Features
AI transcription with 99% accuracy across 54+ languages
Speaker diarization identifying who said what
Multi-language translation into 55+ languages
AI-generated summaries, chapters, and sentiment analysis
Browser-based editor: edit audio by editing text
Automated frame-perfect subtitles and captions
Multi-user permissions and read-only sharing
Centralized billing, audit logs, and full API access for teams
SOC 2 Type 2 and HIPAA compliance
AES-256 encrypted storage with zero-training policy
Automatic timecode sync and verbatim options
PHI detection for medical transcripts
Chain-of-custody audit trails for legal
Conversation modeling: speakers, topics, key statements
Multi-transcript analysis across folders
Multilingual speech transcription (99+ languages)
To-English speech translation
Zero-shot robustness to accents, noise, technical language
Open-source models and inference code
Encoder-decoder Transformer architecture
Trained on 680,000 hours of diverse data
Log-Mel spectrogram input
30-second audio chunk processing
Multiple model sizes (tiny to large)
Whisper.cpp for CPU inference
Fine-tuning via Hugging Face integration
Turbo model on OpenAI API
OpenAI API at $0.006 per minute