--- title: Can Voice Agents Handle Bilingual Customers?... description: ServiceNow AI built a benchmark to evaluate how well frontier ASR systems handle code-switched speech (bilingual mid-sentence language switching) in enterprise... canonical: https://daily.dev/posts/can-voice-agents-handle-bilingual-customers-benchmarking-frontier-asr-on-code-switched-speech-rdd6ryrzx twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Can Voice Agents Handle Bilingual Customers? Benchmarking Frontier ASR on Code-Switched Speech | daily.dev og:description: ServiceNow AI built a benchmark to evaluate how well frontier ASR systems handle code-switched speech (bilingual mid-sentence language switching) in enterprise... og:url: https://daily.dev/posts/can-voice-agents-handle-bilingual-customers-benchmarking-frontier-asr-on-code-switched-speech-rdd6ryrzx og:image: https://api.daily.dev/og/posts/RDd6rYRzx.png og:image:alt: Can Voice Agents Handle Bilingual Customers? Benchmarking Frontier ASR on Code-Switched Speech og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Can Voice Agents Handle Bilingual Customers? Benchmarking Frontier ASR on Code-Switched Speech **[Hugging Face](https://daily.dev/sources/huggingface)** · 13 min read · 1 upvotes · 0 comments ## Summary ServiceNow AI built a benchmark to evaluate how well frontier ASR systems handle code-switched speech (bilingual mid-sentence language switching) in enterprise voice agent settings. The benchmark covers four language pairs (Spanish-English, French-English, Canadian French-English, German-English) across HR and IT service scenarios, using 918 synthetic utterances. Seven ASR models were tested using WER, Semantic WER, and Answer Error Rate. ElevenLabs Scribe V2, Gemini 3 Flash, and AssemblyAI Universal 3-Pro emerged as top performers. Key findings: the number of language switches predicts whether errors occur, while Code-Mixing Index predicts error severity; errors concentrate on English embedded segments rather than matrix-language portions; and Whisper performs poorly due to defaulting to translation instead of transcription on code-switched audio. The benchmark and evaluation harness (AU-Harness) are released publicly. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Granite Switch 4.1: Chat, Decisions, and Speech from One Endpoint](https://daily.dev/posts/granite-switch-4-1-chat-decisions-and-speech-from-one-endpoint-0ig1nmhow) · Hugging Face · 1 upvotes · 1 comments - [Finally, AI’s Most Human Interface is Here\!](https://daily.dev/posts/finally-ai-s-most-human-interface-is-here--ikz7r75he) · Daily Dose of Data Science \| Avi Chawla \| Substack · 0 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#voice-ai](https://daily.dev/tags/voice-ai) [View this post on daily.dev](https://daily.dev/posts/can-voice-agents-handle-bilingual-customers-benchmarking-frontier-asr-on-code-switched-speech-rdd6ryrzx) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Can Voice Agents Handle Bilingual Customers? Benchmarking Frontier ASR on Code-Switched Speech","url":"https://daily.dev/posts/can-voice-agents-handle-bilingual-customers-benchmarking-frontier-asr-on-code-switched-speech-rdd6ryrzx","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/can-voice-agents-handle-bilingual-customers-benchmarking-frontier-asr-on-code-switched-speech-rdd6ryrzx"},"datePublished":"2026-06-09T19:38:48.142Z","dateModified":"2026-10-14T02:26:35.570Z","description":"ServiceNow AI built a benchmark to evaluate how well frontier ASR systems handle code-switched speech (bilingual mid-sentence language switching) in enterprise...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7006095250a1390c1b0ab22e7b561d5e?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7006095250a1390c1b0ab22e7b561d5e?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Hugging Face","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Hugging Face","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/f1f55c67d81a4330acf5b90b26b0c8e1","url":"https://daily.dev/sources/huggingface"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/can-voice-agents-handle-bilingual-customers-benchmarking-frontier-asr-on-code-switched-speech-rdd6ryrzx","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,voice-ai","timeRequired":"PT13M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hugging Face","item":"https://daily.dev/sources/huggingface"},{"@type":"ListItem","position":3,"name":"Can Voice Agents Handle Bilingual Customers? Benchmarking Frontier ASR on Code-Switched Speech"}]} ```