Voice Dictation for Data Scientists
Document experiments, explain models, ship insights faster
Works with your apps
Ottex works system-wide on macOS. Dictate directly into these apps and more.
And any other app that accepts text input. See all supported apps
Why Ottex works for data scientists
Concrete benefits with real-world impact
3x Faster Than Typing
Speak 150+ words per minute vs 40 wpm typing. Finish tasks in a third of the time.
Custom Dictionary
Add names, technical terms, and jargon. Ottex transcribes them accurately every time.
Precision Typing
Say 'new paragraph', 'open quote', 'em dash', 'ellipsis'. Full formatting control by voice.
Voice Corrections
Say 'scratch that' to delete mistakes, 'actually' to rephrase. Fix errors without stopping your flow or touching the keyboard.
Better Context, Better Results
Speaking naturally gives AI agents more context than typing. Describe your intent, explain edge cases, mention file names—your voice carries nuance that typing shortcuts.
Works with AI Chatbots
Dictate prompts to ChatGPT, Claude, Perplexity—anywhere you type. Better prompts, better answers.
Inline AI Commands
Transform text as you speak: 'Ottex start fix grammar Ottex end'. Edit, improve, translate—all by voice.
Technical Term Accuracy
Cloud AI models excel at technical jargon, code terminology, and specialized vocabulary.
What you can do
Write Research Notes
Dictate research notes, literature summaries, or analysis. Capture your thinking process without losing momentum to typing.
Works with
Prompt ChatGPT & Claude
Dictate prompts to ChatGPT, Claude, Perplexity, or any AI chatbot. Speaking naturally lets you give more context—better context means better results.
Write Documentation
Dictate technical documentation, READMEs, or API docs. Speaking lets you explain context, edge cases, and examples naturally—better docs with less effort.
Works with
Other ways Ottex helps data scientists
Capture Ideas Quickly
Speak ideas the moment they hit you. Use Ottex anywhere to capture thoughts, then refine them later.
Works with
Reply to Work Messages
Reply to Slack messages 3x faster. Dictate casual updates, detailed explanations, or quick acknowledgments without switching context.
Respond to Emails
Dictate email responses with the right tone. Use context awareness to see the full thread, then speak your reply naturally.
Write Meeting Notes
Dictate meeting notes in real-time or right after. Capture action items, decisions, and key points while they're fresh in your mind.
Works with
Write Status Updates
Dictate standup updates, weekly reports, or project status. Speak what happened and what's next—done.
Works with
Frequently asked questions
Does it handle technical ML terminology?+
Yes. Cloud models like Gemini 3 Flash are trained on ML papers, documentation, and code. They handle 'XGBoost,' 'SHAP values,' 'attention mechanism,' 'hyperparameter tuning,' and thousands of other technical terms accurately. For project-specific terms (custom model names, internal tools), add them to your custom dictionary.
Can I dictate into Jupyter notebooks?+
Yes. Ottex works anywhere you can type on macOS, including Jupyter in VS Code, JupyterLab in the browser, and Google Colab. Dictate markdown cells for documentation, code comments, and experiment observations.
How does it help with prompting ChatGPT or Claude?+
AI assistants produce better answers when you provide rich context. But typing a 200-word prompt explaining your dataset, model architecture, and specific question takes 5 minutes. Speaking it takes 45 seconds. More context = better answers, and voice removes the friction.
Will it slow down my machine during model training?+
No. Ottex uses less than 2% CPU because it's native Swift, not Electron. Cloud transcription happens via API. When you're running GPU-intensive training, Ottex won't compete for resources.
Can I use it for explaining models to non-technical stakeholders?+
Absolutely. Work modes let you configure different formatting per app. When you're writing in Notion for stakeholders, your explanations can be clear and jargon-free. When you're documenting in Jupyter for other data scientists, you can use full technical precision.
How much does it cost?+
Free forever with local models (Whisper runs on your Mac). Or bring your own API key for cloud models—most data scientists spend ~$1-3/mo. If you want zero setup, the $9/mo premium tier includes Gemini 3 Flash with 99.1% accuracy.
Start documenting experiments faster
Download free. Use local models immediately, or add your API key for cloud quality. Start dictating in Jupyter notebooks in minutes.
Try for freeNo credit card required.