Voice Cloning

API-driven cloning and TTS with SDKs for web/mobile; supports personal and branded voices.

Duplex speech-to-speech stack building realistic, expressive voices for creators and assistants.

Open project enabling instant, controllable cloning from short samples with emotion and accent control.

Easy voice cloning for gamers/streamers and live chats; includes downloadable app and model hub.

Instant cloning for singing and speaking with creator workflows for demos, backing vocals, and podcasts.

Maker-friendly cloning for TTS, singing, and rapping; supports voice conversion and API access.

Create a TTS clone of your own voice at home via guided recordings; long-standing vendor in custom voices.

Rapid voice cloning from seconds of audio; optional local model training for privacy and pro workflows.

Fast voice cloning for video narration and multilingual dubbing; pairs with avatars and lip-sync.

White-glove custom voice cloning for organizations; deploy across web, apps, and embedded SDKs.

Licensed voice avatars and custom brand voices with enterprise controls, QA, and security.

One-minute sample cloning and a studio workflow aimed at marketing, e-learning, and content teams.

Quick voice cloning in the browser with large voice catalogs and export for voiceovers and dubbing.

Clone your voice in minutes and generate narration inside Descript’s editor for podcasts and video.

Cloning plus cross-language synthesis and style transfer for creators, apps, and localization workflows.