Freeway
Freeway is a free, privacy-first voice-to-text app for Mac that lets you turn speech into text anywhere you're typing. Just press a hotkey, start talking, and Freeway transcribes your speech in real time. When you release the key, the text is automatically inserted exactly where your cursor is — in any app, any website, any text field. No switching windows, no copy-paste, no interruptions to your flow. Speaking is up to 4× faster than typing, which means ideas move from your mind to the screen at the speed they appear. Whether you're writing emails, messages, notes, documents, or forms, Freeway removes friction and keeps you in motion.
Learn more
ElevenAgents
ElevenLabs Agents is a platform for building, deploying, and scaling intelligent conversational AI agents that can speak, type, and take action across phone, web, and application environments. It enables developers and teams to create real-time agents that interact naturally with users through voice and text, combining speech-to-text, large language models, and text-to-speech into a unified system that functions like a human conversation partner. It allows agents to resolve customer issues, automate workflows, answer questions, and execute tasks based on connected data sources and predefined logic, making interactions both accurate and context-aware. These agents can be customized with knowledge bases, system prompts, and tools that enable them to access external systems, execute custom logic, and perform actions beyond simple responses. They support multimodal capabilities, meaning they can read, speak, and interpret inputs while handling conversational dynamics.
Learn more
FluidVoice
FluidVoice is a free, open source macOS dictation app that pairs local speech recognition with Fluid-1, an on-device AI model for polishing dictation. One hotkey lets users speak into any text field across email, documents, chat, terminals, code editors, and other apps, with text appearing in near real time. Local speech models keep dictation on-device and work offline, while optional AI post-processing can use Fluid Intelligence, OpenAI, Groq, or custom providers. Fluid-1 cleans up rough dictation, fixes formatting, capitalization, dates, names, and numbers, and adapts tone to the active app without changing the speaker’s meaning. Users can create custom prompts for different apps, while Write Mode, Command Mode, and Direct Dictation make it easy to switch contexts. FluidVoice supports more than 40 languages across models including Nemotron Speech 3.5, Parakeet Flash, Parakeet TDT v2 and v3, Cohere Transcribe, Apple Speech, and Whisper.
Learn more
mrmr
mrmr is a voice-first AI agent for Mac. Press one shortcut and talk, and it takes real action across the apps you already work in. This is speech-to-action, not speech-to-text.
Ask it to create a Linear ticket, post the link in a Slack channel, and add a calendar follow-up, and it does all three in one conversation. mrmr chains multi-step workflows, resolves your channels, teammates, and projects automatically, and confirms anything before it sends or changes it.
It connects to Slack, Linear, Google Calendar, Google Tasks, Google Meet, Zoom, Notion, Gmail, Cal.com, Calendly, Attio, and GitHub through real app APIs, plus Apple Reminders. It also searches your Mac files and browser history, runs cited web search, runs your own scripts by voice, and delegates to background sub-agents.
mrmr also handles fast dictation in around 60 languages, but the focus is doing, not typing. A voice-first alternative to Siri, Wispr Flow, and Superwhisper. Currently in private beta.
Learn more
