Loading video...

Video Failed to Load

Go Home

Today we’re introducing Gemini 3.5 Transcribe, our latest transcription model built for incredibly precise, smart dictation across your favorite apps and devices. Remember when traditional speech-to-text meant shouting over background noise, constantly hitting backspace to fix misspelled words, and manually deleting every "um" and "uh"? Those days are over....

GoogleAI's profile picture

Google AI

2,445,450 subscribers

97,388 views • 1 day ago •via X (Twitter)

Science & TechnologyNews & Politics
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Today, we’re introducing Gemini 3.5 Transcribe, our most precise speech-to-text model yet, designed for intelligent voice interactions in Google Antigravity. It pairs screen context and chat history, with your permission, to ensure pinpoint transcription accuracy across file names, agent thoughts, and active documents.
0:32

Today, we’re introducing Gemini 3.5 Transcribe, our most precise speech-to-text model yet, designed for intelligent voice interactions in Google Antigravity. It pairs screen context and chat history, with your permission, to ensure pinpoint transcription accuracy across file names, agent thoughts, and active documents.

Google Antigravity

129,616 views • 1 day ago

introducing Gemini 3.5 Transcribe: our most precise speech-to-text model yet, designed for intelligent voice interactions this new model: - seamlessly handles self-corrections - removes filler words to deliver clean, formatted text - understands your natural intent and speaking style - captures audio, even in noisy environments - supports 85+ languages, including regional accents and diverse dialects try it today in the Gemini API and in AI Studio
0:44

introducing Gemini 3.5 Transcribe: our most precise speech-to-text model yet, designed for intelligent voice interactions this new model: - seamlessly handles self-corrections - removes filler words to deliver clean, formatted text - understands your natural intent and speaking style - captures audio, even in noisy environments - supports 85+ languages, including regional accents and diverse dialects try it today in the Gemini API and in AI Studio

Google AI Studio

222,094 views • 1 day ago

Introducing Gemini 3.5 Transcribe 🚀 Our most precise speech to text model, that can handle over 85+ languages, has smart correction, and custom vocabulary. I vibe coded a Wispr Flow like app powered by the model. Demo + open sourcing below!
2:05

Introducing Gemini 3.5 Transcribe 🚀 Our most precise speech to text model, that can handle over 85+ languages, has smart correction, and custom vocabulary. I vibe coded a Wispr Flow like app powered by the model. Demo + open sourcing below!

Ammaar Reshi

210,504 views • 1 day ago

Google just launched Gemini 3.5 Transcribe, its most precise speech-to-text model yet. I built this app using Gemini 3.5 Transcribe and have been playing with the model for quite some time. Thanks to the Google DeepMind team for the early access. It’s already available in the Gemini API, AI Studio, and Antigravity, and is now in public preview.
2:03

Google just launched Gemini 3.5 Transcribe, its most precise speech-to-text model yet. I built this app using Gemini 3.5 Transcribe and have been playing with the model for quite some time. Thanks to the Google DeepMind team for the early access. It’s already available in the Gemini API, AI Studio, and Antigravity, and is now in public preview.

AshutoshShrivastava

14,668 views • 1 day ago

Introducing Gemini 3.5 Transcribe, our most precise speech-to-text model yet, designed for intelligent voice interactions! 💬 Available for both real-time speech and audio file transcription, with support for: 💡 smart transcription: rewrite and format text based on intent. 🌍 support for 85+ languages, regional accents and diverse dialects. 📚 custom vocabulary: recognize jargon and specific spellings. 💯 high precision in alphanumerics. 🫂 multi-speaker identification.
4:49

Introducing Gemini 3.5 Transcribe, our most precise speech-to-text model yet, designed for intelligent voice interactions! 💬 Available for both real-time speech and audio file transcription, with support for: 💡 smart transcription: rewrite and format text based on intent. 🌍 support for 85+ languages, regional accents and diverse dialects. 📚 custom vocabulary: recognize jargon and specific spellings. 💯 high precision in alphanumerics. 🫂 multi-speaker identification.

Thor 雷神 ⚡️

20,264 views • 1 day ago

This is dope update for Gemini macOS app 🔥 You can now long press the Fn key and simply talk to Gemini from anywhere on your Mac. By default, it works as an intelligent dictation tool that: - Removes "ums" and "ahs" - Cleans up mid sentence corrections - Formats your text automatically - Pastes polished text directly where your cursor is Enable Gemini Reasoning, and it can do even more by understanding what's on your screen. For example, you can: - Summarize documents, PDFs, and images - Rewrite highlighted text in any tone - Turn notes into polished emails or executive summaries - Generate and edit images using voice commands Instead of switching between apps, you can just speak naturally and Gemini handles the rest. This update is rolling out globally in English for the Gemini app on macOS, with more languages coming soon. Video credit: Google Blog
1:41

This is dope update for Gemini macOS app 🔥 You can now long press the Fn key and simply talk to Gemini from anywhere on your Mac. By default, it works as an intelligent dictation tool that: - Removes "ums" and "ahs" - Cleans up mid sentence corrections - Formats your text automatically - Pastes polished text directly where your cursor is Enable Gemini Reasoning, and it can do even more by understanding what's on your screen. For example, you can: - Summarize documents, PDFs, and images - Rewrite highlighted text in any tone - Turn notes into polished emails or executive summaries - Generate and edit images using voice commands Instead of switching between apps, you can just speak naturally and Gemini handles the rest. This update is rolling out globally in English for the Gemini app on macOS, with more languages coming soon. Video credit: Google Blog

AshutoshShrivastava

14,630 views • 28 days ago

1/ Typeless Dictate (Press "Fn" Key): ☑️ Eliminates filler words — Automatically removes fillers like "um," "uh," and "you know," enhancing the clarity and professionalism of your transcriptions. ☑️ Eliminates repetition — Detects and removes redundant words in your speech, ensuring concise and easily comprehensible language. ☑️ Auto-edits when you change your mind — Typeless captures your corrections and retains only your intended message, reducing confusion. ☑️ Auto-formats — Structures spoken lists, steps, and key points into neat text, eliminating the need for manual formatting. ☑️ Find the perfect words — Typeless helps you articulate ideas clearly, ensuring your message is easily understood. ☑️ Customized style and tone — Adapts to your unique tone and writing habits, making dictation feel personal. Progress tracking shows how well Typeless matches your communication style. ☑️ Understands any accent and pronunciations — You don't need to be perfect when speaking to typeless, it will type for you exactly what you wanted. ☑️ Supports 100+ languages — Speak any language or mix them, with Typeless automatically detecting and transcribing your speech effortlessly. Watch as I try to dictate statements with so many errors and Typeless is going to fix them for me:
3:14

1/ Typeless Dictate (Press "Fn" Key): ☑️ Eliminates filler words — Automatically removes fillers like "um," "uh," and "you know," enhancing the clarity and professionalism of your transcriptions. ☑️ Eliminates repetition — Detects and removes redundant words in your speech, ensuring concise and easily comprehensible language. ☑️ Auto-edits when you change your mind — Typeless captures your corrections and retains only your intended message, reducing confusion. ☑️ Auto-formats — Structures spoken lists, steps, and key points into neat text, eliminating the need for manual formatting. ☑️ Find the perfect words — Typeless helps you articulate ideas clearly, ensuring your message is easily understood. ☑️ Customized style and tone — Adapts to your unique tone and writing habits, making dictation feel personal. Progress tracking shows how well Typeless matches your communication style. ☑️ Understands any accent and pronunciations — You don't need to be perfect when speaking to typeless, it will type for you exactly what you wanted. ☑️ Supports 100+ languages — Speak any language or mix them, with Typeless automatically detecting and transcribing your speech effortlessly. Watch as I try to dictate statements with so many errors and Typeless is going to fix them for me:

Wesley

22,460 views • 6 months ago

Today, we released Gemini 3.5 Live Translate, our latest audio model for live speech-to-speech translation. It supports over 70 languages and starts translating as soon as you start talking, streaming translations while listening to what you say next. No awkward pauses or choppy audio, just real connection without language barriers. So, how does it work? 🤔 The model is able to make split-second decisions to juggle speed and translation quality so conversations actually feel fluid, human, and natural. In order to do this, the model must receive and contextualize the input while simultaneously outputting the translated speech. Through this process, Gemini 3.5 Live Translate manages to stay mere seconds behind each speaker and can even maintain pacing, pitch, and intonation across extended sessions. See it in action below, or try it yourself in the Google Translate app on iOS & Android.
0:25

Today, we released Gemini 3.5 Live Translate, our latest audio model for live speech-to-speech translation. It supports over 70 languages and starts translating as soon as you start talking, streaming translations while listening to what you say next. No awkward pauses or choppy audio, just real connection without language barriers. So, how does it work? 🤔 The model is able to make split-second decisions to juggle speed and translation quality so conversations actually feel fluid, human, and natural. In order to do this, the model must receive and contextualize the input while simultaneously outputting the translated speech. Through this process, Gemini 3.5 Live Translate manages to stay mere seconds behind each speaker and can even maintain pacing, pitch, and intonation across extended sessions. See it in action below, or try it yourself in the Google Translate app on iOS & Android.

Google AI

3,987,766 views • 2 months ago

Typing just became… Typeless. Meet Typeless 1.0.2 for Mac — a tool that transforms your voice into clear, accurate writing across your Mac. Speak naturally and let Typeless handle the typing, corrections, and structure for you. With Typeless, you can dictate, translate, or ask for quick edits in any language or accent. It converts your speech into polished text up to 10× faster than traditional typing, while automatically fixing mistakes along the way. --- 1️⃣ Dictation Typeless acts as a powerful voice keyboard that works across all applications on your Mac. When you speak, it understands your intent, organizes your ideas, and converts your natural speech into well-structured writing. Whether you're drafting emails, notes, documents, or messages, Typeless helps you turn spoken thoughts into clean text instantly. Controls - Press Fn to start or stop dictation - Hold Fn for quick, short dictation --- 2️⃣ Translation Typeless makes writing in other languages effortless. You can speak in your native language and have Typeless translate your words instantly into the language you want. This allows you to communicate, write, and respond in foreign languages smoothly and naturally. Controls - Press Fn + Space to start translation - Press Fn to stop translation --- 3️⃣ Ask Anything Typeless Typeless also lets you interact with your text using voice commands. You can select any text and simply say how you want it changed. Typeless can edit, rewrite, answer questions, or perform quick actions based on your request, making editing and improving text much faster. Controls - Press Fn + Space to start Ask Anything - Press Fn to stop Ask Anything --- With Typeless, your voice becomes the fastest and easiest way to write, edit, and communicate on your Mac. Your voice is now your keyboard. Get Typeless → Available now on Mac, Windows, iOS, and Android. #Typeless
5:30

Typing just became… Typeless. Meet Typeless 1.0.2 for Mac — a tool that transforms your voice into clear, accurate writing across your Mac. Speak naturally and let Typeless handle the typing, corrections, and structure for you. With Typeless, you can dictate, translate, or ask for quick edits in any language or accent. It converts your speech into polished text up to 10× faster than traditional typing, while automatically fixing mistakes along the way. --- 1️⃣ Dictation Typeless acts as a powerful voice keyboard that works across all applications on your Mac. When you speak, it understands your intent, organizes your ideas, and converts your natural speech into well-structured writing. Whether you're drafting emails, notes, documents, or messages, Typeless helps you turn spoken thoughts into clean text instantly. Controls - Press Fn to start or stop dictation - Hold Fn for quick, short dictation --- 2️⃣ Translation Typeless makes writing in other languages effortless. You can speak in your native language and have Typeless translate your words instantly into the language you want. This allows you to communicate, write, and respond in foreign languages smoothly and naturally. Controls - Press Fn + Space to start translation - Press Fn to stop translation --- 3️⃣ Ask Anything Typeless Typeless also lets you interact with your text using voice commands. You can select any text and simply say how you want it changed. Typeless can edit, rewrite, answer questions, or perform quick actions based on your request, making editing and improving text much faster. Controls - Press Fn + Space to start Ask Anything - Press Fn to stop Ask Anything --- With Typeless, your voice becomes the fastest and easiest way to write, edit, and communicate on your Mac. Your voice is now your keyboard. Get Typeless → Available now on Mac, Windows, iOS, and Android. #Typeless

Kuria Chronicles

43,623 views • 5 months ago

Greetings. I've just pressed the option key and now I am holding it, which is why you see that small reddish capsule at the top of my screen, flashing in synchrony with my voice volume, etcetera. Anyway, I hope that didn't somehow clip the audio. The reason I'm doing this is to show off the fact that I've integrated NVIDIA's new parakeet, or relatively new parakeet, voice transcription speech to text model into Hex, my open source free Mac audio transcription tool. And Parakeet is ridiculously fast, so I will stop rambling in just a moment and release the option key, and it will transcribe and paste into the text box. So yeah, that was very fast. Faster than Whisper. Certainly faster and more accurate than Mac dictation. Uh so yeah, give it a shot and enjoy. The download link to Hex will be uh pasted beneath this transcription.
0:59

Greetings. I've just pressed the option key and now I am holding it, which is why you see that small reddish capsule at the top of my screen, flashing in synchrony with my voice volume, etcetera. Anyway, I hope that didn't somehow clip the audio. The reason I'm doing this is to show off the fact that I've integrated NVIDIA's new parakeet, or relatively new parakeet, voice transcription speech to text model into Hex, my open source free Mac audio transcription tool. And Parakeet is ridiculously fast, so I will stop rambling in just a moment and release the option key, and it will transcribe and paste into the text box. So yeah, that was very fast. Faster than Whisper. Certainly faster and more accurate than Mac dictation. Uh so yeah, give it a shot and enjoy. The download link to Hex will be uh pasted beneath this transcription.

Kit Langton

14,301 views • 9 months ago

Typing on my phone was second nature until I ditched it for good. Introducing Typeless | Typeless on Android: speak, and your words become polished text in an instant. The pioneer voice keyboard on Android, it seamlessly integrates across platforms—WhatsApp, Slack, emails, Notes, even ChatGPT. Just speak naturally, and let Typeless handle the magic. Here’s what grabbed my attention 👇 - Cuts out filler words like “um” and “uh” ✂️ - Eliminates repetition for precise text 🔁 - Adapts when you self-correct mid-sentence 🔄 - Converts spoken points into sharp, formatted content 🗣️📝 - Tailors tone to match the app you're in 🎨 - Supports over 100 languages, including mixed speech 🌍 - Adapts to your writing style over time 🕰️ - Allows custom words via a personal dictionary 📚 Privacy triumphs: No data storage, no data training—everything stays on your device. On mobile, it’s faster than typing. Stuck on your phone for writing? This is a game-changer. Download the Android app: Available on iOS, Mac, Windows: #WorkSmarter #ProductivityTools #VoiceTyping #Typeless
1:58

Typing on my phone was second nature until I ditched it for good. Introducing Typeless | Typeless on Android: speak, and your words become polished text in an instant. The pioneer voice keyboard on Android, it seamlessly integrates across platforms—WhatsApp, Slack, emails, Notes, even ChatGPT. Just speak naturally, and let Typeless handle the magic. Here’s what grabbed my attention 👇 - Cuts out filler words like “um” and “uh” ✂️ - Eliminates repetition for precise text 🔁 - Adapts when you self-correct mid-sentence 🔄 - Converts spoken points into sharp, formatted content 🗣️📝 - Tailors tone to match the app you're in 🎨 - Supports over 100 languages, including mixed speech 🌍 - Adapts to your writing style over time 🕰️ - Allows custom words via a personal dictionary 📚 Privacy triumphs: No data storage, no data training—everything stays on your device. On mobile, it’s faster than typing. Stuck on your phone for writing? This is a game-changer. Download the Android app: Available on iOS, Mac, Windows: #WorkSmarter #ProductivityTools #VoiceTyping #Typeless

Atul Kumar

52,796 views • 7 months ago

Google just shipped a free dictation app for Mac and iPhone called AI Edge Eloquent, and the model running it is Gemma 4 12B, entirely on your device. What it actually does: you speak, it transcribes, removes filler words, and polishes the result before dropping clean text into whatever app you are using. You can also give it voice commands to reformat, like "translate to Hindi" or "make this a bullet list." Audio and video file transcription is built in too. The interesting part is the privacy angle. Most AI writing tools send your audio to a server. This one never leaves your machine, which matters if you are dictating anything sensitive. The tradeoff is hardware: you need a Mac with at least 16GB of RAM to run a 12B parameter model comfortably.
1:15

Google just shipped a free dictation app for Mac and iPhone called AI Edge Eloquent, and the model running it is Gemma 4 12B, entirely on your device. What it actually does: you speak, it transcribes, removes filler words, and polishes the result before dropping clean text into whatever app you are using. You can also give it voice commands to reformat, like "translate to Hindi" or "make this a bullet list." Audio and video file transcription is built in too. The interesting part is the privacy angle. Most AI writing tools send your audio to a server. This one never leaves your machine, which matters if you are dictating anything sensitive. The tradeoff is hardware: you need a Mac with at least 16GB of RAM to run a 12B parameter model comfortably.

Aditya ⚡Rao

85,060 views • 2 months ago

🚨 BREAKING A new AI app by Every 📧 launches today: Monologue Monologue is a smart voice dictation app for Mac that lets you work 3x faster without breaking flow. It’s already being used by people like Ben Tossell, Nat Eliason, and Julien Chaumond to write over 1 million words a week. Most voice dictation apps flatten your voice. Monologue is different. It understands your vocabulary, your apps, and your style, so nothing gets lost in translation. What you get: - Smart formatting: Text comes out polished and structured for the app you’re in—no cleanup needed. - Personal dictionary: Proper nouns, acronyms, and slang are remembered automatically. - Deep context: With permission, Monologue sees your screen so it knows what you’re referencing. - Multilingual by default: Dictate in 100-plus languages and switch between them effortlessly. - Flexible modes: Use prebuilt workflows (email, docs, notes, code) or design your own. - Local models: Use Monologue without sending your information to the cloud. We want Every 📧 to be the only subscription you need to stay at the edge of AI. That's why Monologue is available now for free for Every 📧 paid subscribers along with Cora, Sparkle, and Spiral—all for just $30 / month. Or you can use Monologue standalone for just $10 / month if you sign up during our early bird period. Try Monologue now →
0:49

🚨 BREAKING A new AI app by Every 📧 launches today: Monologue Monologue is a smart voice dictation app for Mac that lets you work 3x faster without breaking flow. It’s already being used by people like Ben Tossell, Nat Eliason, and Julien Chaumond to write over 1 million words a week. Most voice dictation apps flatten your voice. Monologue is different. It understands your vocabulary, your apps, and your style, so nothing gets lost in translation. What you get: - Smart formatting: Text comes out polished and structured for the app you’re in—no cleanup needed. - Personal dictionary: Proper nouns, acronyms, and slang are remembered automatically. - Deep context: With permission, Monologue sees your screen so it knows what you’re referencing. - Multilingual by default: Dictate in 100-plus languages and switch between them effortlessly. - Flexible modes: Use prebuilt workflows (email, docs, notes, code) or design your own. - Local models: Use Monologue without sending your information to the cloud. We want Every 📧 to be the only subscription you need to stay at the edge of AI. That's why Monologue is available now for free for Every 📧 paid subscribers along with Cora, Sparkle, and Spiral—all for just $30 / month. Or you can use Monologue standalone for just $10 / month if you sign up during our early bird period. Try Monologue now →

Dan Shipper 📧

258,622 views • 11 months ago

STOP Typing AND START Speaking Using my phone for typing felt second nature until I discovered a new way. With Typeless | Typeless on Android, I just speak, and my words transform instantly into polished text. It's among the pioneering voice keyboards on Android that genuinely grasps conversational speech. Typeless seamlessly integrates with WhatsApp, Slack, emails, Notes, and even ChatGPT. I simply speak, and Typeless handles everything else. Here’s what impressed me 👇 - Automatically filters out fillers like “um” and “uh” - Eliminates redundancy for succinct text - Recognizes mid-sentence corrections - Converts spoken ideas into neat, structured text - Tailors tone to match each app - Supports over 100 languages, including mixed language input - Adapts to your writing style over time - Allows custom vocabulary with a personal dictionary A standout feature: complete privacy with no data storage or external data training. Everything stays on your device. For mobile, it genuinely feels quicker than traditional typing. If your phone is your writing hub, give this a shot. Download the Android app: Available on Android, iOS, Mac, and Windows: #WorkSmarter #ProductivityTools #VoiceTyping #Typeless
1:18

STOP Typing AND START Speaking Using my phone for typing felt second nature until I discovered a new way. With Typeless | Typeless on Android, I just speak, and my words transform instantly into polished text. It's among the pioneering voice keyboards on Android that genuinely grasps conversational speech. Typeless seamlessly integrates with WhatsApp, Slack, emails, Notes, and even ChatGPT. I simply speak, and Typeless handles everything else. Here’s what impressed me 👇 - Automatically filters out fillers like “um” and “uh” - Eliminates redundancy for succinct text - Recognizes mid-sentence corrections - Converts spoken ideas into neat, structured text - Tailors tone to match each app - Supports over 100 languages, including mixed language input - Adapts to your writing style over time - Allows custom vocabulary with a personal dictionary A standout feature: complete privacy with no data storage or external data training. Everything stays on your device. For mobile, it genuinely feels quicker than traditional typing. If your phone is your writing hub, give this a shot. Download the Android app: Available on Android, iOS, Mac, and Windows: #WorkSmarter #ProductivityTools #VoiceTyping #Typeless

Parul Gautam

58,863 views • 7 months ago

Today, we’re introducing new tools and model updates to help you build, deploy, and scale Voice AI applications.🎙️ 🆕 Speech Understanding: Turn transcripts into actionable data with speaker identification, custom formatting & translation 🆕 LLM Gateway: One API for your voice-to-intelligence pipeline, with GPT, Claude, Gemini & more 🆕 Voice AI Guardrails: End-to-end protection for safe, compliant content Model Upgrades: ✅ 99 languages with auto code-switching ✅ 64% fewer speaker counting errors ✅ 57% better accuracy on critical terms with 1,000-word context Real results: 🔥 Calabrio: 80% boost in customer satisfaction, 22% revenue increase 🔥 Siro: "10/10 customers say 'wow, that insight was crisp'" Build & scale Voice AI in minutes! Try it in our Playground or check the docs. 🚀
0:58

Today, we’re introducing new tools and model updates to help you build, deploy, and scale Voice AI applications.🎙️ 🆕 Speech Understanding: Turn transcripts into actionable data with speaker identification, custom formatting & translation 🆕 LLM Gateway: One API for your voice-to-intelligence pipeline, with GPT, Claude, Gemini & more 🆕 Voice AI Guardrails: End-to-end protection for safe, compliant content Model Upgrades: ✅ 99 languages with auto code-switching ✅ 64% fewer speaker counting errors ✅ 57% better accuracy on critical terms with 1,000-word context Real results: 🔥 Calabrio: 80% boost in customer satisfaction, 22% revenue increase 🔥 Siro: "10/10 customers say 'wow, that insight was crisp'" Build & scale Voice AI in minutes! Try it in our Playground or check the docs. 🚀

AssemblyAI

18,157 views • 10 months ago

We’re shipping two major updates to streamline your creative workflow, allowing you to generate high-speed images with one model and then instantly animate them with the other—all at a fraction of the cost 🍌⚡️ 1️⃣ Introducing Nano Banana 2 Lite: Our fastest and most cost-efficient Gemini Image model yet delivers text-to-image outputs in under 4 seconds. Now available via the Gemini API and Google AI Studio, and rolling out soon across @NotebookLM, Google Flow, Google Gemini, Stitch by Google, Google Search and Google Photos. 2️⃣ Gemini Omni Flash in Public Preview: Our natively multimodal model for cost-efficient video generation and conversational editing. Now available via the Gemini API, Google AI Studio, and Gemini Enterprise Agent Platform so you can integrate the model into your workflow. While exciting on their own, the real magic happens when you build using these models together. Watch how our interior design demo integrates Nano Banana 2 Lite and Omni to instantly reimagine any space. Upload a photo, swipe through tailored design concepts, and see Omni bring the details to life in cinematic motion. Try out the demo app in AI Studio:
0:27

We’re shipping two major updates to streamline your creative workflow, allowing you to generate high-speed images with one model and then instantly animate them with the other—all at a fraction of the cost 🍌⚡️ 1️⃣ Introducing Nano Banana 2 Lite: Our fastest and most cost-efficient Gemini Image model yet delivers text-to-image outputs in under 4 seconds. Now available via the Gemini API and Google AI Studio, and rolling out soon across @NotebookLM, Google Flow, Google Gemini, Stitch by Google, Google Search and Google Photos. 2️⃣ Gemini Omni Flash in Public Preview: Our natively multimodal model for cost-efficient video generation and conversational editing. Now available via the Gemini API, Google AI Studio, and Gemini Enterprise Agent Platform so you can integrate the model into your workflow. While exciting on their own, the real magic happens when you build using these models together. Watch how our interior design demo integrates Nano Banana 2 Lite and Omni to instantly reimagine any space. Upload a photo, swipe through tailored design concepts, and see Omni bring the details to life in cinematic motion. Try out the demo app in AI Studio:

Google AI

128,680 views • 1 month ago

Sarvam Beats GPT-4o: India’s New AI Model Claims Top Spot in Indic Speech Sarvam AI, an Indian startup, recently launched Sarvam Audio, a speech recognition model that claims superior performance over GPT-4o Transcribe on Indic language benchmarks. This development highlights India's push for AI sovereignty in handling local linguistic nuances. Sarvam Audio supports 22 Indian languages from the Eighth Schedule, plus Indian English, with strong handling of code-mixing like Hindi-English blends. It features built-in speaker diarization for up to eight speakers and processes long-form audio such as podcasts or meetings. Trained on the IndicVoices dataset 12,000 hours from over 16,000 speakers across 208 districts it captures real-world noise and spontaneous speech. The model reportedly outperforms GPT-4o Transcribe and Gemini 3 Flash in transcription accuracy (lower Word Error Rate) on IndicVoices benchmarks for unnormalized, normalized, and code-mixed speech. Sarvam attributes this to specialization on Indian accents and patterns, unlike global models trained on Western data. Detailed public benchmarks are pending independent verification. Key Applications 🔴 Call centers and logistics for multilingual transcription. 🔴 Banking, fintech, and e-commerce for customer interactions. 🔴 Podcasts, meetings, and lectures via API for real-time or batch processing. ​ 🔴 This B2B-focused tool aligns with India's IndiaAI Mission, backed by government GPU access for sovereign LLMs. Credit : AIM Networks.
5:20

Sarvam Beats GPT-4o: India’s New AI Model Claims Top Spot in Indic Speech Sarvam AI, an Indian startup, recently launched Sarvam Audio, a speech recognition model that claims superior performance over GPT-4o Transcribe on Indic language benchmarks. This development highlights India's push for AI sovereignty in handling local linguistic nuances. Sarvam Audio supports 22 Indian languages from the Eighth Schedule, plus Indian English, with strong handling of code-mixing like Hindi-English blends. It features built-in speaker diarization for up to eight speakers and processes long-form audio such as podcasts or meetings. Trained on the IndicVoices dataset 12,000 hours from over 16,000 speakers across 208 districts it captures real-world noise and spontaneous speech. The model reportedly outperforms GPT-4o Transcribe and Gemini 3 Flash in transcription accuracy (lower Word Error Rate) on IndicVoices benchmarks for unnormalized, normalized, and code-mixed speech. Sarvam attributes this to specialization on Indian accents and patterns, unlike global models trained on Western data. Detailed public benchmarks are pending independent verification. Key Applications 🔴 Call centers and logistics for multilingual transcription. 🔴 Banking, fintech, and e-commerce for customer interactions. 🔴 Podcasts, meetings, and lectures via API for real-time or batch processing. ​ 🔴 This B2B-focused tool aligns with India's IndiaAI Mission, backed by government GPU access for sovereign LLMs. Credit : AIM Networks.

Augadh

43,429 views • 6 months ago

QVAC SDK 0.14.0 is live. This release makes the on-device stack faster on mobile, ships the developer-agent path, and takes local text-to-speech to 31 languages. Main highlights: - OpenCode and OpenClaw. The first official OpenCode plugin, plus a maintained OpenClaw compatibility path, both built on managed mode and qvac serve. Point a coding agent at a local model with far less setup and far fewer surprises. - Brain-computer interface transcription, on the SDK. Take recorded neural signal data and decode it into text, fully on-device, no cloud. Stream it in chunks through a simple API. In 0.14 it runs GPU-accelerated on iOS. - Text to Speech in 31 languages with our Supertonic3 upgrade. VOICE AND SPEECH - Supertonic3 multilingual TTS, 5 languages to 31. - Chatterbox and Supertonic now run on the Android GPU, with lower memory use (especially on iOS), quantized s3gen Chatterbox support, and a fix for Chatterbox occasionally emitting random speech. - Whisper transcription now runs on the iOS GPU. Parakeet runs on the Android GPU, with steadier real-time streaming. VISION AND OCR - VLM multi-tile batching: high-resolution Pan and Scan images are encoded in one pass instead of tile by tile, for faster vision throughput. - OCR on ggml (EasyOCR and DocTR) reaches full speed parity with the onnx path, across Metal, OpenCL, and Vulkan. PLATFORM AND RELIABILITY - Dynamic compute backends on Linux: one build picks the right backend at runtime, and opens the door to ROCm and CUDA support without per-backend builds. - Thinking tokens are kept out of the model context, so reasoning no longer fills the KV cache. SDK 0.14.0 is now leaner and faster to start. Let’s build.
1:51

QVAC SDK 0.14.0 is live. This release makes the on-device stack faster on mobile, ships the developer-agent path, and takes local text-to-speech to 31 languages. Main highlights: - OpenCode and OpenClaw. The first official OpenCode plugin, plus a maintained OpenClaw compatibility path, both built on managed mode and qvac serve. Point a coding agent at a local model with far less setup and far fewer surprises. - Brain-computer interface transcription, on the SDK. Take recorded neural signal data and decode it into text, fully on-device, no cloud. Stream it in chunks through a simple API. In 0.14 it runs GPU-accelerated on iOS. - Text to Speech in 31 languages with our Supertonic3 upgrade. VOICE AND SPEECH - Supertonic3 multilingual TTS, 5 languages to 31. - Chatterbox and Supertonic now run on the Android GPU, with lower memory use (especially on iOS), quantized s3gen Chatterbox support, and a fix for Chatterbox occasionally emitting random speech. - Whisper transcription now runs on the iOS GPU. Parakeet runs on the Android GPU, with steadier real-time streaming. VISION AND OCR - VLM multi-tile batching: high-resolution Pan and Scan images are encoded in one pass instead of tile by tile, for faster vision throughput. - OCR on ggml (EasyOCR and DocTR) reaches full speed parity with the onnx path, across Metal, OpenCL, and Vulkan. PLATFORM AND RELIABILITY - Dynamic compute backends on Linux: one build picks the right backend at runtime, and opens the door to ROCm and CUDA support without per-backend builds. - Thinking tokens are kept out of the model context, so reasoning no longer fills the KV cache. SDK 0.14.0 is now leaner and faster to start. Let’s build.

QVAC

23,973,950 views • 1 month ago

We’re excited to announce the release and open-source of HunyuanImage 3.0 — the largest and most powerful open-source text-to-image model to date, with over 80 billion total parameters, of which 13 billion are activated per token during inference.The effect is completely comparable to the industry’s flagship closed-source model.🚀🚀🚀 HunyuanImage 3.0 originates from our internally developed native multimodal large language model, with fine-tuning and post-training focused on text-to-image generation. This unique foundation gives the model a powerful set of capabilities: ✅Reason with world knowledge ✅Understand complex, thousand-word prompts ✅Generate precise text within images Different from traditional DiT architecture image generation models, HunyuanImage 3.0’s MoE architecture uses a Transfusion-based approach to deeply couple Diffusion and LLM training for a single, powerful system. Built on Hunyuan-A13B, HunyuanImage 3.0 was trained on a massive dataset: 5 billion image-text pairs, video frames, interleaved image-text data, and 6 trillion tokens of text corpora. This hybrid training across multimodal generation, understanding, and LLM capabilities allows the model to seamlessly integrate multiple tasks. Whether you're an illustrator, designer, or creator, this is built to slash your workflow from hours to minutes. HunyuanImage 3.0 can generate intricate text, detailed comics, expressive emojis, and lively, engaging illustrations for educational content. The current release focuses solely on text-to-image generation and future updates will include image-to-image, image editing, multi-turn interaction, and more. 👉🏻Try it now: 🔗GitHub: 🤗Hugging Face:
2:09

We’re excited to announce the release and open-source of HunyuanImage 3.0 — the largest and most powerful open-source text-to-image model to date, with over 80 billion total parameters, of which 13 billion are activated per token during inference.The effect is completely comparable to the industry’s flagship closed-source model.🚀🚀🚀 HunyuanImage 3.0 originates from our internally developed native multimodal large language model, with fine-tuning and post-training focused on text-to-image generation. This unique foundation gives the model a powerful set of capabilities: ✅Reason with world knowledge ✅Understand complex, thousand-word prompts ✅Generate precise text within images Different from traditional DiT architecture image generation models, HunyuanImage 3.0’s MoE architecture uses a Transfusion-based approach to deeply couple Diffusion and LLM training for a single, powerful system. Built on Hunyuan-A13B, HunyuanImage 3.0 was trained on a massive dataset: 5 billion image-text pairs, video frames, interleaved image-text data, and 6 trillion tokens of text corpora. This hybrid training across multimodal generation, understanding, and LLM capabilities allows the model to seamlessly integrate multiple tasks. Whether you're an illustrator, designer, or creator, this is built to slash your workflow from hours to minutes. HunyuanImage 3.0 can generate intricate text, detailed comics, expressive emojis, and lively, engaging illustrations for educational content. The current release focuses solely on text-to-image generation and future updates will include image-to-image, image editing, multi-turn interaction, and more. 👉🏻Try it now: 🔗GitHub: 🤗Hugging Face:

Tencent Hy

412,880 views • 11 months ago

Voice-only programming with the new OpenAI Realtime API ... I spend a lot of time these days pair programming with LLMs. Often I'm talking rather than typing. This "voice dictation" use case has become an important vibe benchmark for me. Being able to create text input just by talking, flexibly, in a context dependent way, with tool calling, is a *hard* problem for today's models. Natural language dictation requires a very high degree of contextual intelligence, instruction following accuracy, and tool calling reliability. Today's new gpt-realtime model is quite good at this hard problem. The original realtime model release last year was impressive. Seeing what a speech-to-speech model could do got a lot of people excited about the possibilities of voice AI. The improvements since that first release are equally impressive. I can use this new model, now, for real world tasks that were past the edge of the "jagged frontier" before. Here's a video showing a couple of fun (and tricky) modes of voice input.
2:40

Voice-only programming with the new OpenAI Realtime API ... I spend a lot of time these days pair programming with LLMs. Often I'm talking rather than typing. This "voice dictation" use case has become an important vibe benchmark for me. Being able to create text input just by talking, flexibly, in a context dependent way, with tool calling, is a *hard* problem for today's models. Natural language dictation requires a very high degree of contextual intelligence, instruction following accuracy, and tool calling reliability. Today's new gpt-realtime model is quite good at this hard problem. The original realtime model release last year was impressive. Seeing what a speech-to-speech model could do got a lot of people excited about the possibilities of voice AI. The improvements since that first release are equally impressive. I can use this new model, now, for real world tasks that were past the edge of the "jagged frontier" before. Here's a video showing a couple of fun (and tricky) modes of voice input.

kwindla

50,874 views • 1 year ago