Nomono opens its spatial audio engine to developers and AI agents
What's the deal? Norwegian audio-tech company Nomono has launched the Nomono Platform, an alpha API and MCP server that opens the speech-enhancement and spatialization engine behind Nomono Studio to developers, producers, and AI agents. It is the first product from Nomono Labs, a new initiative to extend the company's technology beyond its own hardware. Producers upload lavalier tracks and an ambisonics recording, and each speaker comes back separated, cleaned, and placed where they stood in the room.
How it works: The same processing chain behind every Studio recording isolates and cleans each voice to broadcast loudness standards, measures each speaker's position from the ambisonics recording, follows movement, and reports who speaks when. Outputs include stereo and binaural mixes, plus spatial audio masters in the Dolby Atmos, EBU, and IAMF profiles that open directly in DaVinci Resolve or Pro Tools. The company says the work can take sound engineers up to two days by hand; the Platform does it in minutes.
Why now? Immersive video has improved fast, but audio has not kept pace. A typical shoot records an ambisonics sound field plus a lavalier mic per person, yet none of those files say where anyone stood.
What's the endgame? Through Nomono Labs, the company plans to extend the same engines to post-production tools, archives, and voice-AI products. Most speech models train on synthetic data — clean speech with simulated noise added on top. Nomono's bet is that models built on real-world speech in real rooms will outperform those built on approximations.
The Platform works with third-party gear. At launch it accepts any lavalier kit alongside a Sennheiser AMBEODealroom has a profile for this one. Try Dealroom → or Zoom H3-VRDealroom has a profile for this one. Try Dealroom → ambisonics microphone, with more arrays to follow. Developers reach it through an HTTPS and JSON API, while the MCP server gives the same capabilities to agents such as Claude, ChatGPT, and Cursor.
"We built this chain for our own hardware and run every Studio recording through it," said Jimmy Brodd, VP engineering at Nomono. "Opening it up means any recorder, any lav kit, and any AI agent can use the same engine, and every improvement reaches all of them at once."
Founded in 2019 as a SINTEF Digital spinoff, Nomono paired four wireless wearable microphones with a central spatial recorder and cloud-based dialogue processing. The company demonstrated the new workflow at Immersive Warsaw on November 5, 2026.
The signal: The launch follows a broader move to make audio tools reachable through AI agents, with Suno introducing an MCP beta in late October and Descript demonstrating agent-driven editing. Nomono's distinction is its focus on production audio, offering a potentially useful distribution shift. But the offer remains a limited alpha, free for now, with commercial pricing and wider availability unannounced.
Read more: nomono.co
Image credit: Nomono
