p HA howto
voice-cloning Text to Speech Standard Active

XTTS-v2

Clone voices in seconds

by Coqui (via Replicate)

Clone any voice with just 6 seconds of audio. Supports 17 languages.

XTTS-v2

Input Types

text, audio

Output Types

audio

Capabilities

  • Voice cloning
  • 17 languages
  • Emotion transfer
  • Fast generation

Use Cases

  • Custom narration
  • Multilingual dubbing
  • Personalized TTS
  • Character voices

Tags

voice-cloning xtts coqui multilingual
Documentation
License: CPML

Similar Models

MyShell (via Replicate)

OpenVoice

Instant voice cloning with fine-grained control over style, emotion, and accent.

Replicate

Parler TTS

Describe the voice you want in text. Generate speech matching your description.

Use XTTS-v2 in Promptha

Create powerful AI workflows using XTTS-v2 and other models on Promptha.

Create a Block Browse Prompts