Create Persona
This endpoint creates a new persona that can be used by replicas in conversations.
With a persona, you are able to craft the personalities of your replica across conversations.
LLM
With the llm layer, you can leverage your own OpenAI compatible LLM or you can use one a Tavus provided model.
- tavus-gpt-4o: The smartest option for complex interactions.
- tavus-gpt-4o-mini: A hybrid model that balances performance and intelligence.
- tavus-llama: The default choice if no LLM layer is provided. This is the fastest model, offering the best user-to-user (U2U) experience. It’s on-premise, making it incredibly performant.
TTS
With Tavus’ default TTS engine, you get the faster utterance-to-utterance speed, but you can always bring your own if you have voices already trained with:
- Cartesia
- Elevenlabs
- Playht
STT
Although we support both, we highly recommend using tavus-advanced for higher transcription accuracy and non-English languages at little to no additional latency cost.
- tavus-turbo: Our lowest-latency model, but
tavus-advancedprovides higher transcription accuracy. - tavus-advanced: Provides higher transcription accuracy.
Authorizations
Body
A name for the persona.
This is the system prompt that will be used by the llm.
This is the context that will be used by the llm.
The default replica_id associated with this persona if one exists. When creating a conversation, a persona_id with a default_replica_id associated can we used to create a conversation without specifying a replica_id.