Voices & Languages

Cross-lingual Synthesis

Any voice can speak any supported language. The voice keeps its unique character while speaking the target language fluently.


How it works

Simply choose a voice and pass text in any language. The model detects the script automatically and produces speech in that language while preserving the voice's timbre and accent characteristics.

Examples

English-native voice speaking Hindi

python
# English-native voice (Varun) speaking Hindi
config = TTSConfig(model="zero-indic", voice="Varun")
result = await client.tts.synthesize("नमस्ते! आप कैसे हैं?", config=config)

Tamil-native voice speaking English

python
# Tamil-native voice (Murugan) speaking English
config = TTSConfig(model="zero-indic", voice="Murugan")
result = await client.tts.synthesize("Good morning, how are you?", config=config)

Kannada-native voice speaking Tamil text

python
# Kannada-native voice (Shreya) speaking Tamil text
config = TTSConfig(model="zero-indic", voice="Shreya")
result = await client.tts.synthesize("Vanakkam, neenga eppadi irukeenga?", config=config)