GUIDE

Audacity text to speech: make the voice, then edit it in Audacity

Audacity is the free editor many people open for podcasts, voice-overs and audiobooks, so it is natural to look for text to speech there. Audacity does not include it, and neither do Intel’s OpenVINO AI effects for Audacity, which cover noise suppression, music separation, transcription and music generation.

The practical workflow is to make the voice with a text-to-speech engine and do everything else in Audacity. SuperClonica gives you natural voices in 31 languages, free to try online, and a free engine that writes WAV files on your computer. This guide shows both halves.

Browse voices Install the SuperClonica engine

What Audacity can and cannot do

A generated voice comes out clean, so you can skip noise reduction and go straight to editing.

  • Audacity has no built-in text to speech and no text-to-speech plugin of its own.
  • Its OpenVINO AI effects transcribe speech to text, which is the opposite direction.
  • Audacity opens WAV, MP3, OGG and FLAC, so a generated voice is just another track.
  • SuperClonica adds more than 170 catalog voices, 31 languages and a free engine that runs offline.

Voice a line free online

On the page of any voice, type a line of 30 to 100 characters, for example “Welcome back to the show. Today we start with a question.”, choose the language and press Voice it. In a few seconds you can listen and download the recording, with no account.

Edit the voice in Audacity

Normalize the final mix once at the end rather than every clip on its own.

  • Open the WAV file in Audacity, or drag it into a project with your music.
  • Shorten long gaps with Truncate Silence and fade the ends.
  • Put the music on a track below the voice and run Auto Duck: the music drops whenever the voice speaks.
  • Add a little reverb or EQ for character, or a vocoder for a robot voice.

A whole script on your computer

For a long script, install the free engine with python -m pip install superclonica-cpu and voice the whole text file into one WAV: superclonica --text-file script.txt --voice F1 --lang en --normalize --output voice.wav. The engine has no character limit, splits long text into pieces and joins them, and --normalize brings the voice to −18 LUFS. Change one sentence later? Voice just that sentence and paste it over the old one in Audacity.

Voices for what you publish

For a podcast, an audiobook or a video you publish, use the ten stock voices of the model, M1 to M5 and F1 to F5, free under the OpenRAIL-M license, or your own voice trained in the SuperClonica studio. Character voices in the catalog are fan-made: fine for fan projects and parodies, not for commercial work.