Free Text chunk splitter (RAG / LLM)
Paste notes, articles, or transcripts — get numbered chunks you can embed or feed to models. Nothing is uploaded.
How to use this tool
- 1
Open Text chunk splitter
Use it for this task: Long document splitting, character or token budgets, overlap control, RAG / LLM ingest ready.
- 2
Paste your text
Add the content in the main text box, adjust any options, and review the live result.
- 3
Copy the finished text
Copy the output into your editor, chat, API request, or document when it looks right.
Quick facts
| Runs offline? | Yes — after load, processing stays in your browser. |
|---|---|
| Uploads data? | No. Your input is not sent to our servers. |
| Account required? | No signup or login. |
| Locales? | UI in 7 languages; tool logic is locale-agnostic. |
Top use cases
- Long document splitting, character or token budgets, overlap control, RAG / LLM ingest ready.
- Runs offline?: Yes — after load, processing stays in your browser.
- Uploads data?: No. Your input is not sent to our servers.
- Account required?: No signup or login.
- Locales?: UI in 7 languages; tool logic is locale-agnostic.
FAQ
Does my data leave this device?▾
No. Chunking runs in your browser; we do not receive your text.
Are “approximate tokens” exact?▾
No. We use ~4 characters per token as a rough budget for English-like text. Use the token counter when you need model-specific counts.
Why does overlap duplicate text?▾
Overlap repeats a tail of the previous chunk at the start of the next so each slice retains local context (common for RAG). Merging chunks later may require deduping those regions.
How large can inputs be?▾
Limited by device memory; very large documents may slow or freeze the tab.
What does paragraph mode do?▾
It keeps whole paragraphs together when possible, then hard-splits only when a single paragraph exceeds the size limit.
How to report issues?▾
Use the Contact link in the site footer.