# AI voice over for ads: radio spots, video ads and promos

Updated 2026-10-24

An ad lives on versions: a 15-second cut and a 30-second one, a new price, another city, another language. Recording each with a voice actor takes time; an AI voice over turns every version into a typed script and a few seconds of synthesis.

SuperClonica has energetic and calm voices with no character behind them, a free online test and a free engine that voices every version on your computer. This guide shows which voices suit ads, how long a script should be, how to voice the versions offline and what to keep in mind before an ad goes on air.

## Voices for ads

Most catalog voices were recorded in Russian and keep a slight accent in other languages, so voice the key line of your ad in your language before you choose.

- Energetic Katya: a pleasant, energetic young female voice.
- Energetic Narrator: mid-low with clear emphasis, so a promo sounds alive rather than official. No specific host behind the model.
- Young Analyst: reads comparisons and product benefits clearly, without theatrics.
- Pleasant Announcer: low and restrained, for a calm brand voice.
- The ten stock voices of the model, M1 to M5 and F1 to F5: free in the engine.

## Test a line of your ad free

On the page of any voice, paste the key line of your ad, 30 to 100 characters, choose the language and press Voice it. In a few seconds you can hear whether the voice sells it and download the recording. No account is needed.

## Write a script that fits the time

Time every version after voicing it: a few words too many is easier to cut in the script than in the audio.

- About 2 to 2.5 words a second: roughly 30 to 35 words for 15 seconds and 65 to 75 for 30.
- One message per spot, and the brand name early and again at the end.
- Prices and numbers as you want them read; the engine spells digits out in 27 languages, so check the result by ear.
- A clear call to action in the last sentence.

## Every version offline

Install the free SuperClonica engine: python -m pip install superclonica-cpu. Keep each version of the script in its own text file and voice it with one command: superclonica --text-file spot-15s.txt --voice M3 --lang en --normalize --output spot-15s.wav. The --normalize option brings all versions to the same loudness, −18 LUFS, and the result is a 16-bit WAV for any editor. It runs offline on an ordinary processor, with no character limit, so a new price or a new city costs nothing extra.

## Before the ad goes on air

Do not use character voices or voices that imitate real people in ads: a fan-made or parody voice is not an endorsement. For a lasting brand voice, record a clean phrase of 5 to 10 seconds of a speaker who agreed in writing, train it in the studio on a computer with an NVIDIA graphics card, or order it on the exchange. Some platforms and countries require AI-generated content to be labeled, so check the rules where the ad will run.

## 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)
- [Text to speech for videos, audiobooks, games and apps](https://superclonica.com/en/guides/text-to-speech-for-videos)
- [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 in character voices: voice any line as your favourite character](https://superclonica.com/en/guides/character-voice-generator)
- [Free unlimited text to speech without sign-up: run it on your own computer](https://superclonica.com/en/guides/free-unlimited-text-to-speech)
- [Narrator voice generator: narration for videos, audiobooks and podcasts](https://superclonica.com/en/guides/narrator-voice-generator)
- [Child voice text to speech: kid and teenager AI voices](https://superclonica.com/en/guides/child-voice-text-to-speech)
- [Anime voice generator: text to speech in anime character voices](https://superclonica.com/en/guides/anime-voice-generator)
- [Text to speech in 31 languages: one voice for every language](https://superclonica.com/en/guides/text-to-speech-languages)
- [Female voice text to speech: natural AI female voices](https://superclonica.com/en/guides/female-voice-text-to-speech)
- [Male voice text to speech: deep and natural AI male voices](https://superclonica.com/en/guides/male-voice-text-to-speech)
- [Realistic text to speech: AI voices that sound human](https://superclonica.com/en/guides/realistic-text-to-speech)
- [AI voice generator: turn text into speech with ready AI voices](https://superclonica.com/en/guides/ai-voice-generator)
- [Text to speech reader: listen to books, PDFs and articles](https://superclonica.com/en/guides/text-to-speech-reader)
- [TikTok voice generator: voices for TikTok, Shorts and Reels](https://superclonica.com/en/guides/tiktok-voice-generator)
- [Dota 2 hero voices: make any hero say your line](https://superclonica.com/en/guides/dota-2-voice-generator)
- [Cartoon voice generator: make a cartoon character say your text](https://superclonica.com/en/guides/cartoon-voice-generator)
- [Jarvis voice generator: your text in a Jarvis-style AI voice](https://superclonica.com/en/guides/jarvis-voice-generator)
- [Darth Vader voice generator: Star Wars voices for your text](https://superclonica.com/en/guides/darth-vader-voice-generator)
- [Train your own TTS voice on your NVIDIA GPU](https://superclonica.com/en/guides/train-tts-voice)
- [Emotional text to speech: how to make an AI voice sound expressive](https://superclonica.com/en/guides/emotional-text-to-speech)
- [Hindi text to speech: AI voices that read Hindi](https://superclonica.com/en/guides/hindi-text-to-speech)
- [Spanish text to speech: AI voices that read Spanish](https://superclonica.com/en/guides/spanish-text-to-speech)
- [Japanese text to speech: AI voices that read Japanese](https://superclonica.com/en/guides/japanese-text-to-speech)
- [Russian text to speech with voices recorded in Russian](https://superclonica.com/en/guides/russian-text-to-speech)
- [Portuguese text to speech: AI voices that read Portuguese](https://superclonica.com/en/guides/portuguese-text-to-speech)
- [German text to speech: AI voices that read German](https://superclonica.com/en/guides/german-text-to-speech)
- [French text to speech: AI voices that read French](https://superclonica.com/en/guides/french-text-to-speech)
- [Korean text to speech: AI voices that read Korean](https://superclonica.com/en/guides/korean-text-to-speech)
- [English text to speech: AI voices that read English](https://superclonica.com/en/guides/english-text-to-speech)
- [Arabic text to speech: AI voices that read Arabic](https://superclonica.com/en/guides/arabic-text-to-speech)
- [Geralt voice generator: Witcher voices for your text](https://superclonica.com/en/guides/witcher-voice-generator)
- [GTA 5 voice generator: Trevor, Franklin and Lester say your text](https://superclonica.com/en/guides/gta-5-voice-generator)
- [How to make an audiobook with an AI voice](https://superclonica.com/en/guides/audiobook-ai-voice)
- [Text to speech for game development: NPC voices without a studio](https://superclonica.com/en/guides/text-to-speech-for-games)
- [Italian text to speech: AI voices that read Italian](https://superclonica.com/en/guides/italian-text-to-speech)
- [Polish text to speech: AI voices that read Polish](https://superclonica.com/en/guides/polish-text-to-speech)
- [Turkish text to speech: AI voices that read Turkish](https://superclonica.com/en/guides/turkish-text-to-speech)
- [Ukrainian text to speech: AI voices that read Ukrainian](https://superclonica.com/en/guides/ukrainian-text-to-speech)
- [Vietnamese text to speech: AI voices that read Vietnamese](https://superclonica.com/en/guides/vietnamese-text-to-speech)
- [Indonesian text to speech: AI voices that read Indonesian](https://superclonica.com/en/guides/indonesian-text-to-speech)
- [Meme voice generator: funny voices for your memes](https://superclonica.com/en/guides/meme-voice-generator)
- [VHS voice-over dub: the 90s one-voice translation style](https://superclonica.com/en/guides/vhs-voice-over-dub)
- [Stream alert voices: character voices for follows, subs and donations](https://superclonica.com/en/guides/stream-alert-voices)
- [Dutch text to speech: AI voices that read Dutch](https://superclonica.com/en/guides/dutch-text-to-speech)
- [Swedish text to speech: AI voices that read Swedish](https://superclonica.com/en/guides/swedish-text-to-speech)
- [Czech text to speech: AI voices that read Czech](https://superclonica.com/en/guides/czech-text-to-speech)
- [Greek text to speech: AI voices that read Greek](https://superclonica.com/en/guides/greek-text-to-speech)
- [Romanian text to speech: AI voices that read Romanian](https://superclonica.com/en/guides/romanian-text-to-speech)
- [Hungarian text to speech: AI voices that read Hungarian](https://superclonica.com/en/guides/hungarian-text-to-speech)
- [Danish text to speech: AI voices that read Danish](https://superclonica.com/en/guides/danish-text-to-speech)
- [Finnish text to speech: AI voices that read Finnish](https://superclonica.com/en/guides/finnish-text-to-speech)
- [Bulgarian text to speech: AI voices that read Bulgarian](https://superclonica.com/en/guides/bulgarian-text-to-speech)
- [Croatian text to speech: AI voices that read Croatian](https://superclonica.com/en/guides/croatian-text-to-speech)
- [Slovak text to speech: AI voices that read Slovak](https://superclonica.com/en/guides/slovak-text-to-speech)
- [Slovenian text to speech: AI voices that read Slovenian](https://superclonica.com/en/guides/slovenian-text-to-speech)
- [Estonian text to speech: AI voices that read Estonian](https://superclonica.com/en/guides/estonian-text-to-speech)
- [Latvian text to speech: AI voices that read Latvian](https://superclonica.com/en/guides/latvian-text-to-speech)
- [Lithuanian text to speech: AI voices that read Lithuanian](https://superclonica.com/en/guides/lithuanian-text-to-speech)
- [Scary voice generator: horror, villain and demon voices for your text](https://superclonica.com/en/guides/scary-voice-generator)
- [Cute voice text to speech: anime girl, kawaii and cartoon voices](https://superclonica.com/en/guides/cute-voice-text-to-speech)
- [Old man voice generator: grandpa, wizard and elder voices](https://superclonica.com/en/guides/old-man-voice-generator)
- [Deep voice generator: low AI voices for text to speech](https://superclonica.com/en/guides/deep-voice-generator)
- [SpongeBob text to speech: make him say anything](https://superclonica.com/en/guides/spongebob-voice-generator)
- [Batman text to speech: make him say anything](https://superclonica.com/en/guides/batman-voice-generator)
- [Text to speech for presentations: narrate your slides](https://superclonica.com/en/guides/text-to-speech-for-presentations)
- [Rick and Morty voice generator: AI text to speech](https://superclonica.com/en/guides/rick-and-morty-voice-generator)
- [AI podcast voice: intros, ad reads and whole episodes](https://superclonica.com/en/guides/ai-podcast-voice)
- [Russian accent voice generator: English with a Russian accent](https://superclonica.com/en/guides/russian-accent-voice-generator)
- [News anchor voice generator: an AI voice that reads the news](https://superclonica.com/en/guides/news-anchor-voice-generator)
- [Bedtime story AI voice: a calm narrator for fairy tales](https://superclonica.com/en/guides/bedtime-story-ai-voice)
- [AI voice changer or text to speech: which one you need](https://superclonica.com/en/guides/voice-changer-vs-text-to-speech)
- [Linux text to speech: natural offline TTS from the terminal](https://superclonica.com/en/guides/text-to-speech-linux)
- [Windows text to speech: natural voices, offline, saved as WAV](https://superclonica.com/en/guides/text-to-speech-windows)
- [Mac text to speech: natural offline voices on macOS](https://superclonica.com/en/guides/text-to-speech-mac)
- [Voicemail greeting generator: a calm AI voice for your phone](https://superclonica.com/en/guides/voicemail-greeting-generator)
- [AI dubbing: the same voice in 31 languages](https://superclonica.com/en/guides/ai-dubbing-same-voice)
- [AI voice for a faceless YouTube channel](https://superclonica.com/en/guides/faceless-youtube-ai-voice)
- [Witch voice generator: sorceresses, seers and dark fairies](https://superclonica.com/en/guides/witch-voice-generator)
- [AI voice for e-learning: narrate online courses and training](https://superclonica.com/en/guides/e-learning-ai-voice)
- [Text to speech pauses and pronunciation: control the voice with text](https://superclonica.com/en/guides/text-to-speech-pauses-pronunciation)
- [Text to MP3: save text to speech as an MP3 file](https://superclonica.com/en/guides/text-to-mp3)
- [Santa voice generator: Christmas greetings in a warm old voice](https://superclonica.com/en/guides/santa-voice-generator)
- [Happy birthday voice message from a character](https://superclonica.com/en/guides/birthday-voice-message)
- [D&D narrator voice: AI voices for tabletop RPGs](https://superclonica.com/en/guides/dnd-narrator-voice)
- [AI voice acting for visual novels and Ren’Py games](https://superclonica.com/en/guides/visual-novel-ai-voice)
- [AI voices for audio drama and radio plays](https://superclonica.com/en/guides/audio-drama-ai-voices)
- [A Speechify alternative that works offline](https://superclonica.com/en/guides/speechify-alternative)
- [A Murf AI alternative for offline voice-over](https://superclonica.com/en/guides/murf-ai-alternative)
- [A FakeYou alternative: character voices that run offline](https://superclonica.com/en/guides/fakeyou-alternative)
- [An offline alternative to Google Cloud Text-to-Speech](https://superclonica.com/en/guides/google-text-to-speech-alternative)
- [A Balabolka alternative with natural neural voices](https://superclonica.com/en/guides/balabolka-alternative)
- [PDF to audio: convert a PDF to MP3 with natural voices](https://superclonica.com/en/guides/pdf-to-audio)
- [Word document to audio: turn Word and Google Docs into MP3](https://superclonica.com/en/guides/word-document-to-audio)
- [Meditation voice generator: calm AI voices for guided sessions](https://superclonica.com/en/guides/meditation-voice-generator)

## 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

### Is there a free voice for ads?

The engine includes ten stock voices, M1 to M5 and F1 to F5, at no cost, and any catalog voice can be tried free on a line of 30 to 100 characters.

### How long should a 30-second script be?

About 65 to 75 words. Voice it, time it and cut words if it runs long.

### Can I use a celebrity or character voice in an ad?

No. Character and parody voices are fan-made and not endorsed. Use a neutral voice or a brand voice trained from a speaker who agreed.

### Do I need a graphics card?

No. Voicing text runs on an ordinary processor; only training a new voice needs an NVIDIA graphics card.

- [Browse voices](https://superclonica.com/en/explore)
- [Install the SuperClonica engine](https://superclonica.com/en/superclonica)

## Sources

- [Supertonic 3 model card](https://huggingface.co/supertone-oss-archive/supertonic-3)
- [SuperClonica engine on PyPI](https://pypi.org/project/superclonica-cpu/)
- [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)