Resonant
Back to resources
GuideMay 3, 2026
Share

Free Meeting Transcription for Mac (2026)

Unlimited meeting transcription on Mac. No per-minute caps, no per-seat pricing, no subscription. Just download and start recording.

TL;DR

Cloud meeting transcription tools charge because they pay for server compute per meeting. Resonantruns on your Mac's hardware, which you already own. No per-meeting cost = no subscription required. Free, unlimited meeting transcription with no account needed.

Why most “free” meeting transcription isn't

Otter's free tier gives you 300 minutes per month. Hit that limit mid-week and your transcription stops. Fireflies has similar caps. Even “unlimited” free tiers often restrict features — shorter meetings, limited search, no export, or reduced accuracy.

These limits exist because cloud transcription costs money per minute of audio. Every meeting you transcribe costs the vendor GPU compute, bandwidth, and storage. They pass that cost to you via subscriptions and minute caps.

Why Resonant can be genuinely free

Resonant runs speech recognition on your Mac's Neural Engine. There's no server processing your meetings. There's no per-minute compute cost for us. You own the hardware that does the work.

  • No minute limits. Transcribe 10-minute standups or 3-hour workshops. No cap.
  • No meeting limits. Record every meeting, every day. No monthly counter.
  • No subscription. Not a free trial. Not a limited free tier. Just free.
  • No account. Download, install, use. No email, no sign-up, no credit card.
  • No feature gates on basics. Full transcription, search, and recording are free. Pro adds optional cloud features.

Free tier comparison

ToolFree MinutesFree MeetingsSubscriptionAccount
ResonantUnlimitedUnlimitedNone (Pro optional)Not required
Otter.ai300/monthLimited$10–30/user/moRequired
FirefliesLimitedLimited$10–29/user/moRequired
FathomUnlimited*Unlimited*Team features paidRequired
GranolaLimitedLimited$12/monthRequired

* Fathom offers unlimited free transcription for individual use but requires a Zoom integration and account. Team features are paid.

What's free vs. what's Pro

Free (no account needed):

  • Unlimited meeting transcription (on-device)
  • Unlimited live dictation
  • Meeting recording and playback
  • Searchable transcript history
  • Multiple speech models (Parakeet, Whisper, Qwen3)
  • Works offline

Pro (optional upgrade):

  • Cloud LLM transcript cleanup and formatting
  • AI-generated meeting summaries and action items
  • Webhook integrations
  • MCP server for AI agent access
  • Selection transform (rewrite highlighted text)

Also free: live dictation

Resonant isn't just a meeting tool. Press a hotkey and dictate into any app — email, Slack, Notion, docs, code editors. Same on-device processing, same unlimited usage, same $0 price.

Related resources

Frequently asked questions

Is Resonant really free?

Yes. Meeting transcription and dictation are free with no limits. Pro features are optional paid upgrades for power users who want cloud AI summaries and integrations.

Are there minute limits?

No. Transcribe as many meetings as you want, for as long as they last. No monthly cap, no per-meeting limit.

Do I need an account?

No. Download, install, and start using immediately. No sign-up, no email, no credit card. An account is only needed for optional Pro features.

How is this sustainable?

Core transcription runs on your hardware — there's no per-meeting cost for us. Revenue comes from Pro subscribers who want cloud AI features. Free users cost us nothing to serve.

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

Share

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.