Skip to main content

Transcription

Transcribe audio files directly in Serenity* Star by uploading your audio file and selecting your preferred transcription model. Transcriptions are generated instantly and can be easily copied.

How It Works​

The Transcription service converts spoken audio into written text using advanced speech recognition models. Upload your audio files, choose a transcription model, and receive accurate text transcriptions in seconds.

Getting Started​

  1. Navigate to AI Services > Transcription in Serenity* Star
  2. Upload your audio file (supported formats: MP3, WAV, WEBM, and more)
  3. Select your preferred transcription model
  4. Click "Execute" to process your audio

Audio Transcription UI

Use Cases​

Transcription is ideal for:

  • Meeting Recordings: Convert meetings and calls into searchable text
  • Podcast Production: Create show notes and transcripts for accessibility
  • Research Interviews: Transcribe interviews for analysis
  • Content Creation: Generate text from video voiceovers
  • Accessibility: Make audio content accessible to all users
  • Legal Documentation: Transcribe depositions and proceedings

API Access​

Transcription services are available via API for:

  • Automated transcription workflows
  • Integration with content management systems

See the API documentation for integration details.

tip

For best results, ensure your audio files are clear and free from excessive background noise.