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 Scribe v2 Realtime – the most accurate real-time Speech to Text model. Built for voice agents, meeting notetakers, and live applications, it transcribes in 150ms across 90+ languages, including English, French, German, Italian, Spanish, Portuguese, Hindi, and Japanese. Available today by API and through ElevenLabs Agents.

ElevenLabs

210,070 subscribers

318,993 次观看 • 1 年前 •via X (Twitter)

新闻政治科学技术

Anya Rossi• Live Now

Private livecam show

39 条评论

ElevenLabs 的头像

ElevenLabs1 年前

Scribe v2 Realtime sets a new standard for live accuracy, outperforming every low-latency ASR model.

ElevenLabs 的头像

ElevenLabs1 年前

Scribe v2 Realtime is specifically built for agentic use cases. On hard samples containing background noise and complex information, it significantly outperforms all other models.

ElevenLabs 的头像

ElevenLabs1 年前

Key features: - State-of-the-art accuracy - 90+ language coverage - SOC 2, ISO27001, PCI DSS L1, HIPAA, GDPR compliance - EU & India residency - Zero retention mode

ElevenLabs 的头像

ElevenLabs1 年前

Build with the API. Scribe v2 Realtime is available today. Read the docs:

ElevenLabs 的头像

ElevenLabs1 年前

Use Scribe v2 Realtime in ElevenLabs Agents. Deploy natural, human-sounding agents for support, sales, and in-product experiences.

ElevenLabs 的头像

ElevenLabs1 年前

Start building today. Use Scribe v2 Realtime through our API or directly within ElevenLabs Agents. Sign up here:

Seth 🇺🇸 的头像

Seth 🇺🇸1 年前

5$ in hr 😭

Luke Harries 的头像

Luke Harries1 年前

Incredible work by the research team

AshutoshShrivastava 的头像

AshutoshShrivastava1 年前

Congratulations on the launch 🔥🔥

Umesh 的头像

Umesh1 年前

Great to see so many languages supported!

Louis 的头像

Louis1 年前

The research team did it again

Jason Stillerman 的头像

Jason Stillerman1 年前

Nice! There is an error in the docs. The endpoint is /realtime not /realtime-beta

ZOYA ✪ 的头像

ZOYA ✪1 年前

This is huge, 150ms real-time transcription across 90+ languages is next-level.

Dr. Moises Romero 的头像

Dr. Moises Romero1 年前

do you have the TARS voice? i'd subscribe monthly if you did.

Clark 的头像

Clark1 年前

This is the kind of AI application I want to see in the world.

Michael Frisch, PhD 的头像

Michael Frisch, PhD1 年前

Hands-down, the best. I’m looking forward to trying scribe v2 asap; perfect timing for my build. Świetne.

Danon 🛡️ 的头像

Danon 🛡️1 年前

Nice performance, but still very expensive. Many apps that need constant transcription won't become a reality until you do a x10 reduction on price. I will adhere to cheaper options by now

Rahul Dahre 的头像

Rahul Dahre1 年前

Real-time transcription just got a major upgrade. 🚀

Angry Tom 的头像

Angry Tom1 年前

Congrats guys! Great to see so many languages supported...

LEYVERSE 的头像

LEYVERSE1 年前

seems crazy!

The Miracle 的头像

The Miracle1 年前

Incredible. What about voicemails, can it detect a voicemail message?

Blake Ha 的头像

Blake Ha1 年前

damn i’m testing it out rn

Julian Keenaghan 的头像

Julian Keenaghan1 年前

Great work team. Is it realtime only?

Kol Tregaskes 的头像

Kol Tregaskes1 年前

Very nice guys.

𝓐𝓶𝓲𝓷𝓮 的头像

𝓐𝓶𝓲𝓷𝓮1 年前

No thank you, you're the most expensive among all TTS services.

Gokhan Celiker 的头像

Gokhan Celiker1 年前

This looks great! Also loving the animations in the video.

diamond 的头像

diamond1 年前

Finally, super excited about this. Now all that’s left is to integrate it into the agent in a way that enables conversations in additional languages, with the v3 model

Rich Howard 的头像

Rich Howard1 年前

Can't wait to see what people build with this new model!

VancouverIslandMichael 的头像

VancouverIslandMichael1 年前

I've used your agent for over a year, pretty much every day. It gets better all the time, way under priced in my opinion! Thanks you so much!

Meer | AI Tools & News 的头像

Meer | AI Tools & News1 年前

Congratulations team on the launch

Alex Volkov 的头像

Alex Volkov1 年前

Congrats on this release, very exciting!

Sinclair Ta 的头像

Sinclair Ta1 年前

Great product, even V1 already the most accurate stt model 🙌

Anthem 的头像

Anthem1 年前

Video is amazing! Can't move eyes away.

Micah 的头像

Micah1 年前

AI sdk support with scribe v2 real time and real time voice models when?

DeanArtist DA 的头像

DeanArtist DA1 年前

Would be great if I could try it...

Mykhailo Sorochuk 的头像

Mykhailo Sorochuk1 年前

Impressive specs! Real-time transcription will really change the game for live interactions.

Glen Calvert 的头像

Glen Calvert1 年前

@grok what's it cost

Maze 的头像

Maze1 年前

love what i’m seeing here

seán 的头像

seán1 年前

who on the brand team has been on a Burial tip recently 😭

相关视频

Today we’re introducing Scribe v2: the most accurate transcription model ever released. While Scribe v2 Realtime is optimized for ultra low latency and agents use cases, Scribe v2 is built for batch transcription, subtitling, and captioning at scale.

Today we’re introducing Scribe v2: the most accurate transcription model ever released. While Scribe v2 Realtime is optimized for ultra low latency and agents use cases, Scribe v2 is built for batch transcription, subtitling, and captioning at scale.

ElevenLabs

558,355 次观看 • 10 个月前

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

465,353 次观看 • 1 年前

Introducing Scribe v3 and Scribe v3 Live: our most accurate Speech to Text models yet. Built for real-world audio, Scribe excels in situations with extreme background noise, knows pauses from the end of sentences, and keeps track of who said what in a busy meeting.

Introducing Scribe v3 and Scribe v3 Live: our most accurate Speech to Text models yet. Built for real-world audio, Scribe excels in situations with extreme background noise, knows pauses from the end of sentences, and keeps track of who said what in a busy meeting.

ElevenLabs

814,614 次观看 • 2 天前

We pioneered the first ultra-realistic Text to Speech model, and recently launched the world's most accurate Speech to Text model, Scribe. But we're not stopping there. Today, we're taking one small step for man, and one giant leap for man's best friend... with Text to Bark.

We pioneered the first ultra-realistic Text to Speech model, and recently launched the world's most accurate Speech to Text model, Scribe. But we're not stopping there. Today, we're taking one small step for man, and one giant leap for man's best friend... with Text to Bark.

ElevenLabs

291,881 次观看 • 1 年前

We are launching the Eleven v3 (alpha) API. Built for async use cases, Eleven v3 (alpha) delivers the most expressive Text to Speech model: - Dialogue mode, unlimited amount of speakers - 70+ languages - Enhanced voice and emotional control with [audio tags]

We are launching the Eleven v3 (alpha) API. Built for async use cases, Eleven v3 (alpha) delivers the most expressive Text to Speech model: - Dialogue mode, unlimited amount of speakers - 70+ languages - Enhanced voice and emotional control with [audio tags]

ElevenLabs

8,189,340 次观看 • 1 年前

Introducing Eleven Multilingual v2: our new AI speech model supporting 28 languages! v2 comes with enhanced conversational capability, higher output quality & the ability to better preserve unique voice characteristics across languages. Read more:

Introducing Eleven Multilingual v2: our new AI speech model supporting 28 languages! v2 comes with enhanced conversational capability, higher output quality & the ability to better preserve unique voice characteristics across languages. Read more:

ElevenLabs

293,498 次观看 • 3 年前

Introducing Eleven Music. The highest quality AI music model. - Complete control over genre, style, and structure - Multi-lingual, including English, Spanish, German, Japanese and more - Edit the sound and lyrics of individual sections or the whole song

Introducing Eleven Music. The highest quality AI music model. - Complete control over genre, style, and structure - Multi-lingual, including English, Spanish, German, Japanese and more - Edit the sound and lyrics of individual sections or the whole song

ElevenLabs

1,750,303 次观看 • 1 年前

Oh wow…ElevenLabs just dropped the most accurate transcription model ever. - v2 Realtime: built for agents, ultra low latency - v2 Batch: built for scale, subtitling, captioning Transcription just got solved 🤯

Oh wow…ElevenLabs just dropped the most accurate transcription model ever. - v2 Realtime: built for agents, ultra low latency - v2 Batch: built for scale, subtitling, captioning Transcription just got solved 🤯

Alvaro Cintas

156,082 次观看 • 10 个月前

Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborators that can listen, reason, and solve complex problems as conversations unfold. Now available in the API alongside streaming models GPT-Realtime-Translate and GPT-Realtime-Whisper — a new set of audio capabilities for the next generation of voice interfaces.

Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborators that can listen, reason, and solve complex problems as conversations unfold. Now available in the API alongside streaming models GPT-Realtime-Translate and GPT-Realtime-Whisper — a new set of audio capabilities for the next generation of voice interfaces.

OpenAI

3,671,826 次观看 • 6 个月前

Introducing Eleven Realtime, a new class of Speech to Speech models. Voice agents usually make you choose between quick replies or precise answers. Eleven Realtime gives you both. It starts talking in half a second and gets spoken reasoning questions right.

Introducing Eleven Realtime, a new class of Speech to Speech models. Voice agents usually make you choose between quick replies or precise answers. Eleven Realtime gives you both. It starts talking in half a second and gets spoken reasoning questions right.

ElevenLabs

227,066 次观看 • 23 天前

Introducing the ElevenLabs MCP, now available in Claude. Your team can manage your voice and chat agents where you already work - review recent performance, create new agents, update configurations, and even estimate LLM costs before changes go live.

Introducing the ElevenLabs MCP, now available in Claude. Your team can manage your voice and chat agents where you already work - review recent performance, create new agents, update configurations, and even estimate LLM costs before changes go live.

ElevenLabs

336,209 次观看 • 2 个月前

We're releasing Hibiki-Zero, a new real-time and multilingual speech translation model that can translate 🇫🇷French, 🇪🇸Spanish, 🇵🇹Portuguese and 🇩🇪German to English: accurate, low-latency, high audio quality, with voice transfer. And best of all: open-source.

We're releasing Hibiki-Zero, a new real-time and multilingual speech translation model that can translate 🇫🇷French, 🇪🇸Spanish, 🇵🇹Portuguese and 🇩🇪German to English: accurate, low-latency, high audio quality, with voice transfer. And best of all: open-source.

kyutai

81,131 次观看 • 9 个月前

BLACKBOX AI uses ElevenLabs Agents to power Logger and Robocoder - voice-driven coding agents now serving over 30 million developers worldwide. Logger autonomously monitors systems 24/7, detects issues, and calls on-call engineers to explain incidents, propose and implement fixes in real time. Robocoder helps teams build full-stack applications from scratch: front-end, back-end and even AI-powered applications with no API keys required, through natural, conversational interfaces.

BLACKBOX AI uses ElevenLabs Agents to power Logger and Robocoder - voice-driven coding agents now serving over 30 million developers worldwide. Logger autonomously monitors systems 24/7, detects issues, and calls on-call engineers to explain incidents, propose and implement fixes in real time. Robocoder helps teams build full-stack applications from scratch: front-end, back-end and even AI-powered applications with no API keys required, through natural, conversational interfaces.

ElevenLabs

1,085,055 次观看 • 1 年前

Introducing Eleven v3 (alpha) - the most expressive Text to Speech model ever. Supporting 70+ languages, multi-speaker dialogue, and audio tags such as [excited], [sighs], [laughing], and [whispers]. Now in public alpha and 80% off in June.

Introducing Eleven v3 (alpha) - the most expressive Text to Speech model ever. Supporting 70+ languages, multi-speaker dialogue, and audio tags such as [excited], [sighs], [laughing], and [whispers]. Now in public alpha and 80% off in June.

ElevenLabs

1,960,325 次观看 • 1 年前

Universal-Streaming is our real-time speech-to-text model — built for voice agents with ~300ms latency, high accuracy, unlimited concurrency, and just $0.15/hour. 👉 Test it live in the playground →

Universal-Streaming is our real-time speech-to-text model — built for voice agents with ~300ms latency, high accuracy, unlimited concurrency, and just $0.15/hour. 👉 Test it live in the playground →

AssemblyAI

1,017,880 次观看 • 1 年前

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

This week, we launched Eleven Realtime for voice agents that talk to people. Now we’re opening a limited alpha of Eleven Realtime Translation, for people who need to talk to each other. Eleven Realtime Translation builds live voice translation into calls. Each person can speak their own language and hear the other person in theirs, in a natural voice, while the call is happening. It works in more than 90 languages and detects each speaker’s language automatically. Access is open to enterprise customers during the alpha.

This week, we launched Eleven Realtime for voice agents that talk to people. Now we’re opening a limited alpha of Eleven Realtime Translation, for people who need to talk to each other. Eleven Realtime Translation builds live voice translation into calls. Each person can speak their own language and hear the other person in theirs, in a natural voice, while the call is happening. It works in more than 90 languages and detects each speaker’s language automatically. Access is open to enterprise customers during the alpha.

ElevenLabs

21,772 次观看 • 22 天前

Voice agents add a new dimension to learning. Today, we're introducing Albert Einstein's voice to ElevenLabs, and launching an Einstein agent, to bring his written archives to life in his iconic voice.

Voice agents add a new dimension to learning. Today, we're introducing Albert Einstein's voice to ElevenLabs, and launching an Einstein agent, to bring his written archives to life in his iconic voice.

ElevenLabs

47,578 次观看 • 5 个月前

Introducing our new Turbo 2.5 model - Hindi, French, Spanish, Mandarin and 27 other languages just got 3x faster. This unlocks high-quality low-latency conversational AI for nearly 80% of the world. For the first time, we support Vietnamese, Hungarian and Norwegian text to speech. And English is now 25% faster compared to Turbo v2.

Introducing our new Turbo 2.5 model - Hindi, French, Spanish, Mandarin and 27 other languages just got 3x faster. This unlocks high-quality low-latency conversational AI for nearly 80% of the world. For the first time, we support Vietnamese, Hungarian and Norwegian text to speech. And English is now 25% faster compared to Turbo v2.

ElevenLabs

50,875 次观看 • 2 年前

Revolut has selected ElevenLabs Agents to bolster its customer support. Multilingual conversational agents handle support requests for Revolut customers across 30+ languages, reducing time to ticket resolution by more than 8x.

Revolut has selected ElevenLabs Agents to bolster its customer support. Multilingual conversational agents handle support requests for Revolut customers across 30+ languages, reducing time to ticket resolution by more than 8x.

ElevenLabs

23,450 次观看 • 9 个月前