GUIDE

DaVinci Resolve text to speech: AI narration for any edition

DaVinci Resolve is free and powerful, but its free edition cannot turn text into speech. DaVinci Resolve 21 added an AI Speech Generator, and it belongs to the paid Studio edition. So most editors write the narration in one place and voice it in another.

SuperClonica gives you natural narrators, character voices and 31 languages, free to try online, plus a free engine that voices a whole script into WAV files for your timeline. This guide walks from script to timeline in either edition of Resolve.

Browse voices Install the SuperClonica engine

What Resolve can do with text

If you already own Studio, its generator is handy for a quick scratch track; for character voices, other languages or the free edition, voice the text outside Resolve.

  • Free edition: no built-in text to speech.
  • DaVinci Resolve 21 Studio, the paid edition: an AI Speech Generator with a few built-in voices and custom voices made from a short sample.
  • Both editions read WAV, so a voice made anywhere else drops straight onto the timeline.
  • SuperClonica adds more than 170 catalog voices, 31 languages and a free engine that runs on your own computer.

Voice a line free online

On the page of any voice, type a line of 30 to 100 characters, for example “Every great edit starts with a story worth telling.”, choose the language and press Voice it. In a few seconds you can listen and download the recording, with no account.

Bring the voice into Resolve

Name files in timeline order, 001.wav, 002.wav, so a whole folder lines up when you import it.

  • Import the WAV file into the media pool together with your footage.
  • Put the voice on its own audio track and trim the start and the end.
  • On the Fairlight page, lower the music under the voice with volume keyframes.
  • Make subtitles from the same script, so the words on screen match the voice exactly.

A whole script at once

Put the script into script.txt, one scene or paragraph per line, install the free engine with python -m pip install superclonica-cpu and voice every line into a numbered file: from superclonica import Superclonica; tts = Superclonica(); [tts.save(f'{i:03}.wav', tts.synthesize(line.strip(), 'M2', 'en', normalize=True)[0]) for i, line in enumerate(open('script.txt', encoding='utf-8'), 1) if line.strip()]. Every file comes out at the same loudness, −18 LUFS. For one long narration file, use the command line: superclonica --text-file script.txt --voice M2 --lang en --normalize --output narration.wav. The engine runs offline and has no character limit.

Voices for videos you publish

For a monetized channel or a client video, use the ten stock voices, 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 videos and parodies, not for ads or client work.