Hey, I’m building a custom assistant with Raspberry Pi & local mic streaming, but I don’t have Voice Agent mode access in my dashboard. Can you enable it for my org? Do u recommend an other approach?

Hi there! 👋 I'm unable to directly enable Voice Agent mode access for your organization as I don't have the ability to make account changes. However, I can definitely help with alternative approaches for building your custom assistant with Raspberry Pi and local mic streaming! Based on the information I found, here are some alternative approaches you could consider: ### Setting up a local server You can create a local HTTP server to handle knowledge base requests, allowing your assistant to access information locally. According to [this discussion](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1341914745661554788), VAPI will send requests to your server with the conversation context, and your server can return relevant documents or direct responses. ### Using SIP calls with a custom assistant You can utilize SIP calls by setting

assistantId

to

null

and

serverUrl

to your server's URL. As mentioned in [Vapi's SIP documentation](https://docs.vapi.ai/advanced/sip), you can use SIP softphones to connect to the Assistant without requiring authentication or SIP registration. ### Integrating with Raspberry Pi and wake word detection You can integrate VAPI into a smart speaker setup using your Raspberry Pi and explore wake word detection systems (like Porcupine, OpenWakeWord, or Snowboy) to trigger voice interactions, as suggested in [this thread](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1342131253671100427). ### Other approaches: - Attach a custom LLM to an existing assistant in Vapi - Adjust assistant settings like

onNoPunctuationSeconds

- Start with text-based interaction and opt into voice later - Use alternative voice providers like OpenAI or RimeAI For building with Raspberry Pi specifically, you'll want to: 1. Define the purpose of your assistant 2. Choose the right technology stack 3. Design the interaction flow 4. Develop the voice agent 5. Integrate with a Voice API

raspberry pie integration, sounds like a cool project

Message marked as helpful by @slim! 🎉

Hey Slim, checking if this is resolved for you ?