Skip to main content
🎙️

Voice AI

Speech-to-text transcription, meeting notes generation, speaker identification, and voice commands for legal workflows.

Features

🎙️

Speech-to-Text

High-accuracy transcription using OpenAI Whisper and other leading STT engines.

👥

Speaker Diarization

Automatically identify and separate different speakers in recordings.

📋

Meeting Notes

AI-generated meeting summaries, action items, and key decisions.

🗣️

Voice Commands

Voice-controlled legal research and document navigation.

🌍

Multi-Language

Support for 50+ languages with automatic language detection.

⚡

Real-Time Processing

Live transcription for depositions, hearings, and consultations.

Use Cases

Deposition Transcription

Accurate transcription of depositions with speaker identification and timestamps.

Client Meeting Notes

Automatically generate meeting summaries, action items, and follow-up tasks.

Court Hearing Records

Transcribe and organize court hearing recordings for easy reference.

Legal Dictation

Voice-to-text for drafting legal documents, memos, and correspondence.

Upload Audio

🎵

Drag and drop your audio file here, or click to browse

Supports MP3, WAV, M4A, FLAC (max 500MB)

Live Recording

Transcription Options

API Endpoints

POST/api/voiceai/audio/Upload audio
POST/api/voiceai/audio/{id}/transcribe/Transcribe audio
POST/api/voiceai/audio/{id}/generate_notes/Generate meeting notes
GET/api/voiceai/speakers/List speaker profiles
POST/api/voiceai/commands/Process voice command

Transcribe Audio

curl -X POST "http://localhost:8000/api/voiceai/audio/<audio_id>/transcribe/" \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
    "engine": "whisper",
    "language": "en",
    "enable_diarization": true,
    "num_speakers": 2
  }'
← Back to DIY Hub API Docs →