South African talk radio is the last big pool of news that nobody can search. Locl is an attempt to change that: a platform that listens to the live streams of the country’s major English-language talk stations, transcribes everything, indexes it and lets you look up any name, brand or subject and find every time it was mentioned on air.

The stations it ingests are 702, Cape Talk, Power FM and SAfm, with plans to include non-English platforms in time.

“I love all things news, and I’ve always loved all things news,” its creator, Shaun Trennery, told TechCentral on Friday. “With the advent of AI, you’re able to get pretty much any information. The only thing that was missing was radio.”

What interested Trennery was not the bulletins. It was the callers, the interviews and the arguments – the part of radio that has never been indexed, and which disappears the moment it is broadcast. Podcast feeds give you whole shows with no way in. “There aren’t any highlights or anything like that.”

Trennery has been writing software for about 25 years. But he built locl without writing any code himself. “It’s 100% Claude Code,” he said. “We’re at the stage now, we’re not even looking at the code anymore.”

The platform took three to four months, built in the gaps of a working day. “While I’m working throughout the day I have an idea, or on my run I have an idea, and then I just give it to AI, and it iterates and it creates a PR (pull request) that I’m able to review and merge in.”

How it works

A listening tool runs per station, capturing the live stream in half-minute chunks. Each chunk goes through Whisper, the open-source speech recognition model, and the text lands in what Trennery calls a massive index. On top of that sits a retrieval layer that lets a language model query the whole corpus.

From there it can assemble show recaps, cut clips and answer questions about what was said, where and how often.

The hard part was dealing with South African dialect and names. Place names, brand names and people’s names came out wrong, in the confident way transcription models get things wrong. “It would hear one thing and then actually write it in its own way that it’s actually understood,” he explained. “Whisper is actually brilliant and it’s highly accurate, but there’s always going to be those issues.”

His fix was unglamorous: for a couple of months he held the system’s hand, watching the headlines, listening to the shows, reading the transcripts and correcting them one term at a time into a lookup library. “That’s a manual process,” he said. He expects it to matter less as the models improve.

The feature with the most obvious life in it is the newest. Locl now records predictions made on air – by hosts and by callers – and goes back afterwards to check whether they came true.

“Who’s going to win this weekend’s game, and who made that call?” Trennery says. “And then after the fact we use AI to go and look up the actual result. Did this actually happen?”

The obvious application is politics. “If you look at what’s happening with the ANC and the local elections – we’re going to win this, or we’re not going to win this. All these events which are likely to happen because the callers or the hosts have actually made those calls. Now we’re able to record those and say, hang on a second, these were correct and these were incorrect.”

Alongside it sits a set of things that would each be a product elsewhere: a daily briefing of what was said across every station, readable or listenable and available by RSS; recaps of individual shows; alerts on any brand or name; a sentiment view showing whether an entity is being spoken about warmly or badly; and a record of which advertisers are buying the most airtime.

Trennery built a hub around the World Cup while it was on and one for the local elections is a couple of weeks away. He also imagines it on a newsroom wall.

Most of it is free and Trennery wants it to stay that way. The commercial idea sits with brands that want the full archive, shared workspaces and reports.

Ingesting the live output of commercial radio stations, transcribing it and building products on top raises an obvious question, and Trennery does not dodge it. “I’ve looked into the copyright issues,” he said. “I’m listening and I’m using that to then create an overview of what happened in that show … I’m hoping I’ve looked into all the legal issues. I think I’m good.”

It is not a settled area, and the stations may take their own view. What he is working from is the exposed streams the broadcasters already publish for their own listeners.

Three tiers

According to the website, locl runs on three tiers:

The free one costs nothing and stays that way: the daily briefing, a search preview and the podcast feed.
Pro is R199/month, VAT included, and adds unlimited search and chat, five keyword alerts by e-mail, shareable audio clips and what Trennery calls ad intelligence — a view of which brands are buying the most airtime.
Team is R999/month for up to eight seats, with unlimited alerts and shared clips, chats and searches. Every account starts on a seven-day Pro trial.

Where he wants to go next is wider. Television news channels are the obvious extension, since the audio is already there. So are other languages, and other English-speaking markets. He has looked at neither yet. – © 2026 NewsCentral Media