litellm - 💡(How to fix) Fix [Feature]: Add support for voxtral TTS [1 participants]

Fix Plan

To add support for the recently released VoxTral TTS model, we need to integrate it into the LiteLLM proxy.

Steps:

• Update dependencies to include the VoxTral TTS library
• Create a new class to handle VoxTral TTS model interactions
• Modify the proxy to use the new VoxTral TTS class

Example Code:

# Import the VoxTral TTS library
import voxtral

# Create a new class to handle VoxTral TTS model interactions
class VoxTralTTS:
    def __init__(self):
        self.model = voxtral.Model()

    def synthesize(self, text):
        return self.model.synthesize(text)

# Modify the proxy to use the new VoxTral TTS class
class Proxy:
    def __init__(self):
        self.tts = VoxTralTTS()

    def handle_request(self, text):
        audio = self.tts.synthesize(text)
        return audio

Verification

To verify that the fix worked, test the proxy with a sample text input and check that the output audio is generated correctly using the VoxTral TTS model.

Extra Tips

• Make sure to handle any errors that may occur during the integration process
• Consider adding support for multiple TTS models to allow for flexibility and customization
• Refer to the VoxTral TTS documentation for any specific requirements or guidelines for integration.