Go to example tasks
Audio transcripts as chunks for RAG
Transcribe audio and split the text into overlapping, timestamped chunks ready for embeddings, vector databases and RAG pipelines (LangChain, LlamaIndex).
Audio & Video to Text Transcription (Whisper): Speech to Textfguiraud/audio-video-transcriber
File
Status
Language
Duration (s)
+4 fieldsTextNumberBooleanListObject
Input
Audio or video URLs
url:https://archive.org/download/gettysburg_johng_librivox/gettysburg_address_64kb.mp3
Model:base
What to return:chunks+1
Chunk size (characters):1000
Output fields
File
Status
Language
Duration (s)
Billed min
Words
Transcript
Error
Sign up on Apify01
Create your Apify account to access the Audio & Video to Text Transcription (Whisper): Speech 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.
