Particle Launches Radar to Make Podcasts Searchable and Accessible to AI Agents

Particle, the AI newsreader startup founded by former Twitter engineers, launched Radar in August 2026 — a podcast search engine that transcribes and analyzes more than 130,000 podcasts, making their content searchable on the web and accessible to AI agents via an API and MCP.

Radar indexes all Apple Top 200 podcasts across 135 verticals, adding 20,000 episodes to its index daily. Transcriptions include speaker labels and rich metadata, with the platform identifying entities such as people, companies, brands, products, and topics. Users can extract timestamped clips, track entity mentions across podcasts, and receive alerts via email, Slack, or webhook. A dedicated podcast ads search engine is also included, along with tools for political bias analysis, chart rankings, audience size estimates, sponsorship data, and brand suitability scoring.

Particle co-founder and CEO Sara Beykpour said hedge funds have been the platform’s highest-volume API customers, drawn to data their own agents cannot access. AI search platforms and data resellers are also among top-paying customers, and search API provider Exa is listed as a partner.

The product grew out of a feature in Particle’s news-reading app that surfaced podcast clips alongside related news stories. As interest in AI agents grew, the company decided to build a standalone API around that capability. “Agents are generally blind to audio; they can’t see it unless something or someone has transcribed it,” Beykpour said.

Radar is priced at $29 per month per seat, with a $399-per-month business plan covering 20 seats. API access is available at custom pricing. The company says it plans to expand beyond podcasts to include YouTube videos and news clips.

The launch suggests a broader opportunity in audio intelligence, a category largely overlooked by web-crawling AI services that focus on text.