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.
Transcribe an Audio File
Specify a Language
Transcribe YouTube Videos
Build a UI for Transcription with Gradio
Detect Low Confidence Words in a Transcript
🆕 How to Use the EU Endpoint
Transcribe a Batch of Files
Transcribe Multiple Files Simultaneously - Python SDK
Transcribe Multiple Files Simultaneously - Node SDK
Transcribe from an AWS S3 Bucket
Transcribe Google Drive Links
Transcribe GitHub Files
Identify Speakers in Audio Recordings
Generate Speaker Labels with Make.com
Calculate Talk/Listen Ratio of Speakers
Create a Speaker Timeline with Speaker Labels
Use Pyannote to Generate Custom Speaker Labels
Speaker Diarization with Async Chunking
Speaker Identification Across Files using Pinecone and Nvidia's TitaNet Model
Use Automatic Language Detection
Automatic Language Detection as Separate Step from Transcription
Route to Default Language if Language Detection Confidence is Low - Node SDK
Route to Default Language if Language Detection Confidence is Low - Python SDK
Route to Nano Speech Model if Language Confidence is Low
Generate Subtitles for Videos
Create Subtitles with Speaker Labels
Create Custom-Length Subtitles
Delete a Transcript
Delete Transcripts After 24 Hours of Creation
Troubleshoot Common Errors When Starting to Use Our API
Automatically Retry Server Errors
Automatically Retry Upload Errors
Identify Duplicate Channels in Stereo Files
Correct Audio Duration Discrepancies with Multi-Tool Validation and Transcoding
Translate an AssemblyAI Transcript
Translate an AssemblyAI Subtitle Transcript
🆕 Near-Realtime Python Speech-to-Text App
🆕 Near-Realtime Node.js Speech-to-Text App
Split Audio File into Shorter Files
AWS Transcribe to AssemblyAI
Deepgram to AssemblyAI
OpenAI to AssemblyAI
Google to AssemblyAI