# Building Voice AI Agents That Don’t Suck with Kwindla Kramer - #739

Page: https://stenobird.com/podcast/twiml-ai-podcast/building-voice-ai-agents-that-don-t-suck-with-kwindla-kramer-739
Text version: https://stenobird.com/podcast/twiml-ai-podcast/building-voice-ai-agents-that-don-t-suck-with-kwindla-kramer-739.md
Podcast: [The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)](https://stenobird.com/podcast/twiml-ai-podcast)
Published: 2025-07-15T21:04:00+00:00
Episode link: https://twimlai.com/podcast/twimlai/building-voice-ai-agents-that-dont-suck/
Audio file: https://pscrb.fm/rss/p/traffic.megaphone.fm/MLN9079687304.mp3?updated=1752614441
Processing state: failed
JSON: https://stenobird.com/v1/public/podcasts/twiml-ai-podcast/episodes/building-voice-ai-agents-that-don-t-suck-with-kwindla-kramer-739
Duration seconds: 4382

## Resource

In this episode, Kwindla Kramer, co-founder and CEO of Daily and creator of the open source Pipecat framework, joins us to discuss the architecture and challenges of building real-time, production-ready conversational voice AI. Kwin breaks down the full stack for voice agents—from the models and APIs to the critical orchestration layer that manages the complexities of multi-turn conversations. We explore why many production systems favor a modular, multi-model approach over the end-to-end models demonstrated by large AI labs, and how this impacts everything from latency and cost to observability and evaluation. Kwin also digs into the core challenges of interruption handling, turn-taking, and creating truly natural conversational dynamics, and how to overcome them. We discuss use cases, thoughts on where the technology is headed, the move toward hybrid edge-cloud pipelines, and the exciting future of real-time video avatars, and much more. The complete show notes for this episode can be found at https://twimlai.com/go/739.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/twiml-ai-podcast/episodes/building-voice-ai-agents-that-don-t-suck-with-kwindla-kramer-739/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/twiml-ai-podcast/building-voice-ai-agents-that-don-t-suck-with-kwindla-kramer-739.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.