Nomono Opens Speech-Enhancement Pipeline to Broadcasters via API

Norwegian audio technology company Nomono has released an alpha API and MCP server that opens the speech-enhancement pipeline behind its Nomono Studio recorder to broadcasters, production companies and developers.

The product, called Nomono Labs, targets immersive and broadcast production. It handles the full location workflow: crews record multiperson interviews on site, upload each speaker's lavalier track together with an ambisonics recording, and receive every voice separated, cleaned and normalized to broadcast-loudness standards.

What does Nomono Labs actually deliver?

The platform outputs stereo and binaural mixes, or ADM masters in the Dolby Atmos, EBU and IAMF profiles — the three formats that matter for next-generation broadcast and streaming audio in Europe and beyond. ADM, the Audio Definition Model, is the EBU-standardized metadata framework that carries object-based and immersive audio through production and distribution chains.

At launch the system accepts any lavalier kit alongside either a Sennheiser AMBEO or a Zoom H3-VR ambisonics microphone. Nomono said more microphone arrays will follow. That is a deliberately narrow hardware entry point: two ambisonics capture devices, but an open door on the lavalier side, which lowers the barrier for broadcasters with existing inventory.

The company described the processing architecture in a statement: "Five products (Separation, Enhancement, Spatialization, Analysis and Delivery) run on the same processing chain already behind every Nomono Studio recording."

What does each stage do?

According to Nomono, the pipeline:

• isolates and cleans each voice to broadcast loudness standards;
• measures each speaker's position from the ambisonics recording;
• follows speakers as they move during the interview;
• reports who speaks, and when, across the timeline.

That last capability — automated speaker diarization tied to spatial position — is the part that changes post-production economics. Editors no longer need to manually log who spoke on which channel; the metadata arrives with the files.

Outputs include processed and unprocessed files per microphone, stereo and binaural mixes, and spatial audio master files. Those masters open directly in video editing tools such as DaVinci Resolve or digital audio workstations such as Pro Tools, which means the immersive deliverable slots into existing edit suites rather than demanding a separate mixing stage.

Commercial reality versus vendor pitch

Two qualifiers deserve attention. First, this is an alpha release. Nomono has not published pricing, availability windows or service-level terms for the API, so broadcasters evaluating integration should treat the current capability set as provisional. Second, the company's own positioning rests on the processing chain's track record inside Nomono Studio, its hardware recorder — an installed-base claim, not an independently benchmarked figure.

What is verifiable from the announcement: the five-stage chain exists, the supported capture devices are named, and the output formats cover the three ADM profiles that broadcasters and streamers increasingly require for immersive programming. The IAMF profile, in particular, points toward streaming delivery, since IAMF is the Immersive Audio Model and Formats standard adopted for next-generation online video.

Why this matters now

For production teams, the practical change is consolidation. Location recording, voice separation, loudness compliance, spatialization and speaker tracking have typically required separate tools and specialists. Nomono Labs compresses that chain into one upload-and-retrieve pipeline with machine-readable outputs.

The move also signals where audio vendors see the market heading: toward API-first services that plug into broadcaster workflows rather than closed appliances. An MCP server alongside the API suggests Nomono expects AI agents and automated pipelines to become legitimate clients of professional audio processing — a notable bet for a company whose roots are in purpose-built recording hardware.

Nomono said additional microphone arrays will gain support as the alpha progresses, giving prospective users a concrete milestone to watch as they assess whether the pipeline can move from alpha to production-grade deployment.