Microsoft Automotive United States Company newsroom

Mercedes-Benz

Mercedes-Benz wanted to make its in-car "Hey Mercedes" voice control more intuitive than a predefined-command assistant so drivers and passengers could ask broader, more complex questions and still interact hands-free while driving.

The U.S. focused beta programme is expected to last three months
over 900.000 vehicles equipped with the MBUX infotainment system

Reported impact

Business outcome

Mercedes-Benz gave beta users a more conversational in-car assistant capable of more comprehensive answers, while its developers gained request-level insight to improve voice control and plan rollout to more markets and languages.

  • Customer Experience

Solution

Mercedes-Benz extended its in-car MBUX Voice Assistant with generative AI by integrating ChatGPT through Azure OpenAI Service. MBUX remains the vehicle-facing assistant that receives "Hey Mercedes" voice prompts and delivers responses inside cars equipped with the MBUX infotainment system, while ChatGPT adds large-language-model capabilities to improve natural language understanding and handle broader conversational requests such as destination questions, recipe suggestions, and other complex prompts. The beta is activated over the air for eligible U.S. vehicles, and customers can opt in through the Mercedes me app or directly from the vehicle. Mercedes-Benz states that voice command data is stored in the Mercedes-Benz Intelligent Cloud, where it is anonymised and analysed under Mercedes-controlled IT processes. Developer insights from beta requests are then used to prioritize assistant improvements and shape rollout to additional markets and languages.

Data flow

Drivers speak to the MBUX Voice Assistant in eligible vehicles, which passes conversational requests to ChatGPT through Azure OpenAI Service for richer language understanding and answer generation. Responses are returned to the in-car assistant, while collected voice command data is stored in the Mercedes-Benz Intelligent Cloud, where it is anonymised and analysed for product improvement and rollout planning.

Solution architecture

4 components · 4 layers
  1. Compute
    • ChatGPT Provides large-language-model capabilities that expand natural language understanding and answer broader or more complex user questions.
  2. Storage
    • Mercedes-Benz Intelligent Cloud Stores collected voice command data so Mercedes-Benz can anonymise and analyse requests from the beta programme.
  3. Serving
    • MBUX Voice Assistant Serves as the in-car voice interface that receives driver requests and delivers conversational responses inside the vehicle.
  4. Uncategorized
    • Azure OpenAI Service Hosts the ChatGPT integration with Microsoft cloud security, privacy, and reliability controls for the beta deployment.

Architecture clues

  • Mercedes-Benz says it retains complete control over the IT processes in the background.
  • Mercedes-Benz says voice command data is stored in the Mercedes-Benz Intelligent Cloud, where it is anonymised and analysed.
  • The beta rollout happens over the air for eligible vehicles with MBUX.
  • U.S.-focused optional beta started on 2023-06-16.

Evidence from the source

"An optional beta programme will start June 16, 2023 in the U.S. for over 900.000 vehicles equipped with the MBUX infotainment system."
"ChatGPT complements the existing intuitive voice control via Hey Mercedes."
"Mercedes-Benz is integrating ChatGPT through Azure OpenAI Service, leveraging the enterprise-grade capabilities of Microsoft’s cloud and AI platform."
"Soon, participants who ask the Voice Assistant for details about their destination, to suggest a new dinner recipe, or to answer a complex question, will receive a more comprehensive answer"
"The voice command data collected is stored in the Mercedes-Benz Intelligent Cloud, where it is anonymised and analysed."
Transparency Evidence & methodology 75/100 reference value · 92% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value75/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact0/25
    0 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence92%
  • Source authority25/25
    The deployment is described by the adopting organization or a government source.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    5 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity8/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. Mercedes-Benz

    Mercedes-Benz customer story

    First-party
    https://group.mercedes-benz.com/technology/digitalisation/connectivity/car-voice-control-with-chatgpt.html
    Source type
    Customer-published story
    Published
    Jun 16, 2023
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

  • Published on source page Jun 16, 2023 · Mercedes-Benz Group · First-party
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.