​
Supported Languages

Tavus supports over 30 languages for spoken interaction, powered by two integrated text-to-speech (TTS) engines: Cartesia and ElevenLabs. If a selected language is not supported by our default TTS engine (Cartesia), your CVI will automatically switch to ElevenLabs to kick off the conversation.
  • English (all variants)
  • French (France, Canada)
  • German
  • Spanish (Spain, Mexico)
  • Portuguese (Brazil, Portugal)
  • Chinese
  • Japanese
  • Hindi
  • Italian
  • Korean
  • Dutch
  • Polish
  • Russian
  • Swedish
  • Turkish
  • Indonesian
  • Filipino
  • Bulgarian
  • Romanian
  • Arabic (Saudi Arabia, UAE)
  • Czech
  • Greek
  • Finnish
  • Croatian
  • Malay
  • Slovak
  • Danish
  • Tamil
  • Ukrainian
  • Hungarian
  • Norwegian
  • Vietnamese
For a full list of supported languages for each TTS engine, please click on the following links:

Cartesia (default)

ElevenLabs

By default, Tavus uses the Cartesia TTS engine.

​
Setting the Conversation Language

To specify a language, use the language parameter in the Create Conversation. You must use the full language name, not a language code.
cURL
curl --request POST \
  --url https://tavusapi.com/v2/conversations \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api_key>' \
  --data '{
  "persona_id": "pdced222244b",
  "replica_id": "rfe12d8b9597",
  "properties": {
    "language": "spanish"
   }
}'
Language names must match exactly with those supported by the selected TTS engine.

​
Smart Language Detection

To automatically detect the participant’s spoken language throughout the conversation, set language to multilingual when creating the conversation:
cURL
curl --request POST \
  --url https://tavusapi.com/v2/conversations \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api_key>' \
  --data '{
  "persona_id": "pdced222244b",
  "replica_id": "rfe12d8b9597",
  "properties": {
    "language": "multilingual"
   }
}'
This enables ASR (Automatic Speech Recognition) to automatically switch languages, dynamically adjusting the pipeline to transcribe and respond in the detected language throughout the conversation.