Voice to Text in Zoom
Chat Dictation & Captions (2026)
“Zoom voice to text” means two different things, and the confusion is why most people can't find what they need. One is captions and transcriptionfor the meeting audio. The other is dictating textinto Zoom's chat box. This guide covers both.
Part 1: Zoom live captions & transcription
Zoom can generate real-time captions from meeting audio and provide a full transcript after the meeting ends.
How to enable
- Your Zoom admin must enable Automated captions in the Zoom admin panel (Settings > Meeting > In Meeting (Advanced)).
- During a meeting, click the CC or Live Transcript button in the toolbar.
- Captions appear at the bottom of the meeting window.
- For a full transcript, enable Full transcript in the same toolbar. The transcript is available after the meeting ends.
Limitations
- Admin-gated — if your Zoom admin hasn't enabled it, the button won't appear.
- Cloud-only — audio goes to Zoom's servers for processing.
- Meeting audio only — transcribes what's said in the call. Does not help you type in the chat box.
- Variable accuracy — struggles with multiple speakers, accents, and domain terms.
Part 2: Dictating into Zoom chat
Zoom has no built-in speech-to-text for the chat box. To type a message by voice, you need macOS Dictation or a third-party app.
Option A: macOS Dictation
- Enable Dictation in System Settings > Keyboard > Dictation.
- Make sure Zoom has mic access in System Settings > Privacy & Security > Microphone.
- Click into the Zoom chat input.
- Press fn twice and speak.
Limitation: 30–60 second timeout, manual punctuation, filler words stay.
Option B: Resonant
- Download Resonant and grant permissions.
- Click into the Zoom chat input.
- Press fn and speak.
- Release. Clean, punctuated text appears.
No timeout, automatic punctuation, filler removal, fully offline.
Side-by-side comparison
Here's how the three approaches compare.
| Feature | Zoom Captions | macOS Dictation | Resonant |
|---|---|---|---|
| What it does | Transcribes meeting audio as captions | Types text into Zoom chat | Types text into Zoom chat (or any app) |
| Output | Captions overlay / post-meeting transcript | Text in chat input box | Text in chat input box |
| Works for | Meeting audio only | Any Zoom text field (chat, rename) | Any text field (Zoom + every other app) |
| Session length | Full meeting duration | ~30–60 seconds, then stops | As long as you hold the hotkey |
| Punctuation | Automatic (Zoom’s model) | Say “comma,” “period” out loud | Automatic from speech rhythm |
| Filler removal | No | No | Yes — cleaned automatically |
| Internet required | Yes (Zoom meeting + cloud processing) | Partially (macOS Dictation) | No — local processing |
| Privacy | Audio processed by Zoom’s servers | Short: on-device / Long: Apple’s servers | On-device, always |
| Admin control | Must be enabled by Zoom admin | User-controlled | User-controlled |
| Cost | Included with Zoom (varies by plan) | Free (built into macOS) | Free |
Which one should you use?
For meeting captions and transcripts: Zoom's built-in feature is the starting point. Ask your admin to enable it.
For typing in Zoom chat by voice: macOS Dictation works for quick messages. Resonant handles longer messages with automatic punctuation and cleanup.
For both meeting notes and chat dictation: Use Zoom captions for the meeting audio and Resonant for typing in chat, notes, and follow-up emails.
Frequently asked questions
Does Zoom have voice to text for chat?
No. Zoom's speech-to-text only works for meeting audio (captions). To type in chat by voice, use macOS Dictation or Resonant.
How do I enable Zoom live captions?
Click the CC or Live Transcript button during a meeting. Your Zoom admin may need to enable this in the admin panel first.
Can I get a Zoom meeting transcript?
Yes, if your admin has enabled full transcription. The transcript is available after the meeting ends in the Zoom web portal.
How do I dictate in Zoom chat on Mac?
Click into the chat input and press fn twice (macOS) or hold fn (Resonant).
Does Zoom transcription work offline?
No. Zoom captions require Zoom's servers. Resonant's dictation works fully offline (the Zoom call itself still needs internet).
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.