// pro guide
everything you can do with shrp — from free voice typing to pro file transcription, text to speech, and smart ai tools.
// quick start
file upload (paid plans)
- 1. go to your dashboard
- 2. drag and drop your audio/video file
- 3. select language or auto-detect
- 4. wait for processing (1-5 minutes)
- 5. download as txt, docx, srt, vtt, or json
live voice typing (free)
- 1. go to speech to text
- 2. choose your language (55+ supported)
- 3. allow microphone permissions
- 4. start speaking — text appears live
- 5. copy, download, or save to projects
// tools
speech to text
Live voice transcription in your browser using Web Speech API. 55+ languages, auto-punctuation, sentence case. Free forever, no account needed.
file upload transcription
Upload audio/video files (MP3, WAV, MP4, MOV, M4A, AAC) for AI transcription powered by AssemblyAI. Speaker diarization, timestamps, word-level confidence. Starter: 200 min/mo, 100MB. Pro: 1500 min/mo, 500MB.
text to speech
Convert text to natural-sounding audio using Google Cloud neural voices. 40+ languages, adjustable speed. Download as MP3. Free tier: 60K chars lifetime. Starter: 200K/mo. Pro: 500K/mo.
smart voice tools
AI-powered tools — summarize transcripts, translate to other languages, extract key information. Powered by Anthropic Claude.
// pro features in detail
confidence heatmap
Every word in your transcript is color-coded by confidence score. Green = high confidence, yellow = medium, red = low. Instantly see which words to verify — no need to re-listen to the entire file.
speaker diarization
Automatically identifies and labels different speakers in your audio. Perfect for interviews, meetings, and multi-person recordings. Each speaker gets a label (Speaker A, Speaker B, etc.) with their dialogue grouped together.
concurrent transcriptions
Starter: 1 file at a time. Pro: up to 3 files processing simultaneously. Upload a batch and let them all transcribe in parallel.
batch upload
Drag and drop multiple audio files at once. They queue up and process one after another (or concurrently on Pro). Track progress for each file individually.
auto-save to file system
Uses the File System Access API to auto-save your transcript to a real file on your device as you speak. Survives browser crashes. No cloud needed.
project organization
Save transcripts into folders with custom tags. Cloud plan syncs projects across all your devices. Free plan stores up to 25 projects locally in your browser.
// plans
free — $0 — live voice typing, 55+ languages, save 25 local projects, 60K tts chars lifetime
cloud — $3/mo — unlimited cloud project sync, 60 min/mo file transcription
starter — $7/mo — 200 min/mo transcription, 100MB uploads, speaker labels, ai extraction, 200K tts/mo
pro — $15/mo — 1500 min/mo, 500MB uploads, 3 concurrent, 500K tts/mo, priority support
// dashboard features
usage tracking
See your monthly transcription minutes, file uploads, TTS character usage, and credit balance at a glance.
transcription history
Browse all past transcriptions. View with word-level timestamps, speaker labels, and confidence highlighting. Download in any format.
my projects
Organize saved transcripts into folders with tags. Cloud plan and above syncs across devices.
account settings
Manage your subscription, update password, export all data, or delete your account. Billing handled via Stripe customer portal.
// export formats
txt — plain text transcript
docx — formatted word document
srt — subtitle file with timestamps
vtt — web subtitle format
json — full data with segments, speakers, confidence
zip — all formats bundled together
// tips for better accuracy
live voice typing
- - use a quiet environment
- - speak clearly at moderate pace
- - use a good quality microphone
- - select the correct language
- - enable auto-punctuation
file uploads
- - supported: mp3, wav, mp4, mov, m4a, aac
- - max size: starter 100MB, pro 500MB
- - processing: ~1-5 minutes typical
- - better audio quality = better results
- - batch upload multiple files at once