Documentation
Everything you need to get the most out of Soria Voice Note.
Getting Started
Set up your account and start recording in minutes.
- Create an account with email or Google/Apple sign-in
- Choose your preferred language and theme
- Set up folders to organize your notes
- Make your first recording or upload an audio file
Recording
Record audio directly in the app with live transcription.
- Tap the microphone to start recording
- Choose Solo or Meeting mode before recording for more accurate results
- Turn on Live Transcription to see words appear in real time
- Pause and resume without losing progress
- Automatic speaker detection for multi-person conversations
Transcription
Accurate AI-powered speech-to-text conversion.
- 82 input languages with auto-detection
- Speaker diarization — know who said what
- Edit and correct transcriptions after processing
- Timestamps synced with audio playback
AI Features
Intelligent AI-powered analysis.
- Automatic summary generation in multiple styles
- Tone conversion — formal, casual, bullet points
- Action item and todo extraction with dates
- Sentiment analysis for single and multi-speaker recordings
Folders & Organization
Keep your notes structured and easy to find.
- Create nested folders by project or topic
- Move documents between folders from the menu
- Search across all notes with full-text search
- Filter by date, folder, or speaker
Team Collaboration
Work together with shared workspaces and permissions.
- Create a team and invite members via email
- Share documents to team folders
- Collaborative recording sessions with live transcription
- Role-based access: Owner, Admin, Member
Export & Sharing
Take your content anywhere in the format you need.
- Export in PDF, Markdown, or Audio format
- PDF includes speaker labels and formatted layout
- Markdown for integration with other tools
- Copy transcript, summary, or todos to clipboard
- Share documents directly to team workspaces
Language Support
Soria works with voices from around the world.
- 82 input languages for voice recording
- 30+ output languages for transcription and summaries
- App interface in multiple languages, with more being added
- Set input and output languages separately for best results
File Upload
Process existing audio files through our AI pipeline.
- Supported formats: MP3, M4A, WAV, WebM, OGG, FLAC
- Maximum file size depends on your plan
- Drag-and-drop or browse to select files
- Batch processing for multiple files
AI Chat
Have conversations with AI about your recorded content.
- Ask questions about any recorded document
- Get insights and analysis from your meetings
- Cross-reference information across recordings
- Custom prompts for specialized analysis