AssemblyAI is an AI-powered speech-to-text and audio intelligence platform. Transcribe audio and video files with features like speaker diarization, sentiment analysis, entity detection, content moderation, and PII redaction.
Submit an audio or video file URL for transcription. Returns immediately with a queued transcript that will be processed asynchronously. Use Get Transcript to check the status.
12 parameters
Audio URL
Language
Speaker Diarization
Expected Speakers
Sentiment Analysis
Entity Detection
Content Moderation
Key Phrases
PII Redaction
Filter Profanity
Auto Language Detection
Webhook URL
Get Transcript
Retrieve a transcript by its ID. The transcript is ready when the status is "completed".
1 parameters
Transcript
List Transcripts
Retrieve a list of your transcripts, sorted from newest to oldest.
2 parameters
Status
Created On
Delete Transcript
Delete a transcript and its associated data.
1 parameters
Transcript
Get Sentences
Get the transcript split into sentences with timing and speaker information.
1 parameters
Transcript
Get Paragraphs
Get the transcript split into paragraphs with timing information.
1 parameters
Transcript
Get Subtitles
Export the transcript as SRT or VTT subtitles.
3 parameters
Transcript
Format
Characters Per Caption
Search Words in Transcript
Search for specific words or phrases within a transcript.
2 parameters
Transcript
Words
Make HTTP Request
Make an HTTP request to any URL with full control over method, headers, and body.