Aoede
A clear, bright female voice at a moderate pace with a calm, elegant narrative style, suitable for audiobooks and documentary narration.
Text to Speech · English · Chinese · Japanese
Text, a PDF or Word file, or a link — read out word-for-word, or lightly polished by AI first.
I'm sorry, Dave. I'm afraid I can't do that. Mission is too important.
The game is afoot, Watson! Observe everything, miss nothing.
Here we see the wild developer in their natural habitat, drinking coffee.
I'm sorry, Dave. I'm afraid I can't do that. Mission is too important.
The game is afoot, Watson! Observe everything, miss nothing.
Here we see the wild developer in their natural habitat, drinking coffee.
No projects yet
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, or Japanese.
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.
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.
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, and Japanese, 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.
When you want two hosts talking it through rather than one voice reading it out.
When the delivery matters — several voices in one take, or a line that has to land with real emotion.
When none of the library voices should be the one speaking — record 30 seconds and use your own.
Play them here, then take one straight into the editor above. Every voice in the library is free to listen to.
A clear, bright female voice at a moderate pace with a calm, elegant narrative style, suitable for audiobooks and documentary narration.
A clear, steady male voice that is professional and confident, suitable for business presentations, knowledge sharing, and narration.
A clear, steady female voice with warm tones, full of confidence and guidance, suitable for business presentations, knowledge sharing, and narration.
A clear, confident, and professional male voice with medium-low pitch and moderately fast pace, ideal for business, news, and documentary narration.
A steady, magnetic male voice at a moderately fast pace with clear pronunciation, suitable for history, science, and educational narration or audiobooks.
A warm, mellow voice at a moderate pace, suitable for various professional broadcasts and communication scenarios.