#Voice

AIDeveloper @mrgoodmantweets built MiniCPM-o Booking Desk, an open-source appointment booking agent that uses MiniCPM-o 4.5 for real-time, full-duplex voice and audio-visual interaction. The agent listens, speaks, and reads live booking status from an operator screen, while deterministic state control keeps execution reliable. An appointment is only booked after user confirmation.

AIGoogle AI Developers demonstrates Gemini 3.8 Live Extended Thinking as a workshop assistant that analyzes a user's workspace, reasons aloud, and guides a beginner through building a cyberdeck. The demo targets users with no prior experience building one.

AIGoogle's weekly recap covers Gemini 3.8 Live and 3.8 Live Extended Thinking, described as its most advanced live dialogue audio models yet. It also notes Dreambeans, a GoogleLabs experiment curating daily personalized stories, is now generally available, and that CC has expanded into a shared agent for household coordination. Google Pics, a Workspace tool for generating and co-creating images, is now GA, alongside AlphaGenome Atlas, DeepMind's interactive genomics discovery platform.

AIxAI's Grok Voice Transcribe 2.0 is twice as accurate as its predecessor in customer-support calls, spoken credentials, and short voice commands. The post lists these three scenarios as the areas of improvement, with no further figures given.

AIAtlassian reports that Transcribe 2.0 in Loom captured user instructions more accurately than its predecessor. Users can dictate change requests in Loom and export them directly to Cursor for coding.

AIxAI has made Transcribe 2.0 available today in the Grok Voice API. Pricing is $0.10 per hour for batch transcription and $0.20 per hour for streaming. The linked blog post contains further details.

AIxAI has introduced Grok Voice Transcribe 2.0, which it calls the world's most accurate speech transcription model. The post gives no benchmark scores, pricing, or availability details.

AIxAI released Grok Voice Transcribe 2.0, a speech-to-text model that is twice as accurate as Grok Voice Transcribe 1.0 at the same price, and ranks first for accuracy among 32 streaming models on the Artificial Analysis leaderboard. Batch transcription costs $0.10 per hour of audio and streaming $0.20 per hour, with diarization, timestamps, and key terms included. Existing Speech-to-Text API integrations gain the improvement with no code changes, and developers must pin grok-voice-transcribe-1.0 to stay on the older model during the transition.

AIDeveloper Alican Kiraz fine-tuned OpenBMB's open-source VoxCPM2 voice model on nearly 100 hours of natural Turkish speech, creating Kahya-TTS for Turkish text-to-speech. The project shows how open-source voice models can be adapted to new languages and specialized datasets. The model is available on Hugging Face.

AIOpenBMB says Dubedo is the kind of product it hoped VoxCPM2 would enable, citing speaker-aware cloning, multilingual generation, and an editing studio. The post praises @dubedostudio's work, while the background post describes Dubedo as dubbing into 30 languages with per-speaker voice cloning and a beta open for trial.

AIGrok Voice is now live on fal, and the post says it answers in 0.70 seconds and can finish tool calls before a sentence ends. Its listed capabilities include transcription with word-level timestamps, text to speech in 30+ voices across 25+ languages, and voice cloning from two minutes of audio.

AIGreg Brockman shared a demo of Codex voice running in CarPlay, letting users build software by speaking while driving. A quoted post from Jonathan Roomer says the setup runs through a third-party iOS app that connects ChatGPT Voice to Codex and his Mac.

AIGoogle is hosting Gemini Audio | At Night in San Francisco on Thursday, September 24, from 6:00 PM to 10:00 PM at The Pearl. Attendees can try Gemini 3.5 Transcribe, 3.8 Live, and 3.8 Live Extended Thinking, meet the teams that built them, and test live demos. RSVP is available at goo.gle/4xpdcBn.

AIinclusionAI has published Realtime-Venus on Hugging Face with two 9B checkpoints: Realtime-Venus-Omni for audio-visual interaction and Realtime-Venus-Audio for audio-only conversation. Both are built on MiniCPM-o 4.5 with a Qwen3-8B backbone and support full-duplex dialogue, proactive responses, and training-free long-video memory. The asynchronous Realtime-Venus-Harness runtime is hosted in a separate GitHub repository.

AIGoogle AI Studio released Gemini 3.8 Live, a native speech-to-speech model with an Extended Thinking variant, and made it available through the Live API. Gemini 3.5 Transcribe, released last month, supports 85+ languages with a reported 4.0% streaming and 2.6% non-streaming Word Error Rate, and accepts a custom vocabulary of up to 1,000 terms. Live API audio pricing is listed at $0.005/min for input and $0.018/min for output.

Why it matters: The post lists concrete Live API capabilities, per-minute audio pricing, and transcription accuracy figures, helping developers weigh voice agent options against their own cascaded pipelines.

AIGoogle announced Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, voice agents with reasoning capabilities. The post says the models take turns more seamlessly, think through complexity, and feel more natural to converse with.

AILiveKit Agents now supports Gemini 3.8 Live, letting developers choose gemini-3.8-live for low-latency audio or gemini-3.8-live-extended-thinking for longer asynchronous reasoning. Developers can switch between the two modes without changing their stack. The post points readers to LiveKit's documentation for more details.

AIGoogle's Gemini Notebook now offers live spoken Q&A over class materials in about 100 languages, and lets students record lectures on the go with audio notes saved automatically to a chosen notebook. University students in 140+ countries can also still get a free Google AI Plan for higher limits and access to more Google products.

AILiveKit rebuilt its LiveKit Cloud platform around the voice agent as the core unit of work. The redesign lets developers talk to their agent while editing it, click a metric to see the sessions behind it, and navigate back without retracing steps.

AIGoogle introduced two live dialogue models, Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, available through AI Studio and the Gemini API. Gemini 3.8 Live is built for scale and cost efficiency, combining conversational intelligence with fluid dialogue and visual grounding. The Extended Thinking variant targets high-complexity tasks with increased intelligence and multi-step reasoning.

AIGoogle is hosting a first-of-its-kind Gemini Audio experience in San Francisco next week, with Logan Kilpatrick attending. The post also points to new Live audio models for building real-time voice applications.

AIGoogle has released Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, described as new state-of-the-art live audio models available at frontier pricing and performance. The 3.8 Live model supports 97 languages with seamless switching between them, along with async tool calls.

AIGoogle is rolling out Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking across several channels. Consumers get them in Search Live and Gemini Live, developers get public preview access through the Gemini API, and enterprises get private preview through Gemini Enterprise, with Customer Experience support coming soon.

Why it matters: The post lays out where each Gemini 3.8 Live variant reaches consumers, developers, and enterprises, which clarifies access paths for a voice model release.

AIGoogle AI announces Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking as its most advanced Gemini Audio models. Gemini 3.8 Live is built for scale, speed, and cost efficiency, handling mid-sentence interruptions, transitions across 97 languages, and visual context through Search Live. Gemini 3.8 Live Extended Thinking reasons and speaks in parallel, narrating its progress on multi-step tasks such as event planning.

AIGoogle DeepMind introduced Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, two live dialogue models for voice agents. Extended Thinking scores 82.6 on Artificial Analysis' Speech to Speech Quality Index, 68.6% on τ-Voice, and 97.7% on Big Bench Audio. Gemini 3.8 Live is rolling out now in the Gemini API, Google AI Studio, and Search Live, with enterprise access in private preview.

Why it matters: The release covers a voice model's benchmark results and availability across developer, enterprise, and consumer products, useful for judging voice agent options.

AIGoogle introduces Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, two live dialogue models for voice agents that reason and speak simultaneously. The Extended Thinking version scores 82.6 on Artificial Analysis' Speech to Speech Quality Index and 97.7% on Big Bench Audio, while 3.8 Live targets scale and cost efficiency. Developers can access both through the Gemini API in Google AI Studio, and enterprise and consumer rollouts vary by product.

Why it matters: The source names the two models, their access paths, and specific benchmark results, showing how the voice agent capabilities differ between the two tiers.

AIGoogle DeepMind demonstrated 3.8 Live Extended Thinking acting as a programming tutor in Gemini Live. Both 3.8 Live models feature upgraded reasoning, near real-time visual understanding, automatic detection across 97 languages, and background tool calling that doesn't interrupt the chat. The Extended Thinking variant adds higher performance and precision for harder tasks and narrates its progress, and it is available in Gemini Live in the Gemini app or through the Gemini API via Google AI Studio.

AIGoogle reports that its technologies and products now power everyday interactions in more than 300 languages used by over 7 billion people, about 86% of the global population. The post describes new speech models, including Gemini 3.5 Live Translate and Gemini 3.5 Transcribe, plus the TranslateGemma open translation models trained across 55 languages.

AILM Studio has introduced local realtime voice transcription, letting users speak to their agents without sending voice data to the cloud. The feature is available on Mac and Windows, and now Linux as well.

AIGoogle has made two audio-to-audio models, Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, generally available through the Live API. Gemini 3.8 Live, model ID gemini-3.8-live, is the default for low-latency voice agents, with interleaved reasoning and asynchronous function calling. Gemini 3.8 Live Extended Thinking, model ID gemini-3.8-live-extended-thinking, supports background reasoning during live audio and is recommended when more reasoning is needed.

Why it matters: The changelog names two model IDs and their intended use, showing how Live API developers can choose between low-latency voice and higher background reasoning.

AIOpenAI has made GPT-Live-1 available in the API, letting developers build voice apps on the same duplex technology used in the new ChatGPT voice. The quoted announcement says the voice agents can listen while they speak and work with the models and harness developers choose.

AIGPT-Live-1 is now available in the API, letting developers bring ChatGPT-style back-and-forth conversation into their apps. The quoted announcement says the voice agents can listen while they speak and can work with the models and harness developers choose.

Why it matters: The quoted announcement describes a real-time voice model entering the API, which matters for builders weighing voice agents against existing stacks.

AIMicrosoft released Azure AI Speech LLM 2607, which improves multilingual recognition, mixed-language audio handling, and domain-specific entity accuracy, and runs up to 3x faster than the previous 2605 release. A new dedicated phrase list parameter lets developers supply domain vocabulary, supporting 2,000+ entities, without embedding it in a prompt. The model is available through the Fast API and Real-Time API, is testable in the Foundry Playground, and is deployed automatically with no customer action required.

AITencent Hunyuan has released AuK, an open-source foundation model for unified speech generation and editing that takes natural-language instructions and reference audio. It supports tasks including zero-shot TTS, timbre, style and emotion editing, denoising, and music separation. A companion AuK-Flash variant runs 4-step inference and is about 4.5 times faster under matched conditions, with code, weights, and a demo now available.

AIMicrosoft Foundry's July and August 2026 updates make Hosted Agents, Voice Live integration, and Toolboxes generally available. The post adds Claude tools on Azure, Model Router region and model pool changes, Foundry Local preview features, and updated Python, JavaScript, Java, and .NET SDK versions with migration notes.

Why it matters: The roundup links each GA and preview change to code examples, migration notes, and runtime requirements, which helps developers judge what to upgrade and test first.

AIOpenAI's ChatGPT Voice can now use GPT-6 Astra, available to Pro users, for search and reasoning tasks. Users can select any model and effort level, and voice will use the chosen model when it needs to search or reason.

AIGoogle is rolling out new Gemini voice capabilities that let Google AI subscribers search their Gmail inbox, organize thoughts and tasks in Keep, and create new Docs conversationally. The company highlights Docs Live as especially helpful, with a demo included in the post.

AIMicrosoft AI's MAI-Transcribe-2 is a transcription model that the company says offers the highest quality and lowest price at the fastest speed. Microsoft claims it runs 10x faster than GPT-Transcribe, and it is now available on Microsoft Foundry.

AIBAAI and Hao Tang's team at Peking University's School of Computer Science released GaussianMind, an audio-language model built on RoboBrain and OpenMOSS Audio. The model is available on Hugging Face and loads through custom Transformers code with trust_remote_code=True.