What is Somia Buds? AI-native earbuds for wellbeing in motion

Somia™ Buds are personal AI-native earbuds developed by yeshcube for access to Somia experiences while traveling, during moderate physical activity and in moments of individual listening. They integrate sound playback, voice capture and acoustic-environment management, and they serve Somia Sensory and Somia Immersive sessions from an account linked to Somia App, with the phone as the connection to the artificial intelligence core. These AI-native earbuds for wellbeing experiences in motion are at the ideation stage: the industrial design, the battery life, the controls, the price and the commercial release date are determined in the stages that follow.

The ERL scale (Evidence Readiness Level) measures the evidence maturity of a solution across six levels, from the initial hypothesis (ERL-0) to consolidated impact (ERL-5).

The problem: the personal experience outside a controlled space

A voice and sound experience changes when it happens while walking, running, traveling or in a shared space. Noise, wind, movement and the need to stay aware of the surroundings shape both what is heard and what the system captures.

Four concrete difficulties follow from that. The first is keeping playback intelligible when the noise level changes from one minute to the next. The second is capturing voice in motion, with wind and physical effort interfering. The third is switching between isolation and awareness of the surroundings according to what the person is doing. The fourth is holding the continuity of the session without resorting to a screen.

The design principle that answers all four is a personal audio and voice interface that supports both static listening and activity, with explicit control of the acoustic environment.

Design requirements

Five requirements follow from that problem, and they govern the design of Somia Buds:

• Stable mobility: the fit holds during walking, running and everyday journeys.
• Configurable acoustic management: the system offers isolation and awareness of the surroundings according to the activity.
• Voice interaction: the microphones capture requests and conversations under variable conditions.
• Personal continuity: the account, the preferences and the authorized session state are administered from Somia App.
• Understandable privacy: microphone activation and its interruption are identifiable and controllable.

Architecture: the earbuds, the application and the Somia core

Somia’s modular character separates what the core provides from what each product resolves. In that division, Somia Buds are the physical listening and capture layer: voice and sound playback, microphones, acoustic-environment management, essential controls, wireless connectivity and charging case.

Somia App provides the linking, the configuration, the personalization and the permissions, and the phone provides the connection. The core provides the experience orchestration, the content, the safety rules and the data governance.

How a session works

Configuration begins in Somia App. The person links the earbuds to their account, sets privacy and preferences, and chooses the acoustic behavior they want to listen with.

The session starts from the application and, once voice activation is validated, by speaking as well. During the experience the earbuds play the sound, capture the voice and hold the chosen acoustic mode, while the phone carries the interaction to the core, which organizes the response according to the mode of use, the safety rules and the authorized data.

At the end, the history, the preferences and the progress synchronize with consent, so an experience begun on another compatible device is resumed when the integration and the permissions allow it.

Modes of experience

Somia Sensory

Somia Sensory brings together pre-recorded sound content for breathing, relaxation, concentration or rest. It fits a pause, a journey or a walk. Content intended for running preserves attention to the surroundings.

Somia Immersive

Somia Immersive uses the system’s conversational artificial intelligence. The microphones capture the voice and the response plays through the earbuds. A session combines conversation, guided prompts and sound content, and noise, wind and physical effort shape when intervening is appropriate.

Acoustic environment

Isolation mode reduces interference in controlled settings. Environmental mode keeps external signals audible during walking, running and everyday journeys. The cancellation system, the degree of transparency and their controls are subject to the technical specification.

Data and privacy

The person controls when the microphones capture voice and which information is linked to their account. The earbuds capture audio during conversational experiences, and Somia App communicates microphone status, manages permissions and allows capture to be stopped. Personalization memories are enabled voluntarily and can be revoked.

Processing is governed by the GDPR and the Spanish LOPDGDD, with Yeshcube Tech, SL as data controller. The applicable framework is published in the Somia privacy policy and in the AI transparency commitment. What the product retains on its own account — audio, transcripts, control events and metadata, with their retention period and purpose — will be declared with its technical specification.

Artificial intelligence models make mistakes, read a request incompletely or produce a response that does not suit the context. Oversight of what happens in a session rests with the person.

Evidence and validation status

Somia Buds hold level ERL-0, initial hypothesis: the wireless format, the connection to Somia, the acoustic-environment management, the modes of experience and the mobility contexts are defined, with no sound, stability, battery-life or outdoor-safety testing.

Still to be determined are the industrial design and the fit, the transducers and the microphones, wind reduction, the cancellation system and the degree of transparency of environmental mode, the wireless protocol and the distribution of processing, the behavior during a loss of connection, the controls for pause, volume and privacy, the battery life, the case and resistance to water and dust. Each one is published with the technical specification that settles it.

Level ERL-1 (proof of concept) requires a prototype that allows evaluation of playback, the microphones, noise cancellation, environmental mode, latency, the connection to Somia App, stability during walking and running, and comprehension of the privacy controls. It will be declared once that evidence is available.

Commercial transfer is conditioned by the hub’s general rule, which requires at least ERL-3 to transfer any solution.

What they are for and what is left out

Somia Buds are intended for personal voice and sound experiences indoors and outdoors: walking, running, travel, commuting, pauses, concentration, rest and private conversation. Environmental mode preserves awareness of relevant signals during outdoor activity.

The product offers non-clinical support. It does not make diagnoses, does not prescribe treatment and does not replace professional care. Left out of its definition are the measurement of physiological variables, the interpretation of sports performance, automatic activity recognition, hearing protection and any guarantee of safety in traffic or against the risks of the surroundings.

Somia Buds take the place of the personal, mobile interface in the ecosystem, with the application as the administration point and the phone as the connection. Their certification under Somia™ Within is conditioned on technical integration. The details of the system behind them are on the Somia site.