Overview

The Speech Recognition model enables you to transcribe spoken words into written text and is the foundation of all AssemblyAI products. On top of the core transcription, you can enable other features and models, such as Speaker Diarization, by adding additional parameters to the same transcription request.

Basic transcription workflows

• Get YouTube Video Transcripts with yt-dlp

• Build a UI for Transcription with Gradio and Python

• Detect Low Confidence Words in a Transcript

• Select The EU Region for EU Data Residency

Batch transcription

• Transcribe Multiple Files Simultaneously Using the Python SDK

• Transcribe Multiple Files Simultaneously Using the JavaScript SDK

Hosting audio files

• Transcribe from an S3 Bucket

• Transcribe a Google Drive File

• Transcribe GitHub Files

Speaker Labels

• Identifying speakers in audio recordings

• Iterate over Speaker Labels with Make.com

• Calculate the Talk / Listen Ratio of Speakers

• Plot A Speaker Timeline with Matplotlib

• Generate Custom Speaker Labels with Pyannote

• Use Speaker Diarization with Async Chunking

• Setup A Speaker Identification System using Pinecone & Nvidia TitaNet

Automatic Language Detection

• Separating automatic language detection from transcription

• Use Automatic Language Detection as a Separate Step From Transcription

• Route to Default Language if Language Confidence is Low

• Route to Nano Speech Model if Detected Language Confidence is Low

Subtitles

• Create Custom Length Subtitles

• Create Subtitles with Speaker Labels

• Generate Subtitles for Videos

• Translate an AssemblyAI Subtitle Transcript

Delete Transcripts

• Schedule a DELETE request with AssemblyAI and EasyCron

Error Handling and Audio File Fixes

• Troubleshoot Common Errors

• Implement Retry Server Error Logic

• Implement Retry Upload Error Logic

• Identify Duplicate Dual Channel Files

• Correct Audio Duration Discrepancies with Multi-Tool Validation and Transcoding

• Audio File Downsampling Recommendations and Best Practices

Translation

• Translate an AssemblyAI Subtitle Transcript

• Translate AssemblyAI Transcripts Into Other Languages Using Commercial Models

• Transform Chinese transcripts into Simplified or Traditional Text

Migration Guides

• Migration guide: AWS Transcribe to AssemblyAI

• Migration guide: Deepgram to AssemblyAI

• Migration guide: Google Speech-to-Text to AssemblyAI

• Migration guide: OpenAI to AssemblyAI

Do More with our SDKS

• Do More With Our SDKs