Bocca
Bocca · Writing · Voice & Language
Bocca is an AI speech-to-text app for macOS that turns your voice into text in any app you can type into. It runs offline, so your audio stays on your device.
About Bocca
What Is Bocca
Bocca is a dictation app that converts speech to text with AI, and it's built for people who type all day and would rather talk. You hold a key, speak, and the words appear where your cursor is. That works in a document, a chat box, an email draft or a prompt field, since Bocca drops text into whatever app is already open.
The pitch is speed. The site claims you write 5x faster than typing, and it points at the people who notice most: engineers drafting prompts, project managers taking notes in meetings, journalists pulling quotes, podcasters turning episodes into scripts. A 10-minute typing job becomes a 2-minute job when you say it out loud instead.
What sets Bocca apart is where the processing happens. It runs completely offline, on your machine. Nothing gets sent to a server, no account login is needed to dictate, and it works with no Wi-Fi. That last part matters if you handle client calls, medical notes or anything you would rather not upload to someone else's cloud.
The catch is the platform. Bocca is macOS only right now, and it asks for macOS 12 or newer. If you live on Windows or an Intel Mac, this app can't help you yet.
Getting Started
- Download Bocca from bocca.dev, then drag the app into your Applications folder
- Open it and grant microphone and accessibility permissions so it can hear you and type into other apps
- Pick your AI model and language, then bind the push-to-talk hotkey to a key you can reach
- Hold the key, speak, and release it to drop the text where your cursor sits
Product Information
A quick look at Bocca's pricing, supported platforms, and performance.
Best for
The users, tasks, and scenarios where this tool fits best.
Users
- Writers and content creators
- Software engineers
- Journalists and interviewers
- Podcasters and course creators
- Privacy-conscious professionals
Tasks
- Push-to-talk dictation
- Long prompt writing
- Audio file transcription
- Meeting notes
- Subtitle and script production
Scenarios
- Writing is going slowly
- A client meeting just ended
- Editing a piece you already recorded
- Working without a connection
- Repetitive typing in tools that don't have dictation
Key features
Push-to-Talk Dictation in Any App
The core of Bocca is a hotkey you hold down while you talk. Release it and your speech shows up as text at the cursor, in whatever window has focus. There's no separate panel to copy from, which is the part most dictation tools get wrong. You keep working in the app you already had open.
Offline Speech-to-Text Engine
Bocca processes audio on your device rather than in a data center. The site is blunt about it: nothing goes to a database, everything stays on your computer. That design means no Wi-Fi requirement and no round trip to a server, so dictation keeps working on a plane or in a place with no signal. For anyone with sensitive audio, it also removes the question of where the file ends up.
Multilingual Support
You can dictate in many languages, and Bocca states it supports talking in any language you work in. That matters for bilingual writers, international teams and anyone switching between an English draft and a message in another tongue mid-session. Language handling sits alongside the model choice rather than being locked to a single region.
Audio File Transcription
Beyond live dictation, Bocca transcribes audio files. You feed it a recording and get text back, which is the path podcasters, journalists and course creators use to turn spoken content into editable material. It turns raw audio into something you can search, quote and publish.
Choose Your AI Model
Bocca lets you pick the AI model doing the transcription rather than locking you to one. If a newer model lands or one handles your accent better, you switch it in the settings. It's a small thing that keeps the app from going stale on you, since the speech recognition field moves fast.
One-Time Purchase
The paid version is a flat $25 buy, not a subscription. You pay once and keep the app. The free tier covers 50 transcriptions a month, enough to test whether dictation fits your routine before you commit. For anyone tired of monthly AI subscriptions, a one-time fee is a real difference.
Pros and cons
Pros
- Runs fully offline, so your audio never leaves your machine and no internet is required
- Works inside any app you can type into, with no switching windows to paste from
- One-time $25 purchase instead of a recurring subscription
- Free tier gives 50 transcriptions a month, so you can test it before paying
- Lets you swap in the AI model you prefer rather than locking one in
Cons
- macOS 12 and above only, so Windows and older Intel Mac users are left out for now
- No API, which rules it out if you want to wire transcription into your own tools
- The 50-transcription free cap runs out fast for daily dictation, so most regular users end up buying
- Accuracy depends on your microphone and the model you pick, so results vary by setup
Frequently asked questions
Bocca is a speech-to-text app for macOS. You hold a hotkey, speak, and it types what you said into whatever app is open. It also transcribes audio files, and it supports dictation in many languages.
Related content
Explore related tools, skills, and articles for Bocca.
Bocca Alternatives
Google EmbeddingGemma 2
Google DeepMind · Writing · Image · CodingGoogle EmbeddingGemma 2 is a 740M-parameter open model that turns text, code, images, audio, and video frames into vectors in one 768-dimension space, running on phones and laptops.
MePersona
MePersona, Inc. · Writing · Productivity · MarketingMePersona is an AI unified inbox for creators. It learns your voice, drafts replies to fan messages from 12 platforms, and sends only what you approve.
Fluence
Yay Software (Yannick Huchard) · Writing · Voice & Language · ProductivityFluence is an Android app that reads PDFs, EPUBs, Word files and web articles aloud, follows each sentence as it speaks, and answers questions about the text on the phone itself.