#Voice & Audio

10 items

Clone a voice and train a text-to-speech model from about one minute of voice data using a WebUI.

Clone and design voices, dub videos, dictate, transcribe and create audiobooks locally in 646 languages as an ElevenLabs alternative.

Generate speech from text with pretrained models, or train and fine-tune your own text-to-speech models, including XTTS voice models.

Generate natural conversational speech in English and Chinese, suited to dialogue use cases such as LLM assistants.

Generate multilingual speech in 30 languages, design new voices from text descriptions, and clone voices from short reference clips.

Clone a voice from a reference clip and generate speech in multiple languages with control over emotion, accent, and rhythm.

Clone a voice from a few seconds of audio and generate arbitrary speech in real time, with Mandarin support.

Clone a voice from one reference clip and generate controllable speech in Chinese, English, Japanese, Spanish, and Arabic.

Run multilingual, zero-shot voice cloning text-to-speech with support for Chinese dialects, plus training and deployment tools.

Turn a transcript into realistic English dialogue in one pass, including nonverbal sounds like laughter, with audio-based emotion control.