← Back to OTTO Builds a Native Voice Shopping AI Assistant on Google Cloud's Gemini

Source proof for OTTO Builds a Native Voice Shopping AI Assistant on Google Cloud's Gemini

Source-bound proof

Verified source excerpts for every supported field

Each colour maps a published value to the exact source passage used to support it. Only bounded excerpts are public; administrators can inspect the complete captured source.

14 fields supported

Title

OTTO Builds a Native Voice Shopping AI Assistant on Google Cloud's Gemini

derived · high
…nd growing Custom orchestration layer keeps conversations fluent and controlled OTTO became Europe's first retailer with a native voice shopping assistant, turning expert advice into a real conversation. Why search wasn't the final an…

Description

German online retailer OTTO built a native voice shopping assistant on Google Cloud's Gemini Enterprise Agent Platform, using the Gemini Live API with native audio and Chirp 3 speech recognition to deliver conversational product advice across roughly 19 million products. Becoming the first EMEA retailer with native voice shopping in production, OTTO cut end-to-end voice response latency from 8-9 seconds to under 2 seconds and scaled expert product advisory coverage from 5 to 50 categories.

derived · high
…Google Cloud First EMEA retailer with native voice shopping live in production Voice assistant available across ~19 million products Scaled expert product advisory from 5 to 50 categories—and growing Custom orche…
…ion, a capability that improved measurably as Google iterated during the build. End-to-end latency dropped from 8–9 seconds in early prototypes to under two. Keeping that fluency under control required something new. OTTO's engineers in…
…opping live in production Voice assistant available across ~19 million products Scaled expert product advisory from 5 to 50 categories—and growing Custom orchestration layer keeps conversations fluent and controlle…

Company

OTTO

quote · high
…ning expert advice into a real conversation. Why search wasn't the final answer OTTO is the largest German online retailer, offering ~19 million products from both its own wholesale business and 6,100 m…

Country

Germany

quote · high
…1949 catalogs to AI-powered shopping, OTTO has reinvented retail at every turn. Industry: Retail Location: Germany Products: Gemini Enterprise Agent Platform , Gemini Live API (Native Audio), Ge…

Industry

Retail

classification · high
…1949 catalogs to AI-powered shopping, OTTO has reinvented retail at every turn. Industry: Retail Location: Germany Products: Gemini Enterprise Agent Platform , Gemini Live API (Native Audio), Ge…

Problem

Search answers in lists, so a customer typing a broad query like "washing machine" gets thousands of results to filter through, but a customer wanting advice needs a back-and-forth dialogue, follow-up questions, and a recommendation that explains itself — something search alone cannot deliver.

derived · high
…ational shopping, but how to make the experience feel like a real conversation. Search has always been a powerful tool, but it answers in lists. A customer typing "washing machine" gets thousands of results and starts filter…

Solution

OTTO built a native voice shopping assistant on Google Cloud's Gemini Enterprise Agent Platform. After an interim cascading speech-to-text/text-to-speech layer failed to create real engagement in user tests, OTTO rebuilt the voice path on the Gemini Live API with native audio: a text assistant drives guardrails, recommendations and search while a live audio model handles the real-time conversation, with Chirp 3 handling German speech recognition. OTTO's engineers built a custom orchestration layer drawn from formal methods to make provable guarantees about conversation behaviour, and imprecise requests are treated as a retrieval-and-validation problem where candidates are re-evaluated for fit by Gemini 2.5 Flash before reaching the customer.

derived · high
…ough came in November 2025, when Gemini Live had matured enough for production. OTTO rebuilt the voice path on the Live API with native audio. Instead of cascading text into speech, two models now run in parallel: the text…
…in Hamburg, with hands-on support from Google's product and engineering teams, built an orchestration layer drawn from formal methods—the kind used to verify concurrent systems, not just test them. It lets the tea…
…requests—"a very quiet washing machine"—as a retrieval and validation problem: candidates are surfaced, then re-evaluated for fit by Gemini 2.5 Flash before anything reaches the customer. Early signals from a listening catalog The voice assistant entered open beta i…

Business value

OTTO became the first EMEA retailer with a native voice shopping assistant live in production, covering roughly 19 million products. End-to-end latency dropped from 8–9 seconds in early prototypes to under two seconds, and expert product advisory coverage scaled from 5 hand-crafted categories to 50, with the next wave covering the full catalog in progress.

derived · high
…ping AI across 19 million products Get started for free Results on Google Cloud First EMEA retailer with native voice shopping live in production Voice assistant available across ~19 million products Scaled expert product adv…
…ion, a capability that improved measurably as Google iterated during the build. End-to-end latency dropped from 8–9 seconds in early prototypes to under two. Keeping that fluency under control required something new. OTTO's engineers in…
…opping live in production Voice assistant available across ~19 million products Scaled expert product advisory from 5 to 50 categories—and growing Custom orchestration layer keeps conversations fluent and controlle…

AI capabilities

Conversational AI, Generative AI

classification · high
…nd growing Custom orchestration layer keeps conversations fluent and controlled OTTO became Europe's first retailer with a native voice shopping assistant, turning expert advice into a real conversation. Why search wasn't the final answer OTTO is the largest German online retailer,…

Technology

Gemini Enterprise Agent Platform, Gemini Live API (Native Audio), Gemini 2.5 Flash, Gemini 3 Pro, Chirp 3

classification · high
…s reinvented retail at every turn. Industry: Retail Location: Germany Products: Gemini Enterprise Agent Platform , Gemini Live API (Native Audio), Gemini 2.5 Flash , Gemini 3 Pro , Chirp 3 menu Overview Solutions Products Pricing Resources Docs Support Contact us &#xE…

Headline outcome

derived · high
…opping live in production Voice assistant available across ~19 million products Scaled expert product advisory from 5 to 50 categories—and growing Custom orchestration layer keeps conversations fluent and controlle…

Use case type

Conversational assistant

classification · high
…led OTTO became Europe's first retailer with a native voice shopping assistant, turning expert advice into a real conversation. Why search wasn't the final answer OTTO is the largest German online retailer,…

Deployment model

cloud

classification · medium
…apabilities and direct support from Google's forward-deployed engineering team, OTTO chose Gemini Enterprise as the Agent Platform on which to build the new assistant. The technical bet was significant. When the team started, Gemini's native audio…

Deployment options

cloud

classification · medium
…apabilities and direct support from Google's forward-deployed engineering team, OTTO chose Gemini Enterprise as the Agent Platform on which to build the new assistant. The technical bet was significant. When the team started, Gemini's native audio…
Capture details
Captured
10 Oct 2026, 05:23 UTC
Extractor
fetch-strip@1
Snapshot hash
14d3ee8ac7670a78d7463e2ef60f5d8b66b0225ef41aaea6c9290b4d6a97a127