Get ready to embark on an extraordinary musical journey across Asia with YOASOBI! ✨ From beloved songs to spectacular live performances, experience the moment when music, dazzling visuals, and thousands of voices come together under one roof. Follow Ayase and ikura beyond cities and borders, and immerse yourself in the ever-expanding universe of YOASOBI. 🌠 📍Venue & Date Sapporo | November 14 - 15, 2026 | Daiwa House Premist Dome Fukuoka | November 28 - 29, 2026 | MIZUHO PayPay Dome FUKUOKA 🎫Sale Start: September 3, 2026, 13:00 (UTC+9) Click secure your spots! YOASOBIとともに、アジアを巡る壮大な音楽の旅へ！✨ 心を揺さぶる楽曲、圧巻のライブパフォーマンス、そして会場を包み込む光と歌声。AyaseとIkuraが紡ぎ出す物語とともに、都市や国境を越え、さらに広がっていくYOASOBIの世界を体感しよう。🌠 📍会場 & ⏰開演日時： 札幌 |2026年11月14日 – 15日 | 大和ハウス プレミストドーム 福岡 |2026年11月28日 – 29日 | みずほPayPayドーム福岡 🎫販売開始: 2026年9月3日 13:00 (UTC+9) 👉チケットはこちら： #YOASOBI超惑星# #Ayase# #ikura#

GPT-Live-1 (Astra, medium) leads Tau Voice at 67.9%, followed by GPT-Live-1 (Sol, low) at 59.3% and Grok Voice Think Fast 2.0 High at 56.5%, driving its overall Index lead. Both GPT-Live-1 configurations are currently based on one trial. On Big Bench Audio, they achieve 90.1% and 89.0%, respectively, behind Grok at 97.2%. On our Full Duplex Bench subset, they score 94.9% and 97.3%, respectively; this benchmark is reported separately from the Index.

Announcing Multilingual Text to Speech Arena Leaderboards, comparing leading TTS models across 9 languages beyond English 🇯🇵 🇨🇳 🇮🇳 🇪🇸 🇩🇪 🇫🇷 🇵🇹 🇻🇳 🇸🇦 Text to Speech performance varies significantly across languages, with models that perform well in English not necessarily delivering the same pronunciation, pacing, tone, and naturalness in other languages. We have extended the Artificial Analysis Controlled Voice Arena to 9 new languages: Japanese 🇯🇵, Mandarin Chinese 🇨🇳, Hindi 🇮🇳, Spanish 🇪🇸, German 🇩🇪, French 🇫🇷, Portuguese 🇵🇹, Vietnamese 🇻🇳, and Arabic 🇸🇦. Each model is evaluated using standardized cloned voices, with prompts written natively in each language and preference votes collected from first-language speakers. Elo scores are calculated independently for each language, allowing each leaderboard to reflect model preferences among speakers of that language. Key results: ➤ @Cartesia's Sonic family leads 8 of the 9 new language leaderboards, with Sonic 3.6 ranking #1# in 7 languages and Sonic 3.5 leading Portuguese. @InworldAI's Realtime TTS-2 takes the #1# spot in Mandarin. ➤ @ElevenLabs' Eleven v3 family ranks in the top 3 across 7 of the 9 new languages, through Eleven v3 and Eleven v3 Conversational. ➤ Inworld's Realtime TTS-2 leads Mandarin at 1,185 Elo, ahead of Sonic 3.6 at 1,146 and StepFun's StepAudio 2.5 TTS at 1,130. Realtime TTS-2 also ranks #1# in English (US). ➤ More than 100,000 human preference votes have been collected across the 9 new language leaderboards, with 15 to 24 public models ranked per language. See the per-language results below ⬇️

Grok Voice Transcribe 2.0 is absolutely crushing phone calls 92.9% accuracy....way ahead of Deepgram, ElevenLabs and Gemini And it’s only $0.10/hour That price for that level of accuracy is pretty insane

Explore the multilingual Controlled Voice Arena Leaderboards and compare the leading Text to Speech models across all 9 new languages: Controlled Voice Arena Leaderboard - select a language: Vote in the public Text to Speech Arena: Read our Text to Speech benchmarking methodology:

SpaceXAI just launched Grok Voice Think Fast 2.0 - its most capable speech-to-speech model yet The numbers are so impressive: • 82.9% overall Speech-to-Speech Quality Index • 97.2% on speech reasoning • 56.5% on agentic voice tasks • Just 0.70 seconds to first audio • Uses only 0.4× the reasoning tokens of Think Fast 1.0 Grok Voice Think Fast 2.0 now ranks ahead of GPT-Realtime-2.1 and Gemini 3.1 Flash on overall speech-to-speech benchmarks But the biggest improvement is real-world listening Across thousands of short phrases in 24 languages, it delivers 1.5–2× better transcription accuracy than Deepgram Nova 3 and ElevenLabs Scribe v2 In noisy environments and compressed phone calls, that advantage grows to around 10× It can also reason while speaking, allowing tool calls to begin before it even finishes its first sentence.....with no added latency Conversations now feel much more natural: • Shorter responses • One question at a time • Less filler • More fluid dialogue • Better guidance through complex tasks SpaceXAI has already deployed it on Starlink's phone line and saw significant increases in both sales conversion and customer support containment Grok Voice Think Fast 2.0 becomes the default grok-voice-latest model on August 5 Pricing: $0.08 per minute of audio Voice AI is rapidly evolving from scripted assistants into intelligent agents that can listen, reason, speak, and take action in real time

SpaceXAI just released Grok Voice Transcribe 2.0.....and it already ranks #1# for BOTH Final Transcript accuracy and First Partial Transcript accuracy on Artificial Analysis’ streaming ASR benchmark Grok Voice Transcribe 2.0 reaches just 2.7% word error rate on final transcripts That’s down from 3.9% on Grok Voice Transcribe 1.0.....roughly 31% fewer transcription errors It now leads Meta Muse Voice Transcribe, Cartesia Ink, ElevenLabs Scribe Realtime and every other streaming ASR model tested Grok is now leading real-time speech transcription accuracy

“America deserved 9/11.” Hasan Piker said those words. Nearly 3,000 innocent people were killed that day… firefighters, police officers, office workers, mothers, fathers, sons and daughters who had absolutely nothing to do with whatever political grievance he was raging about. And now Piker has become a prominent voice around parts of the progressive left and has campaigned alongside Michigan Senate candidate Abdul El-Sayed. You can criticize America. You can attack its foreign policy. But saying this country deserved 9/11 is a line I will never normalize. Nearly 3,000 innocent Americans did not deserve to die. Never forget what was said. Never pretend it was nothing.