... call over WhatsApp, SMS or email. The user completes the structured input while they're still talking to the agent, and the response comes back into the conversation. It works as a tool inside your existing voice stack including Vapi, Retell, ElevenLabs and LiveKit. The idea is simple: Voice-first, not voice-only. We're launching @VocaLoop on Product Hunt and would genuinely love feedback from other people building voice agents. What information have you found hardest to collect reliably ...

... just launched @Dograh , the open-source alternative to Retell and Vapi

... Series B Comment from Remus Savu(@remus_savu): Congrats !! Comment from Ivan Stakhov(@ivan_stakhov): Congrats on the raise, team Comment from Blake at Vassant(@blakeatvassant): Congratulations!! Comment from Brad Holland(@bradholland): Wow! So cool Congratulations Vapi!! Comment from Robert Douglass(@robert_douglass): Congratulations! I used Vapi

... than v2. 12+ languages Interruption Prediction v1 first audio-only model that tells "mhm, keep going" from "wait, stop." Under a second, under 6% false positives Signal Detectors real-time TTS detection, gender, accent classification Already running inside Daily, Vapi, LiveKit, and some of the largest AI labs. 3.5x better turn-taking, 50% fewer dropped calls. All new models bundled at existing pricing. Would love your thoughts. Happy to go deep on any of the technical details ... ... very real production problem for voice agents. The jump from silence-based turn detection to rhythm/context-aware turn prediction feels especially important, because most awkward AI calls break when the agent interrupts too early or waits too long. The mhm vs

... give him a character,  and ehhh, you can describe it, prompt it, but you need to test it every time. Until you meet Riley. The right balance, between interested and punchy. All this is possible thanks to @Vapi Try it on zoom or Gmeet with Riley. And please give us your feedback. What the thing that made your onboarding easier? Did you already do an interview with AI ? Comment from Bengeekly(@bengeekly): @saad_el_gueddari  Riley is fully ...

... product and your target audience by showing how easy it is to use through relatable, real-world scenarios that help people see how it fits naturally into their workflow. I have experience working with AI agents using tools like Vapi and Retell, and with automation platforms such as Make, n8n, Apollo, and Salesforce. That hands on experience helps me create content that doesn t just show features, but demonstrates how people can actually use the product in their ...

... community templates save hours of setup time, and the AI workflow builder is genuinely useful for complex automations. Make (formerly Integromat) - When you need granular control over data transformations, Make shines. The scenario editor is more powerful than most alternatives, and the pricing scales better for high-volume workflows. What I've learned: The best automation tool depends on your specific stack and technical comfort level. Zapier for simplicity and reliability, n8n for customization and cost control, Make for complex ... ... tools that tend to stick are the ones that reduce operational friction without needing constant oversight: Zapier / Make for dependable glue work across tools Grain-style meeting transcription tools that reliably turn calls into summaries and clear next steps Vapi

... system-level hooks But: Those improvements may also pull voice input deeper into apps , creating opportunities for third-party tools to power native voice experiences. Voice Agents are becoming Infrastructure There s a growing ecosystem underneath all of this: @Vapi @Pipecat @LiveKit @Coval This is the voice agent infra layer, a category we ll cover in later Orbit Awards. Comment from Aaron O'Leary(@aaronoleary): @jannik_jung  Looks cool! Interesting approach using the native mac framework! Have you noticed ...

... noticed two main narratives in how companies view their competitors. Either it s a fight to the death approach exactly like what we see between Replit and Lovable (though it seems Replit does more of the provoking ) basically: We speak badly about our competition. Or it s more motivational: We speak positively about our competition. Tho I do not know whether I have seen some example of this competition, I can see it only in terms of personal branding when ... ... people do not want to say bad things about someone, even when they are competitors

... With these two developer-focused voice app launches today, we should have a bakeoff to see which one rules...! https:// ...

... Voice AI experts from OpenAI, Google, NVIDIA, AWS for Zoom sessions (or watch them async). $10k in credits from Baseten, Cartesia, Cerebrium, Coval, Daily, Deepgram, fal, Fireworks AI, Freeplay, Gladia, Layercode, mem0, Modal, OpenPipe, PlayAI, Rime Labs, Tavus, Ultravox, Vapi, and Weights & Biases. Special Product Hunt deal through this link ($200 for the course, discounted from the $500 full price): https://maven.com/pipecat/voice-... Rajiv Ayyangar, CEO of Product Hunt, is hosting a session about launching well and building community ...

... recently talking with a group of founders, and we went around sharing tools we're using now. Posting my notes for our community here - would love to know what else people are using! Voice AI toolkit: - Vapi - Pipecat (open source) Meeting notes without a bot: - Granola Fast voice input (stop typing!) - Wispr Flow - Aqua -  (newer, has contextual awareness) Agentic coding assistants: - Cursor - Windsurf (getting tons of traction, especially w/ early startups) - Devin - has way fewer reviews and shoutouts ... ... coding and @OpenAI 's o3-mini when speed matters see this thread @v0 by Vercel Comment from Reid Kimball(@reid_kimball): Great list! I ve heard of some and some are new I want to check out like Granola, Vapi

... behavior change for me in the last few months - with @Aqua Voice / @Wispr Flow I type 50% less. Plus the building blocks for voice AI are getting really good (e.g. RTC @Daily.co / open source orchestration @Pipecat / voice agent platform @Vapi / evals for voice agents @Coval ) I'm also super bullish on design founders, especially since the human-AI interface landscape is currently pretty primitive. I think we need to break out of the chat/autocomplete UX paradigm. Also, personal finance ...

... excited to share that Vapi.ai is LIVE on @Product Hunt! Vapi is the platform to build, test, and deploy voice agents in minutes rather than months. We have a community of over 150,000 developers and have powered 44,000,000 calls! We are looking forward to gathering feedback and insights through our launch, and would really appreciate your support! Please drop any suggestions or callouts in the comments. https://www.producthunt.com/post... ...

... really enjoyed this breakdown by @raphaelschaad and @aaron_epstein (YC partner): They walk through some cutting edge AI apps: @Vapi - voice api for devs @Retell AI - build voice agents @Gumloop - AI zapier @AnswerGrid - outbound research @Polymet - AI product designer Zuni - ai in your chrome sidebar and @Argil - video clone generation They talk about some recurring themes: - When prompts take a long time, give the user something engaging to do while they're waiting. - Canvas is a powerful ...

... everyone, One year ago, we launched on this platform with a vision to transform voice AI. Today, Vapi has grown to 100,000+ developers and recently raised our $20M Series A. Voice AI has reached its tipping point. We're seeing hundreds of startups, agencies, and developers building innovative voice solutions for enterprises and SMBs on Vapi

... amanamals): @rajiv_ayyangar check http://speaktheglobe.com , I have implemented Realtime API with Google Maps Comment from Raghav Gupta(@raghav_gupta22): @kwindla Thanks for the answer Comment from Rajiv Ayyangar(@rajiv_ayyangar): Great question - maybe someone like @jordan_dearsley from @Vapi or @kwindla from @Daily.co / @pipecat could weigh in? I think the non-openAI infra for realtime AI has progressed really fast, so maybe there are just better, cheaper, more flexible building blocks outside of the Realtime API? Comment from Rajiv ... ... where the capabilities of the core models are complemented by the recent progress in the orchestration layer. As a side note, it's cool to see how collaborative and fast-moving the companies in the space are. E.g. Vapi