Thanks for reaching out, Test. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.

STT is not sayings dots

It sounds like the issue with STT not recognizing or converting spoken dots in email addresses can vary depending on the STT provider and how it’s set up. To help you better, could you please let me know: • Which STT provider you’re using (like Google Cloud, Deepgram, Speechmatics, etc.)? • If you’ve enabled any settings related to spoken punctuation or text formatting in your STT configuration? For instance, with Google Cloud STT, the

spoken_punctuation

parameter needs to be set to

True

for this to work properly. Just let me know, and I’ll be happy to guide you through the next steps! Sources: Workflows | LiveKit Docs | livekit-plugins/livekit-plugins-cartesia/livekit/plugins/cartesia/stt.py

TTS i means is not saying dots

Thanks so much for letting me know that the issue is related to TTS (Text-to-Speech). To help you better, could you share a bit more about what’s happening? For instance: • Which TTS provider or engine are you using? • What exactly are you noticing? Is it skipping the word "dot" or saying it differently than expected? • What would you like the TTS to do instead? • Have you made any particular settings or adjustments to the TTS engine? With these details, I’ll be in a much better position to support you and find a solution together.

deepgram

Thanks for reaching out! While Deepgram TTS doesn’t have a direct setting to control how dots are pronounced, you can definitely customize this by preprocessing your text before sending it to the TTS engine. For instance, you might replace dots with words like "dot" or "period" using a simple text replacement function. Here’s a friendly example to help you get started:

async def adjust_pronunciation(input_text: AsyncIterable[str]) -> AsyncIterable[str]:
    replacements = {
        ".": " dot ",      # or " period " in certain contexts
        "...": " dot dot dot ",
    }
    async for chunk in input_text:
        for old, new in replacements.items():
            chunk = chunk.replace(old, new)
        yield chunk

This approach lets you preprocess the text so that dots come through exactly how you want them to sound. You can apply this by overriding the

tts_node

in your agent. If you’d like to dive deeper into how to override nodes, the Pipeline nodes and hooks documentation is a great resource. If you’d like a hand setting this up or have any other questions, just let me know—I’m here to help! Sources: Agent speech and audio | LiveKit Docs | Deepgram TTS integration guide | LiveKit Docs | Deepgram TTS integration guide | LiveKit Docs | Pipeline nodes and hooks | LiveKit Docs | Pipeline nodes and hooks | LiveKit Docs