---
title: "AlphaSignal Audio: Realtime Voice News"
url: "https://alphasignal.ai/topic/audio/realtime-voice"
description: "Latest AI and machine learning news about Realtime Voice (Audio) on AlphaSignal."
---

# AlphaSignal Audio: Realtime Voice News

Latest AI and machine learning news about Realtime Voice (Audio) on AlphaSignal.

## Articles

- [Sesame Launches Maya and Miles as Full AI Agents With Their Own Computers](https://alphasignal.ai/news/sesame-launches-maya-and-miles-as-full-ai-agents-with-their-own-computers.md) (2026-10-08)
- [EMA Lightning Beats ElevenLabs on Turkish Speech in Just 34 MB](https://alphasignal.ai/news/ema-lightning-beats-elevenlabs-on-turkish-speech-in-just-34-mb.md) (2026-10-08)
- [Sesame Launches Four Eerily Realistic AI Voice Agents Ahead of Smart Glasses](https://alphasignal.ai/news/sesame-launches-four-eerily-realistic-ai-voice-agents-ahead-of-smart-glasses.md) (2026-10-06)
- [Microsoft's MAI-Transcribe-2-Streaming Tops 38 Models With 2.5% Error Rate](https://alphasignal.ai/news/microsoft-s-mai-transcribe-2-streaming-tops-38-models-with-2-5-error-rate.md) (2026-10-01)
- [Inception Labs' Mercury Voice Hits 320ms Response for Live AI Calls](https://alphasignal.ai/news/inception-labs-mercury-voice-hits-320ms-response-for-live-ai-calls.md) (2026-09-29)
- [Runway Brings ElevenLabs v4 Voice Into Its Visual Production Workflow](https://alphasignal.ai/news/runway-brings-elevenlabs-v4-voice-into-its-visual-production-workflow.md) (2026-09-28)
- [Meta's Muse Slashes Real-Time Avatar Generation from 120 Model Calls to Two](https://alphasignal.ai/news/meta-s-muse-slashes-real-time-avatar-generation-from-120-model-calls-to-two.md) (2026-09-24)
- [OpenAI's ChatGPT Work Lets Voice Control Your Emails, Slack, and Calendar](https://alphasignal.ai/news/openai-s-chatgpt-work-lets-voice-control-your-emails-slack-and-calendar.md) (2026-09-23)
- [Alibaba's Qwen-Audio 3.1 Slashes Voice API Prices by up to 95%](https://alphasignal.ai/news/alibaba-s-qwen-audio-3-1-slashes-voice-api-prices-by-up-to-95.md) (2026-09-23)
- [NetEase Youdao's Confucius4-R2T2 Streams Speech Without Ever Revising Committed Words](https://alphasignal.ai/news/netease-youdao-s-confucius4-r2t2-streams-speech-without-ever-revising-committed.md) (2026-09-22)
- [Artificial Analysis' Benchmark Reveals Gemini 3.1 Flash TTS Beats Sonic 3.6 on Pronunciation](https://alphasignal.ai/news/artificial-analysis-benchmark-reveals-gemini-3-1-flash-tts-beats-sonic-3-6-on.md) (2026-09-22)
- [Alibaba's Qwen-Audio-Agent Hits 91% Success Splitting Voice Tasks Between Two AI Contexts](https://alphasignal.ai/news/alibaba-s-qwen-audio-agent-hits-91-success-splitting-voice-tasks-between-two-ai.md) (2026-09-21)
- [Kyutai's Voice of Reason Thinks While It Speaks, Hitting 77% Math Accuracy](https://alphasignal.ai/news/kyutai-s-voice-of-reason-thinks-while-it-speaks-hitting-77-math-accuracy.md) (2026-09-21)
- [Alibaba's Qwen-Audio-3.1-Realtime Cuts Background Speech Responses by 60%](https://alphasignal.ai/news/alibaba-s-qwen-audio-3-1-realtime-cuts-background-speech-responses-by-60.md) (2026-09-21)
- [Alibaba's Qwen3.8 LiveTranslate Cuts Speech Translation Lag to 2.3 Seconds](https://alphasignal.ai/news/alibaba-s-qwen3-8-livetranslate-cuts-speech-translation-lag-to-2-3-seconds.md) (2026-09-19)
- [LM Studio 1.1.3 Brings Private On-Device Voice Transcription to Linux](https://alphasignal.ai/news/lm-studio-1-1-3-brings-private-on-device-voice-transcription-to-linux.md) (2026-09-15)
- [OpenAI's GPT-Live-1 Cuts Voice Agent Code by 80% at $0.05 a Minute](https://alphasignal.ai/news/openai-s-gpt-live-1-cuts-voice-agent-code-by-80-at-0-05-a-minute.md) (2026-09-10)
- [Inworld's Realtime TTS-2 Beats Cartesia at 58% Lower Cost](https://alphasignal.ai/news/inworld-s-realtime-tts-2-beats-cartesia-at-58-lower-cost.md) (2026-09-03)
- [Meta's Muse Voice Transcribe Beats Every Rival With 3.1% Error Rate](https://alphasignal.ai/news/meta-s-muse-voice-transcribe-beats-every-rival-with-3-1-error-rate.md) (2026-09-01)
- [Sesame's TurnBench Exposes How Gemini Live and OpenAI Realtime Fumble Conversations](https://alphasignal.ai/news/sesame-s-turnbench-exposes-how-gemini-live-and-openai-realtime-fumble.md) (2026-08-28)
- [Fish Audio Squeezes 2M Voices and Voice Cloning Into an iPhone App](https://alphasignal.ai/news/fish-audio-squeezes-2m-voices-and-voice-cloning-into-an-iphone-app.md) (2026-08-26)
- [Artificial Analysis' Speech Arena Reveals Voice AI's Uncomfortable Split Brain Problem](https://alphasignal.ai/news/artificial-analysis-speech-arena-reveals-voice-ai-s-uncomfortable-split-brain.md) (2026-08-21)
- [Kizuna AI Lab's Sokuji Translates Live Calls Offline Without a GPU](https://alphasignal.ai/news/kizuna-ai-lab-s-sokuji-translates-live-calls-offline-without-a-gpu.md) (2026-08-21)
- [Sarvam AI's Kivi Lands Pre-Installed on HP Laptops Across India](https://alphasignal.ai/news/sarvam-ai-s-kivi-lands-pre-installed-on-hp-laptops-across-india.md) (2026-08-15)
- [Sarvam AI Opens Samvaad to Developers After 350M Real Conversations](https://alphasignal.ai/news/sarvam-ai-opens-samvaad-to-developers-after-350m-real-conversations.md) (2026-08-13)
- [OpenAI Rebuilds ChatGPT Voice With GPT-Live to Talk and Listen at Once](https://alphasignal.ai/news/openai-rebuilds-chatgpt-voice-with-gpt-live-to-talk-and-listen-at-once.md) (2026-08-03)
- [Parlor Runs a Full Voice-and-Vision AI Assistant Locally on a Laptop](https://alphasignal.ai/news/parlor-runs-a-full-voice-and-vision-ai-assistant-locally-on-a-laptop.md) (2026-08-03)
- [LiveKit Agents Hits 13K Stars Building Voice AI Without the Lock-in](https://alphasignal.ai/news/livekit-agents-hits-13k-stars-building-voice-ai-without-the-lock-in.md) (2026-08-03)
- [xAI's Grok Voice Think Fast 2.0 Hits Sub-Second Response, Beating GPT-Realtime](https://alphasignal.ai/news/xai-s-grok-voice-think-fast-2-0-hits-sub-second-response-beating-gpt-realtime.md) (2026-07-29)
- [Nous Research Ships Hands-Free 'Hey Hermes' Wake Word to Its 175K-Star Agent](https://alphasignal.ai/news/nous-research-ships-hands-free-hey-hermes-wake-word-to-its-175k-star-agent.md) (2026-07-29)
- [Alibaba's Qwen Audio 3.0 Dethrones OpenAI With a 99.2% Reasoning Score](https://alphasignal.ai/news/alibaba-s-qwen-audio-3-0-dethrones-openai-with-a-99-2-reasoning-score.md) (2026-07-28)
- [Fish Audio's S2.1 Pro Beats ElevenLabs at 11x Lower Cost After $52M Raise](https://alphasignal.ai/news/fish-audio-s-s2-1-pro-beats-elevenlabs-at-11x-lower-cost-after-52m-raise.md) (2026-07-28)
- [OpenAI Ships GPT-Live Voice to Desktop, Turning Speech Into Agent Control](https://alphasignal.ai/news/openai-ships-gpt-live-voice-to-desktop-turning-speech-into-agent-control.md) (2026-07-23)
- [Alibaba's Qwen-Audio-3.0-TTS Tops Speech Arena With 16-Language Voice Cloning](https://alphasignal.ai/news/alibaba-s-qwen-audio-3-0-tts-tops-speech-arena-with-16-language-voice-cloning.md) (2026-07-20)
- [Hume AI's VoiceEQ Benchmark Exposes What 1M Human Ratings Reveal About Voice Models](https://alphasignal.ai/news/hume-ai-s-voiceeq-benchmark-exposes-what-1m-human-ratings-reveal-about-voice.md) (2026-07-15)
- [ByteDance's video-SALMONN 2 Beats GPT-4o by Teaching AI to Hear Videos](https://alphasignal.ai/news/bytedance-s-video-salmonn-2-beats-gpt-4o-by-teaching-ai-to-hear-videos.md) (2026-07-13)
- [ElatoAI Turns a $45 Chip Into a Real-Time Voice AI Device](https://alphasignal.ai/news/elatoai-turns-a-45-chip-into-a-real-time-voice-ai-device.md) (2026-07-10)
- [Alibaba's Wan-Streamer v0.2 Triples Video Resolution Without Adding Latency](https://alphasignal.ai/news/alibaba-s-wan-streamer-v0-2-triples-video-resolution-without-adding-latency.md) (2026-07-10)
- [OpenAI's GPT-Live Ditches Turn-Based Voice for Real-Time Two-Way Conversations](https://alphasignal.ai/news/openai-s-gpt-live-ditches-turn-based-voice-for-real-time-two-way-conversations.md) (2026-07-08)
- [OpenAI's gpt-realtime-2.1-mini Brings Reasoning and Tool Use at 6x Lower Cost](https://alphasignal.ai/news/openai-s-gpt-realtime-2-1-mini-brings-reasoning-and-tool-use-at-6x-lower-cost.md) (2026-07-06)
- [AssemblyAI's Universal-3.5 Pro Gives Voice Agents Memory Between Turns](https://alphasignal.ai/news/assemblyai-s-universal-3-5-pro-gives-voice-agents-memory-between-turns.md) (2026-07-06)
- [Hugging Face Ships an Open-Source Voice Agent That Ditches OpenAI's Realtime API](https://alphasignal.ai/news/hugging-face-ships-an-open-source-voice-agent-that-ditches-openai-s-realtime-api.md) (2026-07-03)
- [Ant Group Pushes Qwen3-Omni to 5.4x Faster With 0.6s Audio Response](https://alphasignal.ai/news/ant-group-pushes-qwen3-omni-to-5-4x-faster-with-0-6s-audio-response.md) (2026-07-03)
- [xAI's Grok Voice Agent Builder Undercuts Every Rival at $0.05 a Minute](https://alphasignal.ai/news/xai-s-grok-voice-agent-builder-undercuts-every-rival-at-0-05-a-minute.md) (2026-07-01)
- [Higgsfield's Seed Audio 1.0 Brings Voice Cloning and Dubbing Into Claude](https://alphasignal.ai/news/higgsfield-s-seed-audio-1-0-brings-voice-cloning-and-dubbing-into-claude.md) (2026-06-30)
- [Artificial Analysis Ranks Every Voice AI Model Into One Score](https://alphasignal.ai/news/artificial-analysis-ranks-every-voice-ai-model-into-one-score.md) (2026-06-23)
- [ModelScope's FunASR Beats Whisper by 13x With a Single Model Call](https://alphasignal.ai/news/modelscope-s-funasr-beats-whisper-by-13x-with-a-single-model-call.md) (2026-06-16)
- [Google Ships Gemini 3.5 Live Translate Across 70 Languages to Developers](https://alphasignal.ai/news/google-ships-gemini-3-5-live-translate-across-70-languages-to-developers.md) (2026-06-15)
- [OmniVoice Studio Beats ElevenLabs on Accuracy Running Fully Offline for Free](https://alphasignal.ai/news/omnivoice-studio-beats-elevenlabs-on-accuracy-running-fully-offline-for-free.md) (2026-06-13)
- [Google's Gemini 3.5 Live Translate Brings Real-Time Voice Translation to 70+ Languages](https://alphasignal.ai/news/google-s-gemini-3-5-live-translate-brings-real-time-voice-translation-to-70.md) (2026-06-12)