正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

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. 📚... show more

Thor 雷神 ⚡️

12,603 subscribers

23,056 次观看 • 1 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

25 条评论

Logan Kilpatrick 的头像

Logan Kilpatrick1 个月前

amazing working getting this model out : )

Thor 雷神 ⚡️ 的头像

Thor 雷神 ⚡️1 个月前

Thanks, Logan 🫶 So excited to see what folks will build 🚀

Thor 雷神 ⚡️ 的头像

Thor 雷神 ⚡️1 个月前

Available now on the Gemini API, @GoogleAIStudio, and many other awesome products like Gboard, @antigravity, the Gemini app, and @googlechrome!

Philipp Schmid 的头像

Philipp Schmid1 个月前

So cool!

Jonathan Ouyang 的头像

Jonathan Ouyang1 个月前

Multi speaker is huge 🗣️

⟁ndrew V 的头像

⟁ndrew V1 个月前

Tour dates for debut album wen?

Thor 雷神 ⚡️ 的头像

Thor 雷神 ⚡️1 个月前

Catch me in Buenos Aires soon!

Pedro Amaral 的头像

Pedro Amaral1 个月前

Google AI Edge Eloquent became the local AI app i can’t recommend enough to those i know as it’s the first thing i launch on my phone & mac. hope this gets integrated into the app in some way

Eleftheria Batsou 的头像

Eleftheria Batsou1 个月前

Seems to be super smart.

Thor 雷神 ⚡️ 的头像

Thor 雷神 ⚡️1 个月前

It must be if it can understand my German 😳

Solution Dr. 的头像

Solution Dr.1 个月前

This is nice

John Usada 的头像

John Usada1 个月前

Is this what you were talking about yesterday, or is there more to come? I really don't want to lose faith in Google, but they still haven't released the model they promised about two months ago

Keith Delk (He/Him) 的头像

Keith Delk (He/Him)1 个月前

Please add computer vision for sign language!

Nora Vale 的头像

Nora Vale1 个月前

Custom vocab plus diarization is the meeting-notes combo. 🫡

Mirolim Mirzakhmedov 的头像

Mirolim Mirzakhmedov1 个月前

Real-time transcribe looks great, but shoutout to the timely edits!

Gabriel Moncha 的头像

Gabriel Moncha1 个月前

amazing how every time i saw you present something it's a new transcription model 🫶 unfortunately this one is not good enough because it cannot codeswitch tried with English, French and Romanian and it only detected Romania

Phanos 的头像

Phanos1 个月前

Will it be used for Gemini live? Currently speech transcription is pretty bad even though the model understands the audio well!

Ke 的头像

Ke1 个月前

Good

Michael Yagudaev 🧑🏻‍💻🇨🇦 的头像

Michael Yagudaev 🧑🏻‍💻🇨🇦1 个月前

Word level Timestamps too? Comparison to whisper and deepgram?

Joe 的头像

Joe1 个月前

@googledevs Dear sir, I am a non English native speaker but you sound like from the UK, do you?

Michael Yagudaev 🧑🏻‍💻🇨🇦 的头像

Michael Yagudaev 🧑🏻‍💻🇨🇦1 个月前

Mutlispeaker identification is epic!

Danny Thompson 的头像

Danny Thompson1 个月前

Now THIS is impressive! Might need to add this into instead of the current transcription tooling I am using. I for sure thought "Unary" would make be a mistake and that would have still be passable but this is good.

OSINT with a splash of good takes and a few bad 1s 的头像

OSINT with a splash of good takes and a few bad 1s1 个月前

Would be great if you could do a follow up on how to enable (configuration/fine tuning/post training) intent based transcription for medical and technical research use cases

Federico Giorgi 的头像

Federico Giorgi1 个月前

Whoah, Xerox and IBM vibes. A dying giant. You had literally everything to achieve AGI, and now you cannot even deliver Gemini 3.5 Pro. After this 3.5 Transcribed was announced, Google stock price went down another 1%.

Pawel 的头像

Pawel1 个月前

It's pretty solid! Kudos team! It can even clean up the interfering speech by itself. Tried to give it some hard time, but it did pretty well. 💪

相关视频

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

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

239,002 次观看 • 1 个月前

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.

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

143,971 次观看 • 1 个月前

Gemini 3.5 Transcribe is our latest speech-to-text model for precise and intelligent transcriptions. 🧵

Gemini 3.5 Transcribe is our latest speech-to-text model for precise and intelligent transcriptions. 🧵

Google DeepMind

69,615 次观看 • 1 个月前

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!

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

220,265 次观看 • 1 个月前

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. Gemini 3.5 Transcribe isn't just dictation — it’s active intelligence with precise, context-aware speech-to-text support in 85+ languages. The model automatically filters out filler words, formats unstructured speech, and even pairs with your screen context to execute voice commands. Watch as Gemini 3.5 Transcribe removes filler words and uses multimodal capabilities to seamlessly turn messy voice input and local files into a polished email draft.

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. Gemini 3.5 Transcribe isn't just dictation — it’s active intelligence with precise, context-aware speech-to-text support in 85+ languages. The model automatically filters out filler words, formats unstructured speech, and even pairs with your screen context to execute voice commands. Watch as Gemini 3.5 Transcribe removes filler words and uses multimodal capabilities to seamlessly turn messy voice input and local files into a polished email draft.

Google AI

116,277 次观看 • 1 个月前

We're introducing two new transcription models in the API: • GPT-Live-Transcribe: built for low-latency live transcription. • GPT-Transcribe: optimized for asynchronous transcription of completed audio files and batch workloads. Both models better understand context and deliver more accurate transcription on real world audio across accents and languages, including for short phrases, numbers, specialized terminology, and speech with loud background noise.

We're introducing two new transcription models in the API: • GPT-Live-Transcribe: built for low-latency live transcription. • GPT-Transcribe: optimized for asynchronous transcription of completed audio files and batch workloads. Both models better understand context and deliver more accurate transcription on real world audio across accents and languages, including for short phrases, numbers, specialized terminology, and speech with loud background noise.

OpenAI Developers

455,729 次观看 • 2 个月前

Introducing Gemini 3.1 Flash TTS 🗣️, our latest text to speech model with scene direction, speaker level specificity, audio tags, more natural + expressive voices, and support for 70 different languages. Available via our new audio playground in AI Studio and in the Gemini API!

Introducing Gemini 3.1 Flash TTS 🗣️, our latest text to speech model with scene direction, speaker level specificity, audio tags, more natural + expressive voices, and support for 70 different languages. Available via our new audio playground in AI Studio and in the Gemini API!

Logan Kilpatrick

805,885 次观看 • 6 个月前

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.

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

20,167 次观看 • 1 个月前

🔊Introducing Voxtral TTS: our new frontier open-weight model for natural, expressive, and ultra-fast text-to-speech 🎭Realistic, emotionally expressive speech. 🌍Supports 9 languages and accurately captures diverse dialects. ⚡Very low latency for time-to-first-audio. 🔄Easily adaptable to new voices

🔊Introducing Voxtral TTS: our new frontier open-weight model for natural, expressive, and ultra-fast text-to-speech 🎭Realistic, emotionally expressive speech. 🌍Supports 9 languages and accurately captures diverse dialects. ⚡Very low latency for time-to-first-audio. 🔄Easily adaptable to new voices

Mistral AI

952,657 次观看 • 6 个月前

Introducing Saaras V4, our most capable speech to text model yet. It delivers strong performance across both English and Indian languages, with better accuracy over a much wider range of speech. Saaras V4 was built with specific attention to noise, accents, dialects and mixed-language speech. Read more in the blog:

Introducing Saaras V4, our most capable speech to text model yet. It delivers strong performance across both English and Indian languages, with better accuracy over a much wider range of speech. Saaras V4 was built with specific attention to noise, accents, dialects and mixed-language speech. Read more in the blog:

Sarvam

216,999 次观看 • 17 天前

Earlier today we introduced Gemini 3.5 Transcribe, our latest text-to-speech model. But, what does this actually mean for your projects? We built this app in Google AI Studio to demonstrate just how much smarter 3.5 Transcribe is. When streaming live audio simultaneously through two parallel transcription pipeline modes, you can see how smart transcription automatically strips out disfluencies (ums, ahs) and condenses long, rambling thoughts while verbatim keeps exact match transcription live:

Earlier today we introduced Gemini 3.5 Transcribe, our latest text-to-speech model. But, what does this actually mean for your projects? We built this app in Google AI Studio to demonstrate just how much smarter 3.5 Transcribe is. When streaming live audio simultaneously through two parallel transcription pipeline modes, you can see how smart transcription automatically strips out disfluencies (ums, ahs) and condenses long, rambling thoughts while verbatim keeps exact match transcription live:

Google for Developers

65,996 次观看 • 1 个月前

Introducing Gemini 3.8 Flash TTS 📣 for expressive, nuanced voice acting, and 3.8 Flash-Lite TTS ⚡️ for high-volume, cost-efficient scale! Our most expressive, multilingual (100+ languages) speech generation models bring powerful new features for developers and creators alike: • Voice Design: Craft custom voices across languages, dialects, and accents using simple text prompts • 2,000+ Prebuilt Voices: A vast, high-fidelity library covering diverse styles and personas • Voice Replication: Fast, authentic replication with built-in consent verification • Multi-Speaker Dialogue: Seamless, natural pacing between distinct voices Try it now in Google AI Studio 👉

Introducing Gemini 3.8 Flash TTS 📣 for expressive, nuanced voice acting, and 3.8 Flash-Lite TTS ⚡️ for high-volume, cost-efficient scale! Our most expressive, multilingual (100+ languages) speech generation models bring powerful new features for developers and creators alike: • Voice Design: Craft custom voices across languages, dialects, and accents using simple text prompts • 2,000+ Prebuilt Voices: A vast, high-fidelity library covering diverse styles and personas • Voice Replication: Fast, authentic replication with built-in consent verification • Multi-Speaker Dialogue: Seamless, natural pacing between distinct voices Try it now in Google AI Studio 👉

Thor 雷神 ⚡️

14,844 次观看 • 19 天前

Eleven v3 (alpha) is the most expressive Text to Speech model. v3 introduces: • Multi-speaker dialogue with contextual awareness • Support for 70+ languages, up from 33 in v2 • Audio tags such as [excited], [sighs], [laughing], and [whispers]

Eleven v3 (alpha) is the most expressive Text to Speech model. v3 introduces: • Multi-speaker dialogue with contextual awareness • Support for 70+ languages, up from 33 in v2 • Audio tags such as [excited], [sighs], [laughing], and [whispers]

ElevenLabs

39,424 次观看 • 1 年前

Introducing Scribe — the most accurate Speech to Text model. It has the highest accuracy on benchmarks, outperforming previous state-of-the-art models such as Gemini 2.0 and OpenAI Whisper v3. It’s now the leading model for English, Spanish, Italian, and many more. With support for 99 languages, speaker diarization, character-level timestamps, and non-speech events such as laughing.

Introducing Scribe — the most accurate Speech to Text model. It has the highest accuracy on benchmarks, outperforming previous state-of-the-art models such as Gemini 2.0 and OpenAI Whisper v3. It’s now the leading model for English, Spanish, Italian, and many more. With support for 99 languages, speaker diarization, character-level timestamps, and non-speech events such as laughing.

ElevenLabs

465,228 次观看 • 1 年前

Say hello to Gemini 3.5 Transcribe! - Build apps that understand user speech / intent, even w/ multiple speakers! - Auto-detection of 85+ languages out of the box - Custom vocab adaptation for specialized jargon... SGTM:) API available now in Google AI Studio and Gemini Enterprise, or try it in the Gemini app on macOS or Rambler on Android! More details:

Say hello to Gemini 3.5 Transcribe! - Build apps that understand user speech / intent, even w/ multiple speakers! - Auto-detection of 85+ languages out of the box - Custom vocab adaptation for specialized jargon... SGTM:) API available now in Google AI Studio and Gemini Enterprise, or try it in the Gemini app on macOS or Rambler on Android! More details:

Sundar Pichai

568,325 次观看 • 1 个月前

Today, we’re launching Gemini 3.5 Transcribe, our new speech-to-text model with sub-second streaming and intelligent post-processing for agent interfaces. 2.6% WER on non-streaming and 4.0% on streaming. Supports 85+ languages, cleans up conversational disfluencies ("um", "ah", and mid-sentence self-corrections), handles alphanumeric tokens (postal codes or IDs), 70% reduction time for the final transcription compared to Chirp 3. - `gemini-3.5-transcribe-live`: Sub-second, bidirectional streaming via the Gemini Live API - `gemini-3.5-transcribe`: Recorded processing via the Interactions API with word-level timestamps and speaker attribution (up to 3 speakers). Having access to Transcribe has made me use voice input way more than I ever did before. The native post-processing is incredible. It knows you mean `.json` and not a person named "Jason". I sometimes speak 5 minutes into and it perfectly refactors my instruction to my context. Available today in public preview in Gemini API, Google AI Studio and already in the Google Gemini and Google Antigravity. Try here:

Today, we’re launching Gemini 3.5 Transcribe, our new speech-to-text model with sub-second streaming and intelligent post-processing for agent interfaces. 2.6% WER on non-streaming and 4.0% on streaming. Supports 85+ languages, cleans up conversational disfluencies ("um", "ah", and mid-sentence self-corrections), handles alphanumeric tokens (postal codes or IDs), 70% reduction time for the final transcription compared to Chirp 3. - `gemini-3.5-transcribe-live`: Sub-second, bidirectional streaming via the Gemini Live API - `gemini-3.5-transcribe`: Recorded processing via the Interactions API with word-level timestamps and speaker attribution (up to 3 speakers). Having access to Transcribe has made me use voice input way more than I ever did before. The native post-processing is incredible. It knows you mean `.json` and not a person named "Jason". I sometimes speak 5 minutes into and it perfectly refactors my instruction to my context. Available today in public preview in Gemini API, Google AI Studio and already in the Google Gemini and Google Antigravity. Try here:

Philipp Schmid

15,084 次观看 • 1 个月前

Introducing Qwen3-TTS! 🗣️ Our new text-to-speech model is designed to be multi-timbre, multi-lingual, and multi-dialect for natural, expressive audio. It delivers strong performance in English & Chinese, and we're excited for you to hear it for yourself!

Introducing Qwen3-TTS! 🗣️ Our new text-to-speech model is designed to be multi-timbre, multi-lingual, and multi-dialect for natural, expressive audio. It delivers strong performance in English & Chinese, and we're excited for you to hear it for yourself!

Tongyi Lab

1,015,006 次观看 • 1 年前

Introducing Parrot 🦜 Our first speech-to-text model built for production-grade voice agents with an industry leading accuracy, built for noisy calls, regional dialects and compressed audio. Trained on thousands of hours of real-world audio to make sure when you say Udaipur, the agent doesn't hear 'you-die-poor'.

Introducing Parrot 🦜 Our first speech-to-text model built for production-grade voice agents with an industry leading accuracy, built for noisy calls, regional dialects and compressed audio. Trained on thousands of hours of real-world audio to make sure when you say Udaipur, the agent doesn't hear 'you-die-poor'.

Vedant

15,953 次观看 • 4 个月前

🗣️✨ Speak your vibes into existence with Gemini 3.5 Transcribe The latest audio model is built for apps that need live transcription and quick visual prototyping. Watch genevieveh@ turn spoken ideas into a dynamic mood board using Gemini 3.5 Transcribe on the Live API. The model maps speech to user intent to create prompts that trigger live image generation and editing with Nano Banana 2 Lite:

🗣️✨ Speak your vibes into existence with Gemini 3.5 Transcribe The latest audio model is built for apps that need live transcription and quick visual prototyping. Watch genevieveh@ turn spoken ideas into a dynamic mood board using Gemini 3.5 Transcribe on the Live API. The model maps speech to user intent to create prompts that trigger live image generation and editing with Nano Banana 2 Lite:

Google for Developers

36,074 次观看 • 1 个月前

Eleven v3 Conversational, our most expressive model for realtime speech, is now generally available. For developers building voice experiences that respond with real emotion, Eleven v3 Conversational includes audio tags for fine-grained control and support across 70+ languages.

Eleven v3 Conversational, our most expressive model for realtime speech, is now generally available. For developers building voice experiences that respond with real emotion, Eleven v3 Conversational includes audio tags for fine-grained control and support across 70+ languages.

ElevenLabs

126,996 次观看 • 1 个月前