Volkswagen
in-car genAI voice assistant
Volkswagen integrated ChatGPT into its in-car IDA voice assistant via Cerence Chat Pro, rolled out by cloud update from June 2024 across the Volkswagen, Cupra, Seat, and Skoda brands, live in five languages.
Key points
- Integration of ChatGPT into the embedded IDA voice assistant.
- Cerence Chat Pro in a hybrid embedded/cloud approach, activated by cloud update.
- Deployed on Volkswagen, Cupra, Seat, and Skoda, live in five languages.
- Evidence level B, confirmed status, deployment in Europe then the United States.
Objective
Add a natural-language conversation layer to the IDA voice assistant already present in the vehicles, to enrich the in-car experience without the driver having to install or configure anything.
The deployment
Cerence Chat Pro integrates ChatGPT into the background of Volkswagen's IDA voice assistant. The driver keeps the embedded vehicle control (climate, navigation, phone) and gains access to conversational answers and real-time web information through the same voice interface, thanks to Cerence's hybrid embedded-plus-cloud approach. Rolled out from June 24, 2024 by cloud update across the European range (ID., Golf, Tiguan, Passat, plus older models), then extended to the United States and other markets in late 2024 and early 2025. Available on Volkswagen, Cupra, Seat, and Skoda, in five languages.
Results Proof B
Case study from the vendor Cerence (interested party) quantifying the deployment (five languages, four brands, full range), corroborated by the official Volkswagen Group blog; multi-market reach but no isolated financial usage metric.
How it works
Documented architectureThe stack in detail
- plateforme Cerence Chat Pro GenAI layer designed for automotive, which integrates ChatGPT into the background of the IDA voice assistant.
- llm ChatGPT (OpenAI) Model that drafts the answers to open questions routed to the cloud.
- outil Assistant vocal IDA Volkswagen's embedded assistant (vehicle command handled locally), single interface for the driver.
- infra NLU hybride embarque/cloud Cerence Arbitration between vehicle commands handled onboard and open questions sent to the cloud LLM.
How it runs, concretely
For ops teams-
1Activation customer
The driver speaks to the IDA assistant already present in the vehicle.
-
2Embedded/cloud arbitration AI
The Cerence hybrid approach handles vehicle commands locally and sends open questions to ChatGPT.
-
3Conversational answer AI
Cerence Chat Pro has ChatGPT draft the answer and delivers it through IDA.
-
4Distribution by update data team
The feature is activated across the fleet by cloud update, market by market and model by model.
The voice request and the distinction between vehicle command (handled onboard) and open question (routed to the cloud LLM). Without connectivity, the cloud conversational part is no longer available.
How your customers perceive this type of use
Sourced studiesLes consommateurs n'acceptent pas les chatbots par defaut : 64% prefereraient que les entreprises n'utilisent pas d'IA dans leur service client (Gartner, 2024) et pres d'un utilisateur sur cinq du service client par IA n'en retire aucun benefice (Qualtrics, 2025). L'acceptation se construit sur trois conditions mesurees par Salesforce : savoir qu'on parle a une IA, pouvoir escalader vers un humain, comprendre la logique de l'agent.
Acceptance conditions
- Etre informe qu'on parle a une IA et non a un humain (pres de 75% le demandent, Salesforce 2024)
- Un chemin d'escalade clair vers un agent humain (45% plus enclins a utiliser l'agent IA, Salesforce 2024)
- Une logique de l'agent clairement expliquee (44% plus enclins, Salesforce 2024)
Red lines
- Rendre l'humain injoignable : c'est la premiere inquietude des consommateurs sur l'IA dans le service client (Gartner 2024) et 50% craignent que l'IA les coupe du contact humain (Qualtrics 2025)
- Remplacer le service client par l'IA sans alternative : 53% envisageraient de partir chez un concurrent (Gartner 2024)
Sources: Salesforce 2024 · Gartner 2024 · Qualtrics 2025
How to replicate
Inference, not sourcedData prerequisites
- existing voice assistant to augment
- vehicle and session context
Org prerequisites
- partnership with an automotive voice vendor
- legal framework on cloud transit
Possible stack
- Cerence or equivalent automotive voice
- cloud LLM such as ChatGPT
- hybrid embedded/cloud NLU
The plan, step by step
- Step 1Choose the automotive voice vendor and frame the legal side of routing requests to the cloud.Deliverable: Partner contract + GDPR framework on request data.
- Step 2Integrate the conversational layer into the existing voice assistant, with embedded/cloud arbitration.Deliverable: Working prototype on bench and test vehicle.
- Step 3Test the target languages and validate driver safety and non-distraction.Deliverable: Acceptance validated by market and by language.
- Step 4Activate the feature on a pilot fleet by cloud update.Deliverable: Feature live on a pilot fleet with voice usage metrics.
- Step 5Deploy market by market and model by model.Deliverable: OTA rollout tracked for usage and incidents.
First step: Connect the voice vendor's conversational layer to the already-deployed embedded assistant, then activate by cloud update.
The same pattern, proven in other industries
ADT
genAI customer agent
Air India
genAI customer agent (automated customer service)
AT&T
Governed enterprise genAI assistant: an LLM connected to internal knowledge, open to tens of thousands of employees and called at scale by automated systems
Sources
- S1 Volkswagen and Cerence Commence Roll-Out of New Generative AI Solutions to Drivers Interested party archive pending
- S2 ChatGPT is now available in many Volkswagen models Primary archive pending
- S3 World premiere at CES: Volkswagen integrates ChatGPT into its vehicles Primary archive pending
An error, newer info, a source?
This page lives on its accuracy. If a figure has moved, if the deployment has changed, or if you have a higher-quality source, tell us. Every sourced correction is verified before publication.