Doc2Audio

Text to Audio

Plain text, Markdown and HTML, made for listening.

Start with the words

Plain text files contain little layout noise, making them useful sources for narration. Notes, drafts and other written material can become a detailed spoken version or a shorter summary. Doc2Audio accepts uploaded TXT, Markdown and HTML files. It does not fetch private webpages or open links inside your document.

What happens to formatting

HTML scripts and styles are removed before narration. Markdown is processed as text, so prose and clear headings work better than code listings or elaborate tables. UTF-8 text is recommended for accents and non-English characters. The output is a spoken adaptation, not an exact reproduction of every markup character.

An estimate before you listen

The estimated duration comes from the extracted word count and your selected summary level. A concise version is normally shorter than a detailed reading. Voice pacing and translation can change the result, so the estimate is approximate. Once full audio is generated, its duration is measured from the finished file.