You just finished an hour-long meeting. Or a lecture. Or a brainstorming session you recorded on your phone. Now you need it in text.

The cloud options are fine until you think about what's in the audio. Client names. Revenue numbers. Medical details. Legal strategy. HR conversations. The moment you upload that audio to Otter.ai or Google's speech API, it exists on someone else's infrastructure, subject to their retention policies and their security posture.

There's a better option: transcribe it on your Mac, locally, with Whisper-class accuracy, and never send the audio anywhere.

How does local speech-to-text work on a Mac?

An on-device model converts microphone or file audio into text using the Mac's Neural Engine. ToolPiper's default is Parakeet TDT v2, an English model that processes speech much faster than real time without touching the network; Parakeet TDT v3 adds other languages.

Speech-to-text models have gotten remarkably good in the last two years. OpenAI's Whisper model was a watershed - it proved that a single model could handle multiple languages, accents, background noise, and domain-specific vocabulary at near-human accuracy.

The models that run locally on your Mac today are derived from that same research lineage. Parakeet, the STT model that ships with ModelPiper's ToolPiper engine, runs on Apple's Neural Engine via CoreML. The Neural Engine is dedicated silicon designed specifically for machine learning workloads - it processes audio faster than real time, meaning a 30-minute recording transcribes in well under 30 minutes.

The quality is real. These aren't the speech-to-text engines of five years ago that turned every third word into gibberish. Modern local models handle crosstalk, accents, filler words, and technical vocabulary with accuracy that's genuinely comparable to cloud services.

How do you transcribe audio in ModelPiper?

Attach or record audio in chat and ask for the transcript, or hold the push-to-talk key to dictate. ToolPiper's FluidAudio STT runs on the Neural Engine and streams the transcript back as text.

Open ModelPiper chat. Hit record, or attach an audio file and ask for the transcript. The audio runs through ToolPiper's FluidAudio STT engine on the Neural Engine, and text streams back in real time.

That's the basic workflow. But the real power is what comes next: the same chat can hand the transcript to a language model for a summary, a translation, or the action items.

What People Actually Use This For

Meeting transcription. Record the meeting (with consent), drop the audio into ModelPiper, get a full transcript. No subscription to a cloud transcription service. No uploading confidential business discussions to a third party.

Voice memos to text. Talk into your Mac's microphone when you're thinking through a problem. Get text back. Faster than typing, more complete than the notes you'd take by hand.

Lecture notes. Record a talk, a webinar, a conference session. Get searchable text. Highlight the parts that matter.

Interview transcription. Journalists, researchers, and recruiters all deal with hours of recorded conversation. Local transcription means source confidentiality stays intact.

Accessibility. For anyone who processes audio better as text, or who needs to make audio content searchable and accessible.

What languages does local transcription support?

The default model, Parakeet TDT v2, is English-only. For other languages, select Parakeet TDT v3 in ToolPiper's settings: it covers 25 European languages, including English, Spanish, French, German, Portuguese, Italian and Dutch, plus Japanese.

The default is English-only on purpose: most installs transcribe English, and v2 is the model ToolPiper sets up first. Switching to v3 is one setting, and it matters for multilingual meetings, international conference talks, or any recording that isn't exclusively English.

Try It

Download ModelPiper, install ToolPiper, and hold the dictation key to transcribe your own speech into any app, free. To transcribe a recording, open chat, attach the audio file and ask for the transcript; that chat transcription tool is part of Pro ($10/month).

Everything runs on your Mac's Neural Engine. The audio never leaves your machine.

This is part of a series on local-first AI workflows on macOS. Next up: Text to Speech - have your Mac read anything aloud with AI-quality voice synthesis.