Features AssemblyAI
Core Transcription
Translates audio and video files, and live speech into text. It helps users get written records of meetings, interviews, podcasts and more.
Audio Intelligence
Interprets your audio for business and personal workflows. Allows users to analyze and extract meaningful insights from their audio data.
LeMUR
A framework for building apps based on spoken data. It enables developers to create AI applications leveraging voice data.
Conformer-2
State-of-the-art AI model for automatic speech recognition trained on extensive data. It offers high accuracy on a wide variety of English audio.
Speaker labels
Labels the speaker in a transcription. Useful in meetings, interviews, and any multi-speaker audio to ensure accurate attribution.
Profanity filtering
Filters out inappropriate language from transcriptions. It ensures the resulting text is professional and suitable for all audiences.
Custom vocabulary
Allows model customization to understand industry-specific vocabulary. Increases transcription accuracy for specialized fields.
Word-level timestamps
Provides timestamps for each spoken word. Provides an easy way to locate specific parts of the audio for reference or editing.