Superwhisper

Superwhisper turns speech into formatted text across applications, including apps where text can be entered. Its Super Mode reads the screen and adapts dictation to the app, such as shaping email as a message or making coding prompts technical. It supports more than 100 languages, with automatic detection and translation between languages. On-device speech models work offline and keep audio on the device. For cloud models, audio and text pass through the Superwhisper proxy to the provider; the product says they are not retained for training. The service names Slack, Cursor, and Notion, offers coding plugins for Claude Code, OpenCode, Codex, and Pi, and includes a CLI for transcript search and export, recording statistics, and starting a local MCP server. The free tier includes voice-to-text, meeting recording and transcription, and email support. Pro features can be tried for 3,000 words, after which free-tier features remain available. Pro is $8.49 per month or $84.99 per year and adds audio and video file transcription and priority support.

Superwhisper combines cross-app dictation with context-aware formatting, offline processing, and tools for transcripts and AI workflows. Free features remain available after the 3,000-word Pro trial; Pro costs $8.49 per month or $84.99 per year.

Superwhisper suits people who want to dictate into apps, work across supported languages, or use local speech processing offline. Its CLI and coding plugins may also suit users incorporating transcripts into AI workflows.

Superwhisper is a voice dictation and transcription app that shapes speech for the app where you use it. It best suits people who dictate across writing and coding tools and want local processing as an option. Its context-aware formatting is more capable than plain dictation, but file transcription and expanded model access require Pro.

Overview

Superwhisper’s defining feature is Super Mode, which reads the screen and adapts dictated text to the task—for example, turning speech into an email-style message or a technical coding prompt. That can reduce editing for people who move between different kinds of writing. If you want speech rendered literally, the context layer may add little.

It works in apps that accept text, with Slack, Cursor, and Notion among the named integrations. The free plan also includes meeting recording and transcription, while Pro adds transcription of audio and video files. Speaker identification and labeling are supported.

Key features

• Context-aware formatting: Super Mode uses what is on screen to shape dictation for the current app. It is a practical fit for switching between conversational messages and technical prompts, but depends on wanting formatted text rather than a verbatim transcript.
• Languages and translation: More than 100 languages are supported, with automatic detection and translation between languages. Pro includes translation to English; that distinction matters if English translation is central to your routine.
• Local and cloud processing: On-device speech models process audio locally, work offline, and do not send audio off the device. Cloud models route audio and text through the Superwhisper proxy to the provider; the company says they are not retained for training. Users who need offline operation can rely on local models, while cloud workflows involve a provider.
• Transcripts and AI workflows: Pro can transcribe audio and video files. The CLI can search and export transcripts, report recording statistics, and start a local MCP server for AI workflows. Coding plugins are offered for Claude Code, OpenCode, Codex, and Pi.
• Security and compliance: The Trust Center lists SOC 2, HIPAA, GDPR, and PIPEDA compliance, relevant to organizations weighing speech tools for work.

Pricing

The free plan costs nothing and includes voice-to-text in any app, meeting recording and transcription, more than 100 languages, unlimited Whisper models, and email support. Pro features can be tried for 3,000 words; afterward, free-tier features remain available. This is a useful way to assess paid capabilities, but the trial is word-limited rather than an ongoing allowance of Pro features.

Pro costs $8.49 a month, billed monthly, or $84.99 a year, billed yearly. Both plans include cloud and local AI models, custom API keys, audio and video transcription, and priority support. Pro is the fit for regular file transcription or priority help; the free plan retains core dictation and meeting transcription but gives up those Pro features. Pro also includes translation to English and own AI API keys.

Pro Lifetime is shown at $249.99 a month with one payment and a one-time license for Pro features. Enterprise has custom pricing and includes SOC 2 Type II certification, centralized billing and authentication, model access control, enterprise-hosted models, and volume discounts. Its administrative controls make it the organization-oriented option.

Platforms

Superwhisper is available for Android, iOS, macOS, and Windows. The download page lists macOS 13.3 or later, Windows 10 or later, and iOS 18 or later, and links to Google Play for Android.

Who it's for

Choose Superwhisper if you dictate in several kinds of apps and value text that is adapted to the active task, local offline speech processing, or a path from recording to AI-assisted transcript workflows. It is less compelling if you only need straightforward voice-to-text or need audio and video file transcription without paying for Pro.

Pros and cons

• Pro: Screen-aware formatting can tailor dictated text to the app, reducing cleanup for people who switch between messages and technical prompts.
• Pro: Local models work offline and keep audio on-device, while cloud models provide another processing route.
• Pro: The free plan retains voice-to-text in any app, meeting transcription, and more than 100 languages after the Pro trial.
• Con: Pro features are limited to a 3,000-word trial on the free tier; file transcription and priority support require a paid plan.
• Con: Cloud-model audio and text pass through a proxy to the provider, so cloud processing is not the on-device option.

Alternatives

Wispr Flow is another freemium choice across Android, iOS, macOS, and Windows; its free plan sets weekly word limits on desktop and mobile and limits Weekly Notetaker use.

Dictanote is worth considering if you want a free plan with up to 50 notes in one notebook, 60 minutes of dictation a day, and support for more than 50 languages; it also runs on Linux and the web.

Google Voice Access is a free Android alternative.

WakaScribe offers a free Local plan with unlimited words and no time limit, making it an option for people who prioritize an uncapped local tier.

Braina is another freemium option across Android, iOS, macOS, and Windows; its Braina Pro plan is $99 a year for use on one Windows PC.

Aqua Voice starts with 1,000 free words and offers Pro for $8 a month, billed annually, for readers comparing a word-limited starter plan with paid dictation.

Wizkey is available on Windows and Android and offers unlimited local dictation with a supported model on its free plan, alongside monthly limits for cloud dictation and Copilot.

Philips SpeechLive is a paid alternative with a free trial, starting with a Basic plan at $12.90 a month, billed annually, excl. tax.

For broader comparisons, see Dictation software, Speech Recognition Software, and Transcription Software.

Verdict

Superwhisper is best for people who want cross-app dictation that adapts to the task, with offline local models and useful transcript and AI-workflow tools. Its clearest reason to choose it is the combination of context formatting and local processing; look elsewhere if you need an ongoing free allowance of Pro features or want file transcription without a subscription.