# Text to speech for videos, audiobooks, games and apps

Updated 2026-10-17

Local text to speech suits narration well: you can regenerate a line as often as you like, voice a whole book on a laptop, and nobody counts characters. This guide covers the practical side with Supertonic 3 voices and the SuperClonica engine: picking a voice that fits the project, writing and pacing the script, getting the audio into your editor, and what a voice bought on SuperClonica lets you do.

If nothing is installed yet, start with the offline text-to-speech guide; everything here assumes a working setup.

## Choose a voice for the project

Listen to the catalog demos, then test the voice on your own script: a voice that shines in a demo may not suit your subject.

- Explainer videos and tutorials: a clear, even voice at a moderate pace.
- Audiobooks: a narrator who stays easy to listen to for hours. Judge a long passage, not a single sentence.
- Games: one voice per character, and the same file for every line of that character. A trained voice file starts from the same timbre each time, so the character stays recognizable across hundreds of lines.
- Apps and assistants: short phrases, so check how the voice handles questions, numbers and names.

## Write the script for the ear

Text to speech reads exactly what it is given, so the script does most of the work.

- Keep sentences short and split long ones at natural pauses.
- Spell out numbers, dates, units and abbreviations the way they should sound.
- Use punctuation to shape the pauses, and start a new paragraph where the picture cuts.
- Listen to names and foreign words; if one comes out wrong, write it the way it is pronounced.
- Set the language code to the language of the text.

## Pacing and retakes

Generate the voiceover in pieces: one file per scene, slide or paragraph. That makes it easy to line up with the picture and to redo a single line.

If a line sounds off, generate it again. The standard Supertonic 3 example has a --speed option (1.05 by default; higher is faster) for the overall tempo. In the SuperClonica Python example the seed parameter controls the random part of generation: keep it to reproduce a take, change it to get a different one. Fine timing belongs in the editor: trim silences, add pauses between sentences, move clips to match the cuts.

By our estimate SuperClonica produces an hour of audio in about 7–11 minutes on a desktop 8-core CPU, so even a whole audiobook chapter can be regenerated after edits.

## Audio formats for video, audiobooks and games

Both the standard Supertonic 3 client and the SuperClonica engine save WAV files. Keep WAV while editing, and export the finished video or audiobook from your editor in the format your platform asks for, such as MP3 or AAC.

Games and apps have two options: render the lines into audio files in advance, or generate speech on the user's device. Supertonic 3 runs on desktops, in the browser through ONNX Runtime Web and in compatible mobile apps, so on-device speech works when the lines are not known in advance.

## What a purchased voice lets you do

A voice bought on SuperClonica is for use in your own projects: the videos, audiobooks, games and apps you make. Reselling the voice or republishing the voice file is not allowed. Supertonic 3 itself is under OpenRAIL-M, a royalty-free license with a list of prohibited uses; impersonating people without their consent is one of them.

You pay once, at the price the author set in US dollars. The file stays in your library, and nobody counts characters or minutes. A voice made to order is private and does not appear in the catalog. If your product needs to ship the voice file itself, for example to generate speech on players' machines, write to [support@superclonica.com](mailto:support@superclonica.com) before release.

## More guides

- [How to convert text to speech offline on your computer](https://superclonica.com/en/guides/offline-text-to-speech)
- [Voice cloning: how to get a voice that sounds like a recording](https://superclonica.com/en/guides/voice-cloning)
- [The best free text-to-speech models for local use in 2026](https://superclonica.com/en/guides/best-free-tts-models)
- [Supertonic 3 voices: where to get custom voices and how to use them](https://superclonica.com/en/guides/supertonic-3-voices)
- [Text to speech in Python: offline, free and with natural voices](https://superclonica.com/en/guides/python-text-to-speech)
- [Self-hosted text-to-speech API in Docker](https://superclonica.com/en/guides/text-to-speech-api-docker)

## Text to speech and comparisons

- [Text-to-speech that runs on your own computer](https://superclonica.com/en/text-to-speech)
- [Supertonic vs SuperClonica: same model, faster and cleaner](https://superclonica.com/en/compare/supertonic)
- [Fish Audio and Fish Speech vs SuperClonica](https://superclonica.com/en/compare/fish-audio)
- [OmniVoice vs SuperClonica: more languages or more speed](https://superclonica.com/en/compare/omnivoice)
- [Qwen3-TTS vs SuperClonica for local text-to-speech](https://superclonica.com/en/compare/qwen3-tts)
- [VoxCPM 2 vs SuperClonica: studio sound or CPU speed](https://superclonica.com/en/compare/voxcpm)
- [F5-TTS vs SuperClonica: zero-shot cloning or fast CPU speech](https://superclonica.com/en/compare/f5-tts)
- [An offline alternative to ElevenLabs](https://superclonica.com/en/compare/elevenlabs)
- [Kokoro TTS vs SuperClonica: two small models for local speech](https://superclonica.com/en/compare/kokoro)
- [Piper TTS vs SuperClonica: tiny devices or custom voices](https://superclonica.com/en/compare/piper)
- [Coqui XTTS-v2 vs SuperClonica: a Coqui TTS alternative](https://superclonica.com/en/compare/xtts)
- [Chatterbox TTS vs SuperClonica: instant cloning or a trained voice file](https://superclonica.com/en/compare/chatterbox)

## Frequently asked questions

### Can I use a purchased voice in my YouTube videos or audiobooks?

Yes, a purchased voice is meant for your own projects, and your videos and audiobooks are such projects. What you may not do is resell the voice or republish its file.

### How long does it take to voice an audiobook?

By our estimate SuperClonica produces an hour of audio in about 7–11 minutes on a desktop 8-core CPU. Add time for listening and for retakes of lines that need them.

### Can I get a unique voice for my game character?

Yes. Order a voice from an author with a reference recording and a description, or train it yourself from a recording if you have an NVIDIA GPU. A voice made to order stays private and does not appear in the catalog.

### Which format should I export narration in?

The engine writes WAV, which suits editing. Export the finished video or audiobook in whatever format your platform requires, usually MP3 or AAC.

- [Find a narrator voice](https://superclonica.com/en/explore)
- [Set up local voiceover](https://superclonica.com/en/superclonica)

## Sources

- [Supertonic example script: options and output](https://github.com/supertone-oss-archive/supertonic/blob/main/py/example_onnx.py)
- [Supertonic 3 model card and license](https://huggingface.co/supertone-oss-archive/supertonic-3)
- [SuperClonica](https://superclonica.com/en/)
- [AI voice catalog for text to speech](https://superclonica.com/en/explore)
- [Custom voice commissions for Supertonic 3](https://superclonica.com/en/requests)
- [How it works: voices, local speech, training](https://superclonica.com/en/guide)
- [Install the faster Supertonic 3 engine](https://superclonica.com/en/superclonica)
- [About us: speech synthesis enthusiasts](https://superclonica.com/en/about)
- [Contacts, support and voice complaints](https://superclonica.com/en/contacts)
- [Privacy policy: what data we keep](https://superclonica.com/en/privacy)
- [Terms of use: rules for buyers and authors](https://superclonica.com/en/terms)
- [Text to speech](https://superclonica.com/en/text-to-speech)