Text to speech: turn written text into a natural voiceover
Text to speech (TTS) turns written text into spoken audio. In Voixie you paste up to 5,000 characters, choose a voice and listen to the result in the page. The default Voixie voices offer preset voices, your own voice clones and controls for emotion, speed and pitch; Voice Design lets you describe the tone and style you want in plain words. Every generation is saved to your history as MP3.
How to convert text to speech with Voixie
- 1.
Paste your text
Add the script you want read aloud, up to 5,000 characters per generation. Write numbers, abbreviations and names the way they should be pronounced, and use punctuation where you want pauses.
- 2.
Choose the engine and voice
Use Voixie TTS for preset or cloned voices with emotion, speed and pitch controls, or Voice Design to describe the delivery in your own words. If you connect your own ElevenLabs, Google Cloud or Azure key in your profile, their voices appear too. The voice you choose decides the language.
- 3.
Listen, adjust and save
Play the result in the page. If a word sounds wrong, change its spelling or the punctuation around it and generate again. The audio is saved as an MP3 in your history.
Text to speech questions
How much does text to speech cost?
Text to speech is charged by characters: 1 credit per 1,000 characters, and small amounts add up so short tests do not use a whole credit. With your own Google Cloud or Azure key it costs 0.2 credits per 1,000 characters, and with your own ElevenLabs key no Voixie credits are used. New accounts start with free credits.
Can I use my own voice?
Yes. Voice clones you have created in Voixie appear in the Voixie TTS voice list. Only clone voices you have the right to use.
Which languages can it speak?
That depends on the voice you choose; each engine lists its own voices by language. Write the text in the voice's language: the tool reads your text as written and does not translate it.