is it possible to change the tts module on the fly...
# ask-ai
a
is it possible to change the tts module on the fly?
t
Thanks for reaching out, affandy. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.
Yes, it is possible to change the Text-to-Speech (TTS) module on the fly. This can be done using the
update_options()
method available in various TTS implementations. For example, you can update parameters like the model, voice, language, and other settings without restarting your application. Additionally, you can switch TTS providers by modifying the configuration in your application code. Let me know if you need further details or examples! Sources: livekit.plugins.deepgram API documentation | Tree View: | dse-workbench | livekit.plugins.cartesia API documentation | AI Voice Assistant Quickstart | LiveKit Docs
a
I mean to update the VoicePipelineAgent's TTS from elevenlabs to cartesia for example
t
To update the VoicePipelineAgent's TTS from ElevenLabs to Cartesia, you can follow these steps: 1. Edit your
agent.py
file and update the imported plugins list to include `cartesia`: 2. Update the
tts
plugin for your assistant in the
agent.py
file: 3. Update your
.env.local
file to include your Cartesia API key: 4. Install the Cartesia plugin locally: 5. Start your agent: Let me know if you need further assistance! Sources: AI Voice Assistant Quickstart | LiveKit Docs | AI Voice Assistant Quickstart | LiveKit Docs
a
how to change the VoicePipelineAgent's TTS from elevenlabs to cartesia during runtime?
t
Currently, the available documentation does not provide specific instructions for changing the VoicePipelineAgent's TTS from ElevenLabs to Cartesia during runtime. The provided guidance focuses on configuring the TTS provider at setup time by editing the
agent.py
file. If runtime switching is critical for your use case, I recommend consulting with a developer or exploring the API documentation further. Let me know if you'd like me to assist with anything else!