Split recordings into RAG chunks with timestamps

Created by

Salih Küçükkayış

Actor

Audio to Text — Whisper Transcription, SRT, RAG Chunks

Transcribe a podcast, meeting or lecture and get it back as RAG-ready chunks of about 1,500 characters, made of whole sentences, each with its start and end time. Store the chunks in a vector database and every search hit can link to the right moment of the recording. Whisper on CPU, $5 per 1,000 audio minutes.

Try for free

Audio to Text — Whisper Transcription, SRT, RAG Chunkssaliga/audio-to-text

URL

File

Episode

Language

+5 fields

Input

Audio or video links:https://archive.org/download/short_story_036_0904_librivox/shortstory036_sciencevsluck_gam_64kb.mp3

Model:base

RAG chunk size (characters):1500

Chunk overlap (characters):200

Output fields

URL

File

Episode

Language

Duration (s)

Billed minutes

Words

Transcript

Error

How it works

Sign up on Apify or log in

The Audio to Text — Whisper Transcription, SRT, RAG Chunks Actor is ready to run with the inputs already set for "Split recordings into RAG chunks with timestamps". Sign up or log in and you'll land in Apify Console with a copy of this exact task.

Start the "Split recordings into RAG chunks with timestamps" task

The Audio to Text — Whisper Transcription, SRT, RAG Chunks Actor will start running based on the input automatically. You can also change all the input fields, like audio or video links, model, and more, to match your specific use case.

Receive the "Split recordings into RAG chunks with timestamps" output

Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as URL, file, episode, and more.

Integrate into your workflow

The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also run the "Split recordings into RAG chunks with timestamps" task via API.