Daily
@trydaily
Followers
5K
Following
2K
Media
486
Statuses
2K
Build human and AI ultra low latency conversations. We maintain Pipecat with contributions from the developer community. https://t.co/tFy0gFjmb1 https://t.co/sLtBYxhhch
Joined October 2014
Some of our secondary services like Docs and Dashboard are being affected by the ongoing AWS us-east-1 outage. Core calling functionality seems to be unaffected. Unfortunately, like many other teams, it's also affecting our ability to log in to Statuspage. We'll do our best to
1
0
4
If you're in London on Thursday, head over to AI After Hours and hang out with our friends at @encord_team. Pipecat core contributor @JonPTaylor is on the panel, so there will lots of good discussion about latency, voice AI, and enterprise agent workflows!
1
6
7
Evals are a top priority for voice AI teams. We're excited to have @cekuraAi as a partner to the @pipecat_ai developer community! ⚒️
📣 Excited to announce our partnership with @pipecat_ai by Daily! Run automated simulations via WebRTC, inspect every tool call on @cekuraAi , and pass production calls in Pipecat format. 👉🏻 Learn more:
1
2
2
Come hang out with Google engineers at @ycombinator on Saturday, plus engineers and founders from @boundaryML, @covaldev, @langfuse, @heytavus, and @trydaily. Hackathon prizes include a guaranteed YC interview, and the opportunity to present what you're doing with Gemini to the
Build multimodal apps with the Gemini Live API and @pipecat_ai in the special voice and real-time AI hackathon on October 11 👇
1
5
19
We're at VapiCon today! 1:10p PT @kwindla is talking Foundations of Voice AI — Components and Benchmarks. Looking forward to the panel discussion with @dan_goosewin, Anoop Dawar, @amontill @DynamicWebPaige
0
1
5
Voice and multimodal AI Hackathon at @ycombinator on October 11th. Engineers from @trydaily and the @pipecat_ai core team will be there. Join us to build something new, learn from other fun people, and win prizes like a guaranteed Y Combinator interview!
7
10
35
After the first episode of Pipecat TV, it’s been hard to go unnoticed outside 😅. It went so well that we couldn’t resist recording a second one. In this new episode we talk about the new Smart Turn v3 model! https://t.co/2rtf8JXR9q
@pipecat_ai
0
4
5
Training weight and inference code
github.com
Contribute to pipecat-ai/smart-turn development by creating an account on GitHub.
1
0
0
SmartTurn v3. Build voice agents with better turn detection — updated: Now with CPU inference in 12 ms. Native audio semantic VAD. Model weights and all data sets on @huggingface
1
0
4
Livestream - London Voice AI Meetup, link in thread. Demos, talks, conversation from @GoogleDeepMind @Speechmatics @heytavus @pipecat_ai 🙌
1
2
2
🙌 Today - Voice AI Meetup, 6:30p in London, at the new @Speechmatics office. ⚡️ Open Source UI Kit demo from Jon @kwindla 🏎️ Ian @GoogleDeepMind race car demo with the Live API ⚒️ Advanced STT, with multi-speaker diarization @uberboffin 🔥 Dr. Ioannis Patras on the
1
3
6
This macOS local voice agent repository from @kwindla with @pipecat_ai via @trydaily is the only local voice stack I’ve tried that 'just works' out-of-the-box. It even supports interruptions (see video)! I got this pointing to gpt-oss hosted by @ollama, and it works flawlessly.
@boustta_mo @trychroma @modal_labs @trydaily Here's voice agent code that runs entirely locally on macOS: https://t.co/wUAxAflaCY Models you can run locally are getting better and better. You still need a pretty high-end machine to run an LLM that's good at conversation and tool calling. In my opinion, the ~30B parameter
1
8
23