Chat transcript format converter
Paste a conversation in one format and convert it to another. Supports OpenAI and Anthropic JSON, ChatML, Llama 3 and plain text, with the input detected automatically, all in your browser.
Files are processed in your browser and never uploaded.
How to use Chat transcript format converter
Add your text
Type or paste your text into the input box. Everything is handled by your own browser, so nothing is sent to a server.
Run it
Press Anthropic JSON to produce the result.
Copy or save it
Copy puts the result on your clipboard.
What this tool does
Reads OpenAI, Anthropic, ChatML, Llama 3 and plain text
Paste a transcript as OpenAI JSON, Anthropic JSON, ChatML, Llama 3 or plain text and it is read without you telling it which one it is.
Detects the input format automatically
The input format is detected from the shape of what you pasted, so a half-remembered export still converts.
Converts to any of those formats
Pick any of the five formats as the output, which is what makes moving a saved conversation between two APIs a paste and a click.
Keeps system prompts and multi-line turns intact
System prompts stay system prompts and a turn that runs over several lines stays one turn, so the conversation still means the same thing afterwards.
Runs in your browser, nothing uploaded
The conversation is parsed and rewritten in your browser, so nothing you paste is uploaded.
Frequently asked questions
Is my conversation uploaded?
No. The transcript is parsed and converted entirely in your browser. Nothing you paste is sent anywhere or stored.
Which formats does it understand and produce?
It reads OpenAI or Anthropic messages JSON, ChatML, the Llama 3 header format, and plain Role: text, detecting the input automatically. It can output any of those formats, chosen with the tabs.
How does it know my input format?
It looks at the content: JSON arrays are read as messages, the ChatML and Llama markers are recognised by their special tokens, and anything else is read as plain lines that start with a role such as User: or Assistant:.
How are system messages handled for Anthropic?
Anthropic keeps the system prompt separate from the messages, so any system turns are merged into a top-level system field and the remaining user and assistant turns go into the messages array.
Will it keep multi-line messages intact?
Yes. In plain text mode a message continues across lines until the next role label, and in the other formats the full content of each turn is preserved when converting.
Last updated: