Start transcribing by uploading an audio file:
Upload your file
You can also select a sample audio file:
Industrial Revolution
Historical
Physics
Ancient Rome
Summarization
Generate a single abstractive summary of the entire source submitted for transcription.
Topic Detection
Label the topics that are spoken in your audio/video files, following the standardized IAB Taxonomy.
Auto Chapters
Generate a summary over time, providing an automatically generated summary for each chapter of content.
Content Moderation
Detect profanity and other unsafe content in your audio/video files.
Important Phrases
Automatically detect important phrases and words in your source. Your submission may take up to 60 seconds longer to process.
Sentiment Analysis
Detect the sentiment of each sentence of speech spoken in your source, returning the confidence score and exact timestamp.
Entity Detection
Identify a wide range of entities that are spoken in your audio files, such as person and company names, locations, and more.
PII Redaction
Automatically remove Personally Identifiable Information, such as phone numbers and social security numbers.
Speaker Labels
Automatically detect the number of speakers in your audio file, and the text associated with its speaker.
Dual Channel
If your source is a dual channel audio file, the API supports transcribing each channel separately.
Profanity Filtering
By default, the API will return a verbatim transcription of the audio, meaning profanity will be present in the transcript.
Try AssemblyAI's API in seconds.
Access production-ready AI models for speech recognition, speaker detection, audio summarization, and more through our API. Quickly test using your own audio or video file.