Beginner · 15 min
Audio Transcription Pipeline with OpenAI Whisper
Transcribe audio files at scale with Pixeltable and OpenAI Whisper. Automatic batching, error handling, and incremental processing.
The Challenge
Transcribing large volumes of audio requires complex orchestration: file handling, API rate limiting, error retries, parallel processing, and result storage across separate systems.
The Solution
Pixeltable automates the entire transcription workflow. Add audio files to a table, and Whisper transcription runs as a computed column with built-in batching and error handling.
Implementation Guide
Step-by-step walkthrough with code examples
Audio Table
Create a table for audio files with automatic transcription.
1import pixeltable as pxt2from pixeltable.functions import openai34# Audio processing table5audio = pxt.create_table('app.audio', {6 'audio_file': pxt.Audio,7 'title': pxt.String,8 'speaker': pxt.String,9})1011# Automatic Whisper transcription12audio.add_computed_column(13 transcript=openai.transcriptions(14 audio=audio.audio_file,15 model='whisper-1'16 )17)1819# Insert files: transcription runs automatically20audio.insert([21 {'audio_file': '/recordings/meeting_01.mp3',22 'title': 'Team Standup', 'speaker': 'All'},23])
Key Benefits
Real Applications
Prerequisites
Performance
Learn More
Related Guides
- Video Intelligence Pipeline: Extract, Enrich, and Search Video at Scale
Modality: Video
Computed column: frame_iterator view, then model columns on each frame
Docs - Declarative AI Infrastructure: Define Pipelines, Not Plumbing
Modality: Table
Computed column: Computed columns with incremental cache
Docs - Multimodal AI Apps: Process Any Data Type in One System
Modality: Multimodal
Computed column: One table for media, models, and indexes
Docs
Ready to get started?
Install Pixeltable and start building in minutes. One pip install, no infrastructure to manage.