dograh VS strawberry

If you like Pipecat’s focus on speed, you might also try out our open source, which comes with all the batteries included (knowledge base, telephony/SIP, variables, BYOK any LLM STT TTS, Speech to Speech, etc )

And it's fully OSS- like n8n for voice AI, and you can use it with OpenClaw or Claude code - recently launched MCPs.Github- https://github.com/dograh-hq/dograh, Youtube -https://www.youtube.com/watch?v=sxiSp4JXqws&list=PLDqzGuN7B1...

I've built voice agents before, but when it came to shipping them for production, I couldn't find a platform that worked quickly in 2 minutes - until we started building Dograh. It's an open-source voice AI platform with a visual workflow builder, built-in telephony, and post-call analytics out of the box. Alternative to Vapi, Retell, and Bland, but self-hostable and BSD-2 licensed. You get a canvas where you connect nodes instead of writing Python, so prompt tweaks don't mean a redeploy. Voicemail detection, call transfer, variable extraction, knowledge base, and CRM connectors all come standard. Same feature set whether you self-host or use the managed cloud. It has native support for BYOK (bring your own key) across every layer. Deepgram or Whisper for STT, ElevenLabs or Kokoro for TTS, and any LLM for the brain. Want to run everything locally? Swap in self-hosted models through the UI, no code required. Check it. https://docs.dograh.com/getting-started Youtube link: https://www.youtube.com/watch?v=sxiSp4JXqws Star the Dograh repo ⭐ → https://github.com/dograh-hq/dograh

We built Dograh OSS, an open-source voice AI platform. When we started, we assumed most failures would come from the LLM - bad answers, missed intent, prompt edge cases. So we spent a lot of early effort there.

The whole setup works on my M2 MacBook Pro with 16 GB RAM. I use Gemma 4B via LiteRT-LM.

I've found that LiteRT-LM has a much lower DRAM footprint than Ollama. I've also made tons of optimizations in the code - for eg, you can do quite a bit with a 16k context window for a voice assistant while managing a good footprint, so I keep track of the token usage and then perform an auto-compaction after a while. I use sub-agents and only do deep-think calls with them, so the context window is separated out. In a multi-turn conversation, if Gemma 4 directly processes audio input, the KV cache fills up within a few turns, so I channel it all via Whisper.

I did not want to use openWakeWord or Picovoice because they had limitations on which wake word you could choose. Alternative was to train a model of my own. So I created my own wake word detection pipeline using Whisper Tiny - works surprisingly well: https://github.com/pncnmnp/strawberry/blob/main/main.py#L143...

Also, I have VAD going with smart turn v3 (like I mentioned above) + I use browser/websocket for AEC + Barge-in (https://github.com/pncnmnp/strawberry/blob/main/audio_ws.py).

I'm using the MacBook's built-in microphones for this, though, and I haven't fully tested it with other microphones. I've been ironing out the rough edges on a daily basis. I should write a quick blog on this too.