Congrats to the @GoogleDeepMind team on an awesome model; 3.8 is a step change in gemini voice performance. And shoutout to movie-star-in-the-making @valeriawu_

Community has always been at the heart of Tau. To celebrate the exciting work happening across our ecosystem, we’re highlighting some contributions here taubench.com/community. If you have built something with Tau, please make a PR and we'll take a look. 🚀

When is voice mode coming to personal assistants? 👀

Introducing τ-i18n (pronounced internationalization), extending τ-Voice to more languages and raising the bar for conversation quality. At Sierra, our work with customers serving non-English speakers reinforces a clear standard: voice agents need to complete the task and deliver a conversation that feels native. Clay Bavor calls this “unreasonable localization”—getting even the small details right. Every language has its own nuances, from noun gender in Hindi to tones in Mandarin. The meaning may be clear, but those mistakes keep a conversation from feeling native. In τ-Voice, accents caused the largest average drop in task completion among the factors we tested. That motivated us to expand beyond English. τ-i18n brings the same airline, retail and telecom tasks to Spanish, Brazilian Portuguese, Hindi, Korean, and Mandarin. Tasks, policies, tools, and success criteria stay fixed, allowing comparisons across languages. We also examine how database localization affects performance. Working with native speakers, we built callers and evaluation rules that reflect local conventions—from name order and code-switching to forms of address and honorifics. These conventions affect outcomes: an agent can hear a family-first name correctly and still fail authentication by putting it into the wrong fields. Across 4,500 calls, task completion in Spanish, Portuguese, and Hindi stays within 3.2 percentage points of English. Korean and Mandarin trail by 14.7 and 8.4 points. But completing the task is only part of a good call. Roughly 30–43% of evaluated utterances fail naturalness checks. A caller can get what they need and still have a bad experience. Our evaluations need to capture both. These five additional languages are a starting point. We’ll soon open source our codebase and LanguageFactory, our workflow for building localized user simulators and evaluation criteria, so native speakers can contribute new language packs. If your language is missing, we’d love your help bringing it to the benchmark: build representative callers, review conversations, and define the conventions agents should meet—so voice agents can better serve speakers around the world. We’re also tackling the hardest part separately with τ-Entity–how reliably do voice agents collect names and numbers, decide when to verify, and correct mistakes? Built with friends at @SierraPlatform (Edgard dos Santos Paiva Neto, Ruben Valenzuela, Keshav Dhandhania, Vijay Iyengar, Ajeet Grewal), @mercor (Victor Barres), and @Princeton (Karthik Narasimhan). Papers: τ-i18n arxiv.org/abs/2609.35820v1, τ-Entity arxiv.org/abs/2609.13602v1 Submission instructions, codebase, and updated leaderboard coming soon.

Introducing τ-Entity, a benchmark for how voice agents collect, verify, and correct the details callers give them. In τ-Voice, capturing names and other identifying information was a recurring bottleneck: get a detail wrong, and authentication fails before the agent can help. τ-Entity breaks that exchange down. Can an agent collect one exact value, recognize when it needs to check what it heard, and repair a mistake? We test 200 tasks across ten entity types, including names, phone numbers, addresses, and emails. Each call asks for a single field, with a cooperative caller who spells accurately when asked. Most calls last less than two minutes. And even here, reliability is far from solved. When agents choose their own verification strategy, only 14–41% of tasks succeed across all tested conditions. A brute-force approach—prescribing spelling, read-back, and confirmation—raises that to 37–54%, but makes calls longer. The challenge is finding the balance: knowing when to trust a capture and when to spend more effort checking it. Across systems, agents recognize hard and unfamiliar entities and verify them more carefully. But they do not increase verification for the caller voices they struggle with most, and their response to noise is inconsistent. And verification often fails to produce a repair: just 24–37% of wrong captures that agents verify end up correct. Agents need to get better at both deciding when to check and using the answer to fix the record. We’re introducing τ-Entity alongside τ-i18n, and plan to extend these entity-collection tasks across languages with the upcoming codebase release. Together, they help us measure whether voice agents can both handle the details accurately and deliver a conversation that feels native. Thanks to Victor Barres at @mercor for collaborating on this. Papers: τ-Entity arxiv.org/abs/2609.13602v1, τ-i18n arxiv.org/abs/2609.35820v1 Codebase and multilingual extension coming soon!

This makes total sense. The benchmarking cycle is insanely fast now: new benchmark drops -> data companies crank out training data -> benchmark saturated in months. Real progress requires specialization—the high-value difficulty is in the nuances generalized data misses. I'm interested to see how this evolves, and grateful for the partnership with @FireworksAI_!

its been a wild week!

GPT live takes a big lead on tau-voice! and the text-voice gap from 6 months ago gone, 88% is the highest on text vs 86 on voice.

Awesome stuff from Sierra favorites Ben Shi, Keshav Dhandhania, Victor Barres and Karthik Narasimhan. Hypertau lets you benchmark coding agents, their harnesses, and their self improving capabilities. How do coding agents decide to spend their budget? How do they decide which models to pick for sub agents? How do they decide when to run simulations, and how many? How do they resolve ambiguities? Reach out to the client? Or look for answers in simulated slack threads, websites, snapshots or knowledge base artifacts? Learned so much from this, and we see these gaps everyday at Sierra. First of many tau releases, stay tuned!

Interaction as a first class citizen, and knowledge over voice with tau-voice banking

Looking forward to AI agents sounding natural, like everyday voices, and not studio/podcast like!

love to see the explicit decoupling of holding a conversation and completing a task. Reinforces that perceived latency in voice AI agents is not just making progress on the task at hand but also responsiveness to the user.

Tired of the echo chamber?

When we built tau voice, there was no open source model that supported tool calls and so nothing to benchmark. Very exciting that tau has a new leader, and it’s open source! Let’s goooo

Excited for long horizon cx

I do this quite often! When I type I find myself trying to be concise (just me?) but that’s out the window with speech, and I am able to better express vague ideas in speech than text. Not always speech ofc. Usually i know exactly what I want to say and text is good enough.