XTTS-v2
XTTS-v2 provides cross-lingual text-to-speech with voice cloning, allowing the same voice to speak multiple languages.
Overview
| Property | Value |
|---|---|
| Provider | Coqui |
| Cost | 80 credits |
| Modality | Audio |
| Duration | Variable |
| Prompt Required | Yes |
What It's Best For
- Multilingual content — Same voice, different languages
- Localization — Global content distribution
- Voice cloning — Custom voice models
- International brands — Consistent global voice
- Dubbing — Same voice for translations
Inputs
Text (Required)
The text to speak.
Connection Color: 🟡 Yellow
Voice Sample (Optional)
Audio sample for voice cloning.
Connection Color: 🟠 Orange
Configuration
Language
Type: Select
English, Spanish, French, German, Italian, Portuguese, Polish, Turkish, Russian, Dutch, Czech, Arabic, Chinese, Japanese, Korean, Hindi.
Speed
Type: Slider
Range: 0.5 - 2.0
Default: 1.0
Seed
Type: Number
Output
Type: Audio
Connection Color: 🟠 Orange
Use Cases
Multilingual Narration
Same voice narrating in English, Spanish, and French,
consistent brand voice across languages.
Global Marketing
Product announcement in multiple languages,
same spokesperson voice,
localized content.
Dubbing
Translate video narration to new language,
maintain original voice characteristics.
Supported Languages
| Language | Quality |
|---|---|
| English | ⭐⭐⭐⭐⭐ |
| Spanish | ⭐⭐⭐⭐⭐ |
| French | ⭐⭐⭐⭐⭐ |
| German | ⭐⭐⭐⭐ |
| Chinese | ⭐⭐⭐⭐ |
| Japanese | ⭐⭐⭐⭐ |
| Others | ⭐⭐⭐ |
Tips for Best Results
- Match language — Voice sample in target language helps
- Clear samples — Better cloning results
- Native text — Use native speakers for text
- Test languages — Quality varies by language
Related Models
- Voice Cloning — Single language
- Dia TTS — Multi-speaker
- Kokoro TTS — Fast generation