--- title: The best voice to text apps for a Mac | daily.dev description: This is a comparison of Mac dictation apps and speech-to-text APIs, checked October 30, 2026. Superwhisper's free plan runs local Whisper models for unlimited... canonical: https://daily.dev/posts/the-best-voice-to-text-apps-for-a-mac-uvmwbq1e7 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: The best voice to text apps for a Mac | daily.dev og:description: This is a comparison of Mac dictation apps and speech-to-text APIs, checked October 30, 2026. Superwhisper's free plan runs local Whisper models for unlimited... og:url: https://daily.dev/posts/the-best-voice-to-text-apps-for-a-mac-uvmwbq1e7 og:image: https://api.daily.dev/og/posts/UvMwBq1e7.png og:image:alt: The best voice to text apps for a Mac og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # The best voice to text apps for a Mac **[Flavio Copes](https://daily.dev/sources/flaviocopes)** · 18 min read · 0 upvotes · 0 comments ## Summary This is a comparison of Mac dictation apps and speech-to-text APIs, checked October 30, 2026. Superwhisper's free plan runs local Whisper models for unlimited dictation, while Pro costs $8.49/month, $84.99/year, or $249.99 once. Wispr Flow's free tier has a 2,000-word weekly allowance with a 5,000-word maximum, and Pro is $15/month. MacWhisper's Pro is €64 once. For APIs, OpenAI's gpt-transcribe is the current file model, and whisper-1 leaves the API on February 26, 2027. Groq's whisper-large-v3-turbo costs $0.04/hour, and Deepgram's Nova-3 multilingual pre-recorded rate is $0.0052/minute. The guide also covers dictating prompts into Cursor, Claude Code (hold Space), and Codex. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is the keyboard shortcut to use voice dictation in Cursor's Agents Window? Press and hold Control-M in the Agents Window to record a voice prompt. Cursor records the whole clip, then runs batch speech-to-text to transcribe it. Separately, the general chat input shortcut listed is Command-Shift-Space for Toggle Voice Mode. If Superwhisper or another dictation app also uses that key, assign it a different shortcut to avoid a conflict. _Developers wiring voice input into Cursor can compare shortcut conflicts and workflows on daily.dev._ ### How does Claude Code's /voice dictation feature work and what does it cost? Claude Code's /voice command defaults to hold mode: hold Space to record, release to stop, with /voice tap switching to press-once-to-start and press-again-to-send, and /voice off disabling it. Anthropic transcribes audio on its own servers and requires a Claude.ai account; it does not work over SSH or via API/Bedrock/Foundry access since it needs a local microphone. The docs state this transcription does not consume Claude messages or tokens. _Anyone budgeting AI coding workflows can track feature costs like this one on daily.dev._ ### When will OpenAI's whisper-1 and gpt-4o-transcribe models be removed from the API? OpenAI announced on August 26, 2026 that whisper-1, gpt-4o-transcribe, gpt-4o-mini-transcribe, and gpt-4o-transcribe-diarize will leave the API on February 26, 2027. New work should call gpt-transcribe for files or gpt-live-transcribe for live audio instead. Until the cutoff, the pricing page still lists Whisper at $0.006 a minute. _Teams relying on OpenAI's transcription API can track this kind of deprecation timeline on daily.dev._ ## Similar posts on daily.dev - [The best AI-powered dictation apps of 2025](https://daily.dev/posts/the-best-ai-powered-dictation-apps-of-2025-ydn7bqirh) · TechCrunch · 1 upvotes · 0 comments - [I dismissed this hyped AI app for months, and now I use it for every Claude and ChatGPT prompt](https://daily.dev/posts/i-dismissed-this-hyped-ai-app-for-months-and-now-i-use-it-for-every-claude-and-chatgpt-prompt-ak3oxz93b) · XDA Developers · 0 upvotes · 0 comments - [zachlatta/freeflow: Free and open source alternative to Wispr Flow / Superwhisper / Monologue / etc](https://daily.dev/posts/zachlatta-freeflow-free-and-open-source-alternative-to-wispr-flow-superwhisper-monologue-etc-vqpbtac6m) · Hacker News · 1 upvotes · 0 comments - [MacOS: PrivateTranscriber. Private Alternative to WhisperFlow. Faster Than VoiceBox](https://daily.dev/posts/macos-privatetranscriber-private-alternative-to-whisperflow-faster-than-voicebox-2dijljypx) · Medium · 0 upvotes · 0 comments --- Tags: [#mac](https://daily.dev/tags/mac), [#speech-recognition](https://daily.dev/tags/speech-recognition), [#whisper](https://daily.dev/tags/whisper) [View this post on daily.dev](https://daily.dev/posts/the-best-voice-to-text-apps-for-a-mac-uvmwbq1e7) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"The best voice to text apps for a Mac","url":"https://daily.dev/posts/the-best-voice-to-text-apps-for-a-mac-uvmwbq1e7","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/the-best-voice-to-text-apps-for-a-mac-uvmwbq1e7"},"datePublished":"2026-10-30T10:48:52.521Z","dateModified":"2026-10-30T10:49:24.781Z","description":"This is a comparison of Mac dictation apps and speech-to-text APIs, checked October 30, 2026. Superwhisper's free plan runs local Whisper models for unlimited...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/2e06f7184ed0341db234c7b458ce7530?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/2e06f7184ed0341db234c7b458ce7530?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Flavio Copes","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Flavio Copes","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/1f2dbd275797411bbd37bfdaaf0951a9","url":"https://daily.dev/sources/flaviocopes"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/the-best-voice-to-text-apps-for-a-mac-uvmwbq1e7","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"mac,speech-recognition,whisper","timeRequired":"PT18M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Flavio Copes","item":"https://daily.dev/sources/flaviocopes"},{"@type":"ListItem","position":3,"name":"The best voice to text apps for a Mac"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/the-best-voice-to-text-apps-for-a-mac-uvmwbq1e7#faq","mainEntity":[{"@type":"Question","name":"What is the keyboard shortcut to use voice dictation in Cursor's Agents Window?","acceptedAnswer":{"@type":"Answer","text":"Press and hold Control-M in the Agents Window to record a voice prompt. Cursor records the whole clip, then runs batch speech-to-text to transcribe it. Separately, the general chat input shortcut listed is Command-Shift-Space for Toggle Voice Mode. If Superwhisper or another dictation app also uses that key, assign it a different shortcut to avoid a conflict. Developers wiring voice input into Cursor can compare shortcut conflicts and workflows on daily.dev."}},{"@type":"Question","name":"How does Claude Code's /voice dictation feature work and what does it cost?","acceptedAnswer":{"@type":"Answer","text":"Claude Code's /voice command defaults to hold mode: hold Space to record, release to stop, with /voice tap switching to press-once-to-start and press-again-to-send, and /voice off disabling it. Anthropic transcribes audio on its own servers and requires a Claude.ai account; it does not work over SSH or via API/Bedrock/Foundry access since it needs a local microphone. The docs state this transcription does not consume Claude messages or tokens. Anyone budgeting AI coding workflows can track feature costs like this one on daily.dev."}},{"@type":"Question","name":"When will OpenAI's whisper-1 and gpt-4o-transcribe models be removed from the API?","acceptedAnswer":{"@type":"Answer","text":"OpenAI announced on August 26, 2026 that whisper-1, gpt-4o-transcribe, gpt-4o-mini-transcribe, and gpt-4o-transcribe-diarize will leave the API on February 26, 2027. New work should call gpt-transcribe for files or gpt-live-transcribe for live audio instead. Until the cutoff, the pricing page still lists Whisper at $0.006 a minute. Teams relying on OpenAI's transcription API can track this kind of deprecation timeline on daily.dev."}}]} ```