GUIDE

FL Studio text to speech: natural spoken vocals for your beats

Spoken words are everywhere in beats: a producer tag, an intro, a skit between tracks, a chopped phrase on the hook. FL Studio has its own speech synthesizer, but it sounds like a computer from another decade, and it only runs on Windows.

SuperClonica gives you natural voices in 31 languages, free to try online, and a free engine that turns any list of phrases into WAV files for your project. This guide compares the two, shows how to use a spoken phrase in FL Studio and which voices you can use in tracks you release.

Browse voices Install the SuperClonica engine

FL Studio’s own speech synthesizer

Use both: the built-in synth for a retro robot hook, a natural voice for tags, intros, skits and spoken hooks.

  • FL Studio has a built-in speech synthesizer: drag a speech preset from the Speech folder of the browser onto an empty channel and type your text.
  • According to the FL Studio manual it runs on Windows only and makes computerized, vocoder-like vocals.
  • It offers voice personalities, a few styles and a whispered mode, and you can raise single words by semitones.
  • SuperClonica gives natural voices in 31 languages, in the browser and in an engine for Windows, macOS and Linux.

Voice a phrase free online

On the page of any voice, type a phrase of 30 to 100 characters, for example “Turn it up. This one was made for the late night drive.”, choose the language and press Voice it. In a few seconds you can listen and download the recording, with no account.

Use the voice in FL Studio

The engine’s --speed option makes the voice faster or slower, so a phrase can fit a bar before you even open the project.

  • Drag the WAV file into the playlist as an audio clip, or onto the channel rack to trigger it from the piano roll.
  • Load it into Slicex or Fruity Slicer to cut it into words and play them as a vocal chop.
  • Trim and fade it in Edison, the audio editor of FL Studio.
  • Speech does not sing: to make it melodic, chop it to the beat or tune it with a pitch-correction plugin.

Many phrases at once

For a whole pack of tags, intros and ad-libs, put the phrases into phrases.txt, one per line, install the free engine with python -m pip install superclonica-cpu and voice each into a numbered WAV: from superclonica import Superclonica; tts = Superclonica(); [tts.save(f'phrase_{i:02}.wav', tts.synthesize(line.strip(), 'M4', 'en', normalize=True)[0]) for i, line in enumerate(open('phrases.txt', encoding='utf-8'), 1) if line.strip()]. Offline there is no character minimum, so even a two-word tag works, and every file comes out at the same loudness.

Vocals in tracks you release

In a track you release, 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. Fan-made character voices and parody voices in the catalog are not for released music, and never use a voice that imitates a real artist.