Hold-to-talk dictation
Hold a key to speak and release it to send the dictation, matching the app's demonstrated voice-to-text workflow.
Blurt
Blurt is a free, open-source Mac dictation app that uses AssemblyAI's Dictation API to place finished spoken text into the field where you are typing. It is intended for people who want to replace some keyboard input with a hold-to-talk voice workflow.
Blurt at a glance
Blurt is a free, open-source Mac dictation app from AssemblyAI. It is designed for entering spoken words into the text field where you are working: hold a key, talk, and the words are placed wherever you are typing.
The app runs on AssemblyAI's Dictation API, which turns a spoken clip into finished, formatted text in one request. The source demonstrates a workflow for replacing some keyboard entry with short voice input, while leaving platform requirements, account setup, privacy behavior, and detailed Blurt controls unspecified.
Features
Text-field output
Blurt inserts the resulting words into the text field where you are already typing, rather than requiring a separate transcription window.
Finished dictation text
The app is powered by AssemblyAI's Dictation API, which returns finished text instead of only a raw, verbatim transcript.
Fast response through the Dictation API
The underlying API is built for short spoken clips and reports typical short-clip responses in under a second, with a p50 of 134 ms; the product pages do not state a separate Blurt latency.
Multilingual and configurable API foundation
The Dictation API supports 19 languages, automatic language detection, native code-switching, key-term prompting, and formatting instructions. The available materials do not establish which options are configurable in Blurt itself.
Open-source Mac app
Blurt is released as free, open-source software, with the download page linking to its GitHub repository and identifying an MIT license.
Use cases
Writing in text fields
Speak a sentence or paragraph while composing an email, document, or message, then continue working with the text in the active field.
Voice-entered prompts
Use short spoken prompts when typing into an AI assistant or other text-based tool is slower than saying the request aloud.
Quick note capture
Capture notes while moving between tasks by dictating directly into the application or document where the note belongs.
Alternative to keyboard entry
Use the API-backed workflow to enter text when keyboard input is inconvenient, such as during hands-busy work; the source does not specify particular supported applications.
Pros and Cons
Pros
- Places dictated text directly into the field where you are typing.
- Uses AssemblyAI's Dictation API for finished, formatted dictation text rather than only a raw transcript.
- Supports a simple hold-to-talk workflow suited to short spoken input.
- Free and open source, with an MIT license and a public GitHub link.
- The underlying API supports 19 languages and native code-switching.
Cons
- Mac-only in the current product description; Windows and Linux support are not stated.
- The available pages do not document supported macOS versions, account or API-key requirements, offline behavior, or the full set of app controls.
- Blurt-specific pricing or usage limits are not provided beyond the description that the app is free.
FAQ
What is Blurt?
Blurt is a Mac dictation app that uses AssemblyAI's Dictation API to place spoken words into the text field where you are typing. The demonstrated workflow is to hold a key, speak, and release it to insert the resulting text.
How do I install Blurt?
Open the downloaded Blurt.dmg file, drag the Blurt icon into the Applications folder, and open the app from Applications. The supplied setup page describes these three installation steps.
Is Blurt free, and does it require an account or API key?
Blurt is described as a free, open-source Mac app. The available product pages do not specify whether an AssemblyAI account, API key, or additional configuration is required for the desktop app.
What platforms does Blurt support?
Blurt is currently presented as Mac-only. The available source does not specify supported macOS versions or provide equivalent Windows or Linux applications.
What kind of text does Blurt produce?
The related Dictation API returns finished, formatted text rather than a verbatim transcript. It supports formatting instructions, key terms, automatic language detection across 19 languages, and native code-switching, but the available Blurt-specific pages do not confirm which of these controls are exposed directly in the app.
Quick Facts
- Category
- Voice dictation / productivity
- Platform
- Mac
- License
- MIT open source
- Price
- Free app
- Input method
- Hold a key and speak
- Output
- Dictated text in the active text field
Alternatives à Blurt
SpeakoFlow
SpeakoFlow is a free, open-source desktop voice-to-text app for Windows, macOS, and Linux. It supports dictation into any app, voice-driven writing with Flow, cleanup, translation, and a screen-aware assistant.
Sanota
Sanota is an app that turns spoken memories, reflections, and interviews into clear written stories. It supports personal storytelling, family history, and shared memories, with guided prompts and subscription pricing.
Carbon Voice
Carbon Voice is an asynchronous voice messaging app for teams and individuals, with transcripts, AI catch-up, and cross-device access. It helps people and agents communicate without needing a live call.
QuickQuill
QuickQuill is a macOS dictation and transcription app that runs locally on the device. It helps users record meetings, transcribe audio, generate summaries, and export notes without using a cloud service.
Zen Whisper
Zen Whisper is a local-first dictation and transcription app for Apple Silicon Macs running macOS 14 or later. It lets users dictate into most Mac text fields, transcribe media or supported public links, and work across 110 spoken language options.
Speech to Text Converter
Speech to Text Converter is a browser-based transcription tool for live dictation and uploaded audio or video files. It offers a free tier for short tasks and a Pro plan for unlimited transcription, AI summaries, translation, speaker identification, and advanced exports.