Every caller on the show is a one-of-a-kind character — generated in real time by a custom-built AI system. Here's a peek behind the curtain.
Every caller starts as a blank slate. The system generates a complete identity: name, age, job, hometown, and personality. Each caller gets a unique speaking style — some ramble, some are blunt, some deflect with humor. They have relationships, vehicles, strong food opinions, nostalgic memories, and reasons for being up this late. They know what they were watching on TV, what errand they ran today, and what song was on the radio before they called.
Some callers become regulars. The system tracks returning callers across episodes — they remember past conversations, reference things they talked about before, and their stories evolve over time. You'll hear Carla update you on her divorce, or Carl check in about his gambling recovery. They're not reset between shows.
And some callers are drunk, high, or flat-out unhinged. They'll call with conspiracy theories about pigeons being government drones, existential crises about whether fish know they're wet, or to confess they accidentally set their kitchen on fire trying to make grilled cheese at 3 AM.
Callers know real facts about where they live — the restaurants, the highways, the local gossip. When a caller says they're from Lordsburg, they actually know about the Shakespeare ghost town and the drive to Deming. They know the current weather outside their window, what day of the week it is, whether it's monsoon season or chile harvest. They have strong opinions about where to get the best green chile and get nostalgic about how their town used to be. The system also pulls in real-time news so callers can reference things that actually happened today.
Some callers have a problem — a fight with a neighbor, a situation at work, something weighing on them at 2 AM. Others call to geek out about Severance, argue about poker strategy, or share something they read about quantum physics. The system draws from over 570 discussion topics across dozens of categories and more than 1,400 life scenarios. Every caller has a purpose, not just a script.
Luke talks to each caller using push-to-talk, just like a real radio show. His voice is transcribed in real time, sent to an AI that responds in character, and then converted to speech using a voice engine — all in a few seconds. The AI doesn't just answer questions; it reacts, gets emotional, goes on tangents, and remembers what was said earlier in the show. Callers even react to previous callers — "Hey Luke, I heard that guy Tony earlier and I got to say, he's full of it." It makes the show feel like a living community, not isolated calls.
When you dial 208-439-LUKE, your call goes into a live queue. Luke sees you waiting and can take your call right from the control room. Your voice streams in real time — no pre-recording, no delay. You're live on the show, talking to Luke, and the AI callers might even react to what you said. And if Luke isn't live, you can leave a voicemail — it gets transcribed and may get played on a future episode.
Listeners can send emails to submissions@lukeattheroost.com and have them read on the show. A background poller checks for new messages every 30 seconds — they show up in the control room as soon as they arrive. Luke can read them himself on the mic, or hit a button to have an AI voice read them aloud on the caller channel. It's like a call-in show meets a letters segment — listeners who can't call in can still be part of the conversation.
The entire show runs through a custom-built control panel. Luke manages callers, plays music and sound effects, runs ads, monitors the call queue, and controls everything from one screen. Audio is routed across multiple channels simultaneously — caller voices, music, sound effects, and live phone audio all on separate tracks. The website shows a live on-air indicator so listeners know when to call in.
During every show, the system records five separate audio stems simultaneously: host microphone, AI caller voices, music, sound effects, and ads. Each stem is captured as an independent WAV file with sample-accurate alignment. This gives full control over the final mix — like having a recording studio's multitrack session, not just a flat recording.
Once the show ends, a 15-step automated pipeline processes the raw stems into a broadcast-ready episode. Ads and sound effects are hard-limited to prevent clipping. The host mic gets a high-pass filter, de-essing, and breath reduction. Voice tracks are compressed — the host gets aggressive spoken-word compression for consistent levels, callers get telephone EQ to sound like real phone calls. All stems are level-matched, music is ducked under dialog and muted during ads, then everything is mixed to stereo with panning and width. A bus compressor glues the final mix together before silence trimming, fades, and EBU R128 loudness normalization.
A single command takes a finished episode and handles everything: the audio is transcribed using MLX Whisper running on Apple Silicon GPU to generate full-text transcripts, then an LLM analyzes the transcript to write the episode title, description, and chapter markers with timestamps. The episode is uploaded to the podcast server, chapters and transcripts are attached to the metadata, and all media is synced to a global CDN so listeners everywhere get fast downloads.
No manual editing, no scheduling tools. After each episode, an LLM reads the full transcript and picks the best moments — funny exchanges, wild confessions, heated debates. Each clip is automatically extracted, transcribed with word-level timestamps, then polished by a second LLM pass that fixes punctuation, capitalization, and misheard words while preserving timing. The clips are rendered as vertical video with speaker-labeled captions and the show's branding. A third LLM writes platform-specific descriptions and hashtags. Then clips are uploaded directly to YouTube Shorts and Bluesky via their APIs, and pushed to Instagram Reels, Facebook, and Mastodon — six platforms, zero manual work.
Episodes are served through a CDN edge network for fast, reliable playback worldwide. The RSS feed is automatically updated and picked up by Spotify, Apple Podcasts, YouTube, and every other podcast app. The website pulls the live feed to show episodes with embedded playback, full transcripts, and chapter navigation — all served through Cloudflare with edge caching. From recording to available on every platform, the whole pipeline is automated end-to-end.
Every conversation is improvised. Luke doesn't know what the caller is going to say. The AI doesn't follow a script. It's a real conversation between a human and an AI character who has a life, opinions, and something on their mind.
This isn't an app with a plugin. Every piece — the caller generator, the voice engine, the control room, the phone system, the post-production pipeline, the publishing automation — was built specifically for this show.
Everything happens live. Caller generation, voice synthesis, news lookups, weather checks, phone routing — all in real time during the show. There's no post-production trickery on the caller side. What you hear is what happened.
Callers aren't isolated — they hear what happened earlier in the show. A caller might disagree with the last guy, back someone up, or call in specifically because of something another caller said. The show builds on itself.
Every episode runs through a 15-step post-production pipeline: stem limiting, high-pass filtering, de-essing, breath reduction, spoken-word compression, telephone EQ, level matching, music ducking with ad muting, stereo imaging, bus compression, and EBU R128 loudness normalization.
From recording to your podcast app, the entire pipeline is automated. Post-production kicks off when the show ends, then a publish script handles transcription, AI-generated metadata, chapter detection, CDN sync, and RSS distribution — all with a single command.
Want to hear it for yourself?
Listen to Episodes