Modalities
Voice Cloning
AI that learns to mimic a specific person's voice from a short sample, then generates new speech in that voice from any text.
01 ——
In plain English
Voice cloning is AI technology that captures a specific person's voice — often from just a few seconds or minutes of sample audio — and lets you generate new spoken content in that voice from any text.
Legitimate uses:
- Audiobook narration — let an author "read" their own book
- Localisation — keep the original actor's voice across languages
- Accessibility — preserve the voice of someone losing their ability to speak
- Content creation — podcasters and creators producing scaled audio
Misuse risks:
- Fraud — voice-cloned scam calls impersonating CEOs or family
- Deepfake media — fake political audio, defamation
- Identity theft — bypassing voice-based authentication
Major providers: ElevenLabs leads on quality. Resemble, PlayHT, and Descript also offer voice cloning. All require some form of consent and watermarking — though enforcement varies.
02 ——
Related terms
Text-to-Speech
AI that converts written text into natural-sounding spoken audio — used for narration, accessibility, voice assistants, and content creation.
Deepfake
AI-generated media — usually video or audio — that convincingly impersonates a real person saying or doing something they didn't.
Generative AI
AI systems that create new content — text, images, audio, video, or code — rather than just classifying or predicting from existing data.
Conversational AI
AI systems designed for natural back-and-forth dialogue with users — covering chatbots, voice assistants, and AI agents.
Back to glossaryLast reviewed May 2026