Meeting Transcription Without a Bot (2026)
Transcribe Zoom, Meet, and Teams calls without “Notetaker Bot has joined the meeting.” Resonant captures audio on your Mac — invisible to everyone else on the call.
TL;DR
Bots like Otter's OtterPilot and Fireflies Notetaker join your meetings as visible participants — making clients, prospects, and candidates uncomfortable. Resonant captures meeting audio at the system level on your Mac and transcribes locally. No bot, no cloud upload, no awkwardness.
The bot problem
“Fireflies Notetaker has joined the meeting.”
That one notification has killed more deals, chilled more conversations, and created more awkward moments than any other feature in the meeting transcription space. When a bot joins your call as a visible participant, everyone else knows three things: the conversation is being recorded, a third party has access, and the host didn't think to mention it.
For internal standups, that's usually fine. For client calls, investor conversations, HR discussions, legal consultations, or any meeting where trust matters — it's a problem.
How Resonant transcribes without a bot
Resonant captures meeting audio using macOS system audio capture. It records what comes through your speakers (the other participants) and your microphone (you) simultaneously. No extra participant joins the call. No integration with Zoom or Meet is needed. If audio plays on your Mac, Resonant can transcribe it.
- System audio capture. Records the audio output of your Mac — the voices of everyone else on the call.
- Microphone capture. Records your voice separately for complete transcripts.
- Local transcription. Parakeet models run on Apple Silicon's Neural Engine in real-time.
- No network. Works fully offline. No audio is ever uploaded.
- Universal compatibility. Works with Zoom, Meet, Teams, Webex, Slack huddles, Discord, FaceTime — any app.
Bot-based vs. botless transcription
| Feature | Resonant (Botless) | Bot-Based Tools |
|---|---|---|
| Bot joins meeting | No — system audio capture | Yes — visible participant |
| Other attendees notified | No | Yes — bot name appears |
| Processing location | Your Mac | Vendor's cloud |
| Works with | Any app that plays audio | Specific integrations only |
| Internet required | No | Yes |
| Audio uploaded | Never | Always |
| Free tier | Unlimited meetings | Limited minutes |
When botless transcription matters most
- Sales calls. Prospects don't want to feel recorded by a third party during discovery.
- Client meetings. Professional services firms need discretion.
- Candidate interviews. A bot joining signals surveillance, not partnership.
- Legal calls. Attorney-client privilege doesn't mix with cloud uploads.
- Executive conversations. Board discussions and strategy calls are not for a vendor's servers.
- Healthcare. Patient discussions carry HIPAA implications when audio leaves the device.
Other bot-free options
- Granola— captures system audio like Resonant, but uploads to cloud for AI processing.
- Otter.ai— OtterPilot is bot-based. No botless option available.
- Fathom— bot joins Zoom calls. No system audio capture.
- Private meeting transcription— our guide on keeping transcripts fully local.
Frequently asked questions
Can I transcribe a meeting without a bot joining?
Yes. Resonant captures audio from your Mac's system output and microphone without joining the call as a participant. Other attendees see nothing.
Why do meeting bots cause problems?
Bots appear as visible participants, signaling to everyone that the conversation is being recorded and sent to a third party. This erodes trust in sales, legal, and executive contexts.
Does Resonant work with Zoom, Meet, and Teams?
Yes. It captures system audio regardless of the app. Zoom, Google Meet, Microsoft Teams, Webex, Slack, Discord, FaceTime — all work.
Is this legal?
Recording laws vary. In one-party consent jurisdictions, you can record calls you're part of. In two-party consent areas, all parties must agree. Resonant removes the technical limitation of needing a bot — legal requirements still apply.
What Resonant offers beyond dictation
Resonant isn't just a faster way to type. It's a voice workspace with capabilities no other dictation tool provides.
MCP server for AI tools
Resonant exposes 11 MCP tools that let any AI agent — Claude, Codex, and more — query your entire voice workspace — meetings, dictations, memos, ambient context, and daily journal. Your AI assistant knows what you said this morning. Learn more
Meeting transcription with speaker labels
Dual-channel recording — your mic and system audio on separate channels. NVIDIA Sortformer diarization identifies who said what. No bot joins the call. No audio leaves your Mac. Learn more
Ambient context capture
Passively records which apps you use, window titles, URLs, and dwell time — all locally. This makes dictation context-aware and gives your AI tools a queryable work timeline. Learn more
Two on-device speech models
NVIDIA Parakeet TDT v3 (0.6B, 25 languages) and Qwen3 ASR (0.6B, 30+ languages), both compiled to CoreML and running on Apple Neural Engine. Under 4% WER on English benchmarks. Learn more
Cloud cleanup with hallucination detection
Optional AI post-processing fixes STT errors and adapts to context (email, message, code). Guardrails detect when the LLM rewrites your meaning instead of cleaning your grammar. Learn more
Start with private Mac dictation
Local speech recognition is free and runs on your Mac. Pro adds cloud cleanup, rewrites, summaries, and sharing when you want the full workflow.