Transcribe audio files with Whisper
Convert speech to text locally using OpenAI's open-source Whisper model—no API key needed.
Updated Open in Colab
Transcribe speech and identify speakers with WhisperX
Transcribe speech with WhisperX in Python, identify speakers, and search the transcript with word-level timestamps.
Audio · Recipe · Updated
How it works
You have recorded conversations and need a transcript with word timestamps and speaker labels. You want to find relevant speech and return to the point in the recording where it was said.
You use WhisperX to transcribe speech locally and align each word to a time and a speaker. pixeltable.functions.whisperx.transcribe() does that as a computed column on audio, or on audio taken from a video with extract_audio().
What it covers
- Preview WhisperX transcription and save it for each clip
- Extract word timestamps and speaker labels
- Search speech segments with an embedding index
What it uses
- Install
- terminalpip install pixeltable 'whisperx>=3.8' sentence-transformers
- Environment variables it names
HF_TOKEN- Pixeltable calls
whisperx.transcribe()json.list_iterator()pxt.create_table()pxt.create_view()insert()add_computed_column()add_embedding_index()similarity()
A look at the code
whisperx-transcription.mdx
segments.add_embedding_index('text',string_embed=sentence_transformer.using(model_id='all-MiniLM-L6-v2'),)
One block of the recipe, copied as it is. The rest is on the docs page.
More in Audio
Browse all 103Transcribing and Indexing Audio and Video in Pixeltable
In this tutorial, we'll build an end-to-end workflow for creating and indexing audio transcriptions of video data.
Updated Open in ColabSummarize podcasts and audio
Transcribe audio files and generate summaries automatically using Whisper and LLMs.
Updated Open in ColabGenerate Podcast Chapters
Generate YouTube-style chapter timestamps for podcast episodes. WhisperX detects where speech starts and stops, then an LLM summarizes each segment into a chapter title.
Updated Open in Colab