Audio Tools · 12 Languages
Drop in what needs reading, hear it in a natural voice
Text, a PDF or Word file, or a link — read out word-for-word, or lightly polished by AI first.
Type or paste your text, upload one file (PDF, Word, EPUB, Markdown, or TXT), or paste a link to read from.
Choose a voice from the library — or one you cloned yourself — and set the output language to English, Chinese Mandarin, Japanese, Spanish, Portuguese, French, German, Turkish, Korean, Italian, Thai, or Vietnamese.
Leave AI Polish off and the voice speaks your text word-for-word. Switch it on and the script is tidied into spoken language first.
Listen in the browser, then export the audio file — and SRT subtitles when you need captions.
Text to speech (TTS) converts written text into spoken audio using synthetic voices, so you can listen to a document instead of reading it — or produce a voiceover without recording anything.
Type or paste text directly, upload one file (PDF, Word, EPUB, Markdown, or TXT), or paste a link such as a YouTube video or an article page.
You can generate speech in English, Chinese Mandarin, Japanese, Spanish, Portuguese, French, German, Turkish, Korean, Italian, Thai, and Vietnamese, choosing from the built-in voice library or a voice you cloned yourself.
With AI Polish off, the voice speaks exactly what you wrote — useful for scripts you have already edited. With it on, your text is rewritten into smoother spoken language before it is read aloud.
Yes. Export the finished audio file, and export SRT subtitles alongside it when you need captions for video or accessibility.
Yes. A voice you create in Voice Cloning shows up in the voice picker here, so the same voice can read any text you paste in.
Turn a long PDF or report into audio you can play on a commute instead of reading it at a desk.
Generate a clean narration track for tutorials, ads, and social clips without booking studio time.
Publish a spoken version of an article or newsletter for readers who would rather listen.
Have a draft read back word-for-word to catch clumsy sentences and typos your eyes skip over.