// how it works

free voice typing in your browser. upload audio files for ai transcription. save and sync your work across devices.

// quick start — 3 steps

1

pick your language

Select from 55+ languages. Hindi, Spanish, Arabic, French, German, and more — all free.

2

click start recording

Allow microphone access once. Speech recognition runs locally in your browser — nothing sent to any server.

3

speak, edit and save

Watch words appear in real-time. Edit, copy, download, or save to My Projects for later.

try it now — free →

// microphone mode (free)

01

open shrp in your browser

No download, no install. Works on Chrome, Edge, Safari, and Firefox. No account required.

02

allow microphone access

Your browser asks for permission once. Click Allow. You can revoke it any time from browser settings.

03

speak naturally

Words appear in real time as you speak. Uses your browser's built-in speech engine — your audio never leaves your device.

04

use ai enhance

After dictating, click AI Enhance to fix grammar, add paragraphs, or both. Powered by Claude Haiku.

05

copy, download or save

Copy to clipboard, download as .txt, or save to My Projects. Auto-saved to browser — nothing lost if you close the tab.

// file upload mode (starter+)

01

upload your audio or video file

Drag and drop or click to browse. Supports MP3, WAV, M4A, MP4, MOV, OGG, FLAC, WebM — up to 500MB on Pro.

02

assemblyai processes it

Your file is sent securely to AssemblyAI — one of the most accurate transcription engines available, delivering ~98% accuracy on clean audio.

03

speaker diarization

If your audio has multiple speakers, SHRP automatically detects and labels each one. Speaker labels appear in the transcript and all exports.

04

read the confidence heatmap

Words are colour-coded by AI confidence. Yellow = double-check, Red = verify before publishing. Instantly see where to review.

05

use ai extraction

One click to extract meeting minutes, action items, key names and dates, or a full summary from your transcript.

06

export in any format

Download as TXT, SRT, VTT, DOCX, or JSON. SRT and VTT include timestamps for video captioning. JSON includes full word-level data.

// text to speech

01

go to text to speech

Navigate to /text-to-speech. No login required for basic use.

02

type or paste your text

Enter any text — articles, scripts, emails, study notes, anything.

03

choose your voice and language

Select from 20+ languages and multiple Google Neural2 voices. All users get Neural2 — the highest quality tier.

04

generate and download

Click Generate. Audio plays instantly in your browser. Download as MP3 for offline use.

try text to speech →

// smart voice tools

dictate naturally and auto-format into a structured document. no editing needed.

📋

meeting notes

Structured notes with key points and decisions.

action items

Extract tasks and next steps from any discussion.

📧

email draft

Turn a voice memo into a professional email.

📝

summary

Condense long transcripts into a short summary.

🏥

soap notes

Medical SOAP note format for clinical documentation.

🔤

rewrite

Clean up and reformat raw dictation.

try smart voice tools →

// my projects — save and sync

every transcription can be saved to My Projects — organised, tagged, and searchable.

no account

Saved in browser only. 25 projects max.

free account

25 cloud projects. Access from any device.

free signup

cloud+ ($3/mo)

Unlimited cloud projects. Auto-sync.

from $3/mo

// supported file formats

formatqualitynotes
mp3goodmost common, widely compatible
wavbestuncompressed, highest accuracy
m4agooddefault on iOS and macOS
mp4goodvideo with audio track
movgoodApple QuickTime video
ogggoodopen source format
flacbestlossless compression
webmgoodbrowser recordings

// browser support

desktop

Google ChromeBest accuracy, all features
Microsoft EdgeFull support
SafariSupported, some limitations
FirefoxLimited Web Speech API

mobile and tablet

Chrome for AndroidFull support
Safari for iOSFull support
Install as PWAWorks offline, all devices

// privacy

microphone mode is 100% localYour voice is processed by your browser — nothing sent to any server, ever

no cookies, no session recordingCookieless Vercel Analytics only. No GA, no Facebook Pixel, no Clarity

no login requiredStart immediately, completely anonymous

uploaded files deleted within 30 daysFile transcription uploads are automatically purged from storage

transcripts are yoursWe never use your content for advertising or AI training

read the full privacy policy →

// tips for best results

1.

use a quiet environmentBackground noise reduces accuracy significantly

2.

speak clearly and naturallyDon't rush — natural pace gives better results

3.

use chrome or edgeThey have the best Web Speech API implementations

4.

enable auto punctuationSaves you from manual editing after dictating

5.

use ai enhance after dictatingClean up grammar and formatting in one click

6.

select the right languageMatching the language improves accuracy considerably

ready to start?

free forever for voice typing. upgrade when you need file transcription or cloud sync.

start free voice typing →see plans from $3/mo →