategy. By the end, the recap and action items are already written.
VoxAI · A copilot for every conversation
Your AI, in the room.
Meetings, calls, negotiations, interviews — it listens live, slips you advice, and speaks up when you talk to it. All on your Mac.
10 meetings free · then US$19.90 once · macOS 14+ · Apple Silicon
AI connected — in the room
01 — Pick a scene
Four scenes, one copilot.
Both sides on separate channels — zero-error labels
Mic is you, system audio is them — labeled in real time, no voiceprint guessing. Hang up, and the named transcript is just… there.
Negotiation, interview, 1-on-1 — tuned advice
A number sounds off; a question deserves a better answer. The fact-check and the next line land in your side panel — mid-conversation, when they still matter.
Talk with your AI by voice
Speak from across the room; it answers out loud. Ship code, ask what was decided last Tuesday — hands free, screen optional.
02 — How it works
Ears. Advice. Voice.
Your AI is smart but senseless: it can't hear the conversation you're in, and it can't speak up when it matters. VoxAI is the missing layer — a native macOS recorder-transcriber with an embedded MCP server.
01
Ears
Live speaker-labeled transcripts stream to your AI while the conversation is still happening.
02
A voice in the room
It pushes advice cards into the session window, silently: fact checks, risks, negotiation strategy.
03
A voice out loud
speak(text) plays through your Mac; the floating dialog turns your speech into its input — a full two-way voice conversation.
03 — What's in the box
Everything a copilot needs.
The meeting copilot
Every line gets a speaker's name — live, while you talk. Your AI checks in by name, follows the growing transcript, and drops color-coded notes in the side panel: follow-ups, action items, risks, strategy. Export Markdown with the notes attached, or hand the whole thing over for a summary.
Call mode: channel is identity
System-audio capture puts the far side on its own channel — mic is you, system audio is them. Real-time labels with zero guessing; no voiceprint model in the loop.
A voice dialog with your AI
A compact chat window: your speech goes straight to the AI; replies come back as bubbles — and out loud, if you want. Light or dark, following your system.
Refinement that outlives the app
After the session, a second pass sharpens everything: mlx-whisper re-transcribes on the Apple GPU, pyannote splits speakers word by word. It runs detached — quit the app, the job still finishes. One-click undo if you preferred the original.
Connect your AI — paste one prompt
Settings hands you a short prompt. Paste it to your AI, and it wires itself up: registers the server, verifies the link, then introduces what the two of you can do together. No Python, no venv — the MCP server ships inside the app.
04 — Local-first
Nothing has to leave your Mac.
Recording, transcription, speaker labels, and the flagship voice all run on-device. In a blind listening test, the local Qwen3 voice held even with the cloud — six voices, no account, nothing uploaded.
- Local voice — Qwen3 1.7B, near-cloud quality, six voices; a one-time ~2.2 GB download, with the system voice filling in until it lands.
- Local ears — live transcription and speaker labels on the Apple GPU; post-meeting refinement by mlx-whisper large-v3-turbo.
- Cloud, strictly opt-in — a free cloud voice, Azure with your own key, cloud refinement: each one is off until you switch it on, behind an explicit upload notice.
No ports, no telemetry, no account — the MCP server is local stdio.
05 — Bring your own AI
Your AI — not another chatbot.
VoxAI does not ship an assistant. It hands senses to the one you already have. Any MCP client gets the archive; an agentic one becomes a copilot. The server writes its full protocol into MCP instructions — a brand-new AI learns the rules the moment it connects.
Archive
- needs
- any MCP client — Claude Desktop, …
- you get
- browse & summarize recordings, speaker-labeled transcripts, TTS
Copilot
- needs
- an agentic client that can loop — Claude Code, …
- you get
- live listening, real-time advice, voice-direct dialog
list_meetings() All recordings with metadata and live status get_meeting(id) Full speaker-labeled transcript get_live_transcript(after_index) Incremental live transcript + speaker map push_advice(text, kind, label?) Advice card into the meeting window start_listening(name) / stop_listening() Copilot check-in / check-out get_dialog_input(after_index) Your speech as chat input post_dialog_reply(text) AI reply bubble in the dialog window speak(text, voice?) / stop_speaking() TTS out loud / interrupt list_voices() / update_voice_config(…) Voice management 06 — Get it
Put a copilot in the room.
One notarized .dmg. Drag it to Applications, connect your AI — and your conversations stop being write-only.
Try it free
Your first 10 meetings, free
The full app, nothing locked. No account, no card.
- Every feature, unlocked
- Only real recordings count (60 s+)
- Notarized .dmg — drag, drop, done
Keep it forever
$39 US$19.90 Early bird
Early-bird price — the regular price is $39.
One payment. Your license key arrives by email, instantly. Offline activation.
- One-time purchase — yours forever
- Two Macs, one license
- Free updates through 1.x
How do I get my license key?
It is emailed to your payment address right after purchase. Paste it into the app — activation is verified locally and unlocks permanently.
What happens when the free trial runs out?
It degrades gently: every recording stays viewable and exportable forever; new recordings cap at 10 minutes; the copilot's live advice pauses until you unlock.
Notarized (Developer ID) · macOS 14+ · Apple Silicon