How to turn text into speech
- 1. Add your text
Type or paste it, or import a .txt or .docx file. For several speakers, use Dialogue Mode: one voice per line.
- 2. Choose a voice
Filter the voices by quality (Free or Plus), gender and country, then select one.
- 3. Adjust the reading
Set the speed from 0.8x to 1.5x, add pauses, and add background music that gets quieter while the voice speaks.
- 4. Generate and download
Press Generate speech, listen, then download MP3, WAV or SRT subtitles.
Frequently asked questions
Is text to speech free?
Yes, with the free voices. They cost no credit and need no account, up to a number of characters a day, and signing in raises that number. Plus voices cost credits. See the pricing page for the current numbers.
Which languages can it read?
The free voices read Vietnamese (a female and a male voice, both southern), English with US and UK accents, Chinese, Japanese, Korean, Thai, French and Spanish. Plus voices add more Vietnamese voices and voices in other languages. Filter the list by country to see the voices for one language.
Do I need an account?
Not for the free voices. Plus voices need you to sign in and have credit.
Can I download the audio as MP3?
Yes. Download MP3, WAV, or an SRT subtitle file with one entry per sentence. MP3 is converted on our server and not stored; WAV is put together in your browser. SRT timings are estimated from the length of each sentence, so check them before you publish.
Is my text private?
Plus voices run on our own machines: the text is processed in memory and not stored. Free voices send your text through our servers to Microsoft's Edge speech service; we do not store it, but Microsoft's terms apply. For private text, use a Plus voice.
Can it read long text?
Yes. Long text is split into parts and joined into one audio file for you. If a text is longer than one generation allows, the character counter shows the maximum: shorten the text or generate it in several runs.
Can I add background music?
Yes. Select one of the built-in tracks or upload your own music, and set its volume. The music gets quieter while the voice speaks, and it is mixed into the audio you download.