GPU-accelerated transcription with speaker diarization, legislative meeting management, and a full editorial workflow — built for government, media, and enterprise.
Core Transcription Engine
High-performance batch transcription powered by OpenAI Whisper and NVIDIA GPUs.
GPU-Accelerated
Leverage NVIDIA GPUs for fast transcription. Process hours of audio in minutes with CUDA-optimized Whisper models.
Speaker Diarization
Automatically identify and label different speakers. Know who said what with speaker-aware transcription.
Batch Processing
Queue and process hundreds of audio and video files. Supports MP3, WAV, MP4, MKV, and more.
On-Premise
Run on your own hardware. Your data never leaves your network. Full control over your transcription pipeline.
Client-Server
Backend server processes transcriptions. Desktop client for easy file management. Multiple users, one server.
Multiple Formats
Export transcripts as TXT, SRT, VTT, or JSON. Timestamps, speaker labels, and confidence scores included.
Legislative & Government Platform
Purpose-built tools for councils, legislatures, and government bodies to manage meetings, record votes, and publish official records.
Meeting Management
Create meetings, manage attendees, build agendas, and track attendance with roll call. Supports regular, special, committee, and hearing types.
Editorial Review
Multi-editor workflow with segment claiming, video-synced editing, and overlap detection. Track review progress across your team.
Full-Text Search
Search across all transcripts with speaker, date, and category filters. Find any word spoken in any meeting instantly.
Motions & Voting
Record motions, capture votes per attendee, and get automatic tallies with pass/fail results. Supports main, amend, table, and postpone motions.
Minutes Export
Generate formal minutes with roll call, agenda, motions, and vote results. Export to DOCX or PDF with one click.
Public Archive
Publish meetings with synced video, transcript, captions, and index points. Give citizens searchable access to public proceedings.
Professional Editor Tools
Advanced editing features for transcriptionists, court reporters, and media professionals.
Waveform Editor
Visual audio waveform with click-to-seek and playhead tracking. See the audio as you edit the transcript.
Configurable Hotkeys
12 default keyboard shortcuts, fully rebindable per editor. Speed up your workflow with custom key bindings.
Foot Pedal Support
WebHID integration for USB transcription foot pedals. Play, pause, rewind, and fast-forward hands-free.
Multi-Track Audio
Per-channel volume, mute, and solo controls. Isolate individual speakers on multi-channel recordings.
Closed Captions
Generate VTT and SRT captions with configurable timing, line limits, and speaker labels.
Index Points & Annotations
Mark topics, flags, bookmarks, and notes on the video timeline. Jump between key moments instantly.
Pricing
One-time purchase. No subscriptions for the software.
Backend Server
$400 CAD
- ✓ GPU-accelerated transcription
- ✓ All Whisper model sizes
- ✓ Speaker diarization
- ✓ Unlimited file processing
- ✓ REST API access
- ✓ 1 server license
Frontend Client
$100 CAD / seat
- ✓ Desktop application
- ✓ Drag-and-drop file management
- ✓ Batch queue management
- ✓ Real-time progress tracking
- ✓ Export to TXT, SRT, VTT, JSON
- ✓ 1 seat license
Bundle
$500 CAD
- ✓ Backend Server license
- ✓ Frontend Client license
- ✓ All features included
- ✓ Legislative platform & archive
- ✓ Save $100 over separate
- ✓ Priority setup support
- ✓ 1 server + 1 seat
System Requirements
Backend Server
- OS: Windows 10/11, Ubuntu 22.04+
- GPU: NVIDIA GPU with 8GB+ VRAM (RTX 3060 or better)
- RAM: 16GB minimum
- Storage: 10GB for models + space for audio files
- CUDA: 11.8 or 12.x
- Python: 3.10+
Frontend Client
- OS: Windows 10/11
- RAM: 4GB minimum
- Storage: 200MB for application
- Network: LAN access to backend server
Ready to get started?
Create an account, purchase a license, and start transcribing in minutes.
Create Account