Go to example tasks
Transcribe audio into chunks for RAG
Created by
Matvey
Transcript split into overlapping chunks with timestamps — drop them straight into a vector database.
Audio Transcriber — Podcasts, Calls & Meetings to Textlergassy/audio-transcriber
File
Minutes
Language
Quality
+5 fieldsTextNumberBooleanListObject
Input
🎙️ Audio or video URLs:https://raw.githubusercontent.com/lergassy/apify-actor-assets/main/audio-samples/test-10min.ogg
🎚️ Recognition quality:accurate
Split into RAG chunks:true
Chunk size (characters):1200
Chunk overlap (seconds):2
Output fields
File
Minutes
Language
Quality
Words
Segments
Chunks
Status
Transcript
Sign up on Apify01
Create your Apify account to access the Audio Transcriber — Podcasts, Calls & Meetings to Text.
Start the run02
The Actor will start running based on the input automatically.
Receive the output03
Monitor the progress in real-time. You will be notified as soon as your dataset is complete and ready for review.
Integrate into your workflow04
The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow.
