SuperwhisperUnclaimed profile

AI dictation that turns your voice into polished, app-aware text — hands-free, offline-capable, in 100+ languages.

Task: Composing Music & AudioUse case: Voice to text transcription with ai powered formatting and tone adaptation acrosModels: gpt-5, claude haiku 4.5, llama 4

0.0

based on 0 reviews

Claim this Agent

Are you the vendor?

reviews

Building the picture

Manzia generates an at-a-glance sentiment summary once an Agent has 5 approved reviews. This Agent has 0.

Video tutorials

Official tutorial

Community tutorials

Summarized from 3 community tutorials · July 2026

What you need

Access: Free tier
API key: Not needed — included
Runs on: Desktop app · Mobile app
You’ll need: Mac (Windows/iOS also supported)
Microphone access granted
macOS accessibility permission enabled
Skill level: No code — point and click

Worth knowing: Custom modes with LLM post-processing (formatting, tone, cleanup) require the paid tier -- the free plan only does raw local transcription.

Summarized from 3 community tutorials · July 2026

Highlights

Global hotkey dictation into any appPress a hotkey, speak, and the cleaned-up text is placed on the clipboard and pasted wherever the cursor is -- works across all Mac apps.
Custom 'modes' reformat speech via an LLMEach mode pairs a system prompt with an LLM (e.g. formal-letter, playful, email) so raw speech is rewritten into a specific tone/format automatically.
Local-only voice model for privacyA downloadable on-device voice model transcribes speech without sending audio to the cloud; higher-accuracy cloud/Ultra models are optional.
History with re-processingEvery recording is saved to disk; you can reopen a past recording and re-run it through a different mode if the first output wasn't right.
Bring-your-own API key for LLM modesUsers can plug in their own API key for an LLM provider to power the post-processing modes beyond the built-in options.

Summarized from 3 community tutorials · July 2026