Hey there, what’s the best setup for Google STT (

latest_long

for pl_PL),

gemini-2.5-flash-live-preview

for Realtime model and TTS from elevenlabs? It looks like Elevenlabs stops in the middle of greeting and I’m not sure I configured that correctly.

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

Elevenlabs, just like this one

tts=elevenlabs.TTS(
            voice_id="gFl0NeqphJUaoBLtWrqM",  # Piotr Pro
            model="eleven_multilingual_v2",
            voice_settings=elevenlabs.VoiceSettings(speed=1.0, stability=0.8),
        ),

I'm here to help you with the issue of ElevenLabs TTS stopping mid-greeting. Let's try a few steps together to get things running smoothly: 1. Increase the inactivity timeout: Sometimes, longer greetings might get cut off if the timeout is too short. You can adjust the

inactivity_timeout

parameter to give your greetings more time. Here's an example:

tts = elevenlabs.TTS(
    voice_id="gFl0NeqphJUaoBLtWrqM",  # Piotr Pro
    model="eleven_multilingual_v2",
    voice_settings=elevenlabs.VoiceSettings(speed=1.0, stability=0.8),
    inactivity_timeout=300  # Set to 300 seconds or higher
)

1. Check SSML formatting: If you're using SSML tags, it’s important to make sure they’re correctly formatted. Sometimes incomplete tags like

<phoneme>

or

<break>

can cause interruptions. 2. Verify the API key: Double-check that your

ELEVEN_API_KEY

is properly set, either as a parameter or an environment variable, so the service can authenticate correctly. 3. Inspect network and connection options: Network hiccups can affect streaming, so ensuring a stable connection and maybe increasing connection timeout values can really help, especially if you’re in a high-latency environment. 4. Test with minimal configuration: To pinpoint the issue, try simplifying your setup with some example code. This can help identify if the problem is with the configuration or integration logic. Please don’t hesitate to reach out if you want me to walk you through any of these steps or if you have other questions. I’m here to support you! Sources: livekit-plugins/livekit-plugins-elevenlabs/livekit/plugins/elevenlabs/stt.p... | examples/src/restaurant_agent.ts | pipeline-tts/elevenlabs_change_language.py

Got it, I had to increase Elevelabs tokens per month is my 11labs configuration 🙂

I'm so glad to hear that increasing the ElevenLabs tokens helped resolve the issue! If you have any more questions or need a hand with anything else, please don't hesitate to reach out. We're here to help!