I'm looking for a long-form video editor, ideally starting today. Need the video cut with good pacing and ideally some motion graphics. Budget's solid. Comment a recent edit please. VIDEO NEEDS TO BE DONE ASAP.

Hey @philipkiely do thinking models like GLM-5 or Kimi K2.5 actually perform any reasoning before their response on Baseten? I'm not seeing any thinking tokens come through, and the TTFT is suspiciously good 😄

Looking for a graphic designer - For a LinkedIn carousel Need someone with solid design experience. Really like the work that Framer designers put out - always quality stuff. Drop your portfolio in the comments or shoot me a DM.

RAG is arguably the single most critical piece for building truly useful AI Voice Agents But if RAG is so crucial… Why are there so many people struggling to use it correctly And more importantly how can we ensure we deploy ours effectively? The reality is… Truly effective RAG for voice isn’t just about finding relevant documents It demands optimising for extreme low latency and conversational flow Getting this wrong leads to those awkward silences during tool calls Or completely off topic answers that kill conversations The solution… The “Scenarios” RAG method I made a detailed video on why it’s better, how it works and how to implement it Watch here: youtu.be/Lkr8jjeGMEo

Looking for a video editor again Willing to pay good money 💰 Need a 10min video edited ASAP (less animations) And a 2 min intro (animations, 10/10 editing) (will need 2 separate people for these roles) Send me your edits to dm's please

Cartesia recently released Sonic 2.0 Which they claim is the top-performing model in blind tests. Preferred 1.5x more than their closest competitor (11labs) I created a video showing how to use this new model Vapi and also doing my own comparison of the models ability with ElevenLabs. You can check it out here: youtu.be/QSHxC9RRjqs

Looking for a video editor again Willing to pay good money Need a long form video edited ASAP Send me your edits to dm's please

Sesame’s new CSM (Conversational Speech Model) is one of the biggest developments in AI speech we’ve seen in a while. It's the most human sounding ai voice yet (in my opinion), pausing, laughing, shifting intonations and even changing pronunciations based on the conversation history. I made a video going through what I learned about Sesame and their new model from their research article. If you want to watch that you can find it here: youtu.be/X8zZOBrrxYc

Thank you for all the DM's however I'm no longer looking for an editor. Thank you to @Justiinstudios for editing the intro to my video. If you want to see what he cooked you can watch it here: youtu.be/b2dTfxnyMvw

Looking for a video editor. Willing to pay good money. Needs to be available for a quick 1st project now!

just posted a video, building a restaurant voice AI system from scratch. I switched up the video style a bit so that literally no part of the process was gatekeeped

Recently, I had an issue with one of our AI voice agent's extremely slow response, this was due to loud and clear background noise of someone talking (the system believed it should be "listening" not "talking"). To improve how this issue was being handled, I needed to replicate the exact audio from the failed call. So I found a method where I could use the phone call recording and pass that in as my input audio to any Voice AI platform. I wanted to share it in my recent video as it might be valuable to anyone else developing in the Conversational AI space. Watch here: youtube.com/watch?v=iZOmULVV…

If you’re building complex AI voice systems and fighting reliability issues, here’s your problem: unfocussed tokens. The fix? The Focussed Token Principle → Only pass what’s needed now. Cut the rest. Multiple small surgical prompts = faster, cheaper, more reliable LLM responses. Changed the style of this video to dive deeper into how it works, why it works so well and how you can use it in practice. Watch here: youtube.com/watch?v=Q8sW3hmx…

Recently 11Labs released their Conversational AI, combining STT, LLMs, and TTS models to enable the creation of AI Voice Agents. - It supports 32 languages and has a native integration with Twilio for phone deployment - All of this on paper makes it extremely good but... I think there are few things needed to be mentioned about it in practice. Would a video about this be useful?

I made a video on why I believe AI phone calls are the future. I also explain why I'm so bullish on Voice AI, and by giving you the facts, why I believe you probably should be too. Check it out here: youtu.be/E8mC96pY66o?si=nSjb…

Having built countless Voice AI Agents - from basic voice chatbots to complex multi-agent systems. I've faced a fair share of failures and technical challenges along the way. So I decided to share the 5 most common mistakes I made. Watch here: youtu.be/aYqXtYwNEXE?si=S8r_…

Freelance AI Developer Opportunity at Artilo AI Position: AI Developer (Voice AI & Prompt Engineering Specialist) - Freelance Hello all 👋🏼, we're seeking an exceptional freelance talent for our innovative Voice AI projects. Key Requirements: • Expert in prompt engineering and voice AI development • Proficient with Voice AI platforms like Vapi, Sindarin or Retell • 1+ years of AI development experience • Skilled in designing prompts for voice-based AI applications • Capable of integrating voice AI into client systems Ideal Candidate: • Passionate about AI advancements • Available for significant project commitment • Thrives in dynamic environments We Offer: • Cutting-edge Voice AI projects • Direct collaboration with our team and clients • Flexible freelance work with long-term potential If you're interested please contact me directly on Twitter

Will OpenAI's Realtime API kill Voice AI platforms like Vapi? Thats a question many are asking. So I made a new video comparing the two. Which one comes out on top? Watch to find out and decide for yourself: youtube.com/watch?v=58NWN90X…

If you don't measure Voice AI latency, you're at a disadvantage. I've developed a tool to accurately measure Voice AI latency. In my new video, I share: 1. Why standard VAPI latency estimates are inaccurate 2. How my tool works 3. The full code for the tool Watch here: youtu.be/4Gz_pQYaV14?si=PQdm…