Documentation
Voxtral Documentation
Everything you need to know about using Voxtral's audio transcription service. From getting started to advanced features.
Getting Started
Learn the basics of audio transcription with Voxtral
File Upload
Learn how to upload and manage your audio files
Results & Export
Understanding and exporting your transcription results
Language Support
Multi-language transcription capabilities
Export & Integration
Export options and third-party integrations
Account & Billing
Manage your account and subscription
Quick Start Guide
Get started with Voxtral in just 3 simple steps
Upload Audio
Upload your audio file in any supported format
AI Processing
Our AI models transcribe your audio with high accuracy
Get Results
Download your transcription in your preferred format
Key Features
Discover what makes Voxtral the best choice for audio transcription
High-Accuracy Transcription
- 99% accuracy with premium models
- Support for multiple audio formats
- Real-time processing capabilities
- Advanced noise reduction
Multilingual Support
- 50+ languages supported
- Automatic language detection
- Translation between languages
- Regional dialect recognition
AI-Powered Summaries
- Automatic content summarization
- Key point extraction
- Topic identification
- Action item detection
Flexible Export Options
- Multiple format support (TXT, SRT, VTT, JSON)
- Cloud storage integration
- API access for developers
- Batch export capabilities
Tips for Best Results
Follow these guidelines to get the most accurate transcriptions
Audio Quality
- • Use clear, high-quality recordings
- • Minimize background noise
- • Ensure speakers are close to microphone
- • Avoid overlapping speech
File Preparation
- • Use supported formats (MP3, WAV, M4A)
- • Keep files under limits (Demo: 30MB, Premium: 100MB)
- • Split long recordings if needed
- • Name files descriptively
Need More Help?
Our support team is here to assist you with any questions or issues