正在加载视频...

视频加载失败

返回首页

Announcing Universal-2, our most advanced speech-to-text model to date. Building on Universal-1's industry-leading performance, we've pushed Speech AI even further. Here's what's new:

AssemblyAI's profile picture

AssemblyAI

45,726 subscribers

42,970 次观看 • 1 年前 •via X (Twitter)

教育科学技术新闻政治
LIVE

Anya Rossi• Live Now

Private livecam show

10 条评论

A 的头像
A1 年前

Great progress, congrats! However you still do not support streaming STT for German. When will you finally launch that?

Sumanth 的头像
Sumanth1 年前

Congrats team on the launch, Can't wait to try this! 🔥

FirstHuman 的头像
FirstHuman1 年前

Awe-inspiring to work.

Ralf Waldukat 的头像
Ralf Waldukat1 年前

Is Universal-2 available in the API? I only found 'best' and benchmarked it with these settings: ```aai.TranscriptionConfig(speaker_labels=True, speech_model="best" )``` I don't get higher performance than whisper + pyannote. Worse in some cases.

Mohsen.gh 的头像
Mohsen.gh1 年前

Hi.which languages support you're library? Thanks a lot.

KraKra 的头像
KraKra1 年前

Congrats, have you included Portuguese?

Advait Bopardikar 的头像
Advait Bopardikar1 年前

Love more speech models! Heads up that the latest-long model is from the V1 Google STT API and is many years old. You may want to run your benchmarks against Chirp_2

Global Allied Health 的头像
Global Allied Health1 年前

Your sales team never responded to my attempts to contact via your website. Are you still open for business? How can I get a sales call?

bestofx 的头像
bestofx1 年前

I don't know about universal -1

lucky 的头像
lucky1 年前

Nicee

相关视频

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 →
1:03

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

Today we're sharing new progress on our AI speech work. Our Massively Multilingual Speech (MMS) project has now scaled speech-to-text & text-to-speech to support over 1,100 languages — a 10x increase from previous work. Details + access to new pretrained models ⬇️
1:30

Today we're sharing new progress on our AI speech work. Our Massively Multilingual Speech (MMS) project has now scaled speech-to-text & text-to-speech to support over 1,100 languages — a 10x increase from previous work. Details + access to new pretrained models ⬇️

AI at Meta

326,826 次观看 • 3 年前

📢New paper We are announcing ReVISE, the first universal audio-visual speech enhancement model powered by SSL. paper: demo: w/ Yossi Adi @TalRemez BowenShi Jacob Donley
1:08

📢New paper We are announcing ReVISE, the first universal audio-visual speech enhancement model powered by SSL. paper: demo: w/ Yossi Adi @TalRemez BowenShi Jacob Donley

Wei-Ning Hsu

46,382 次观看 • 3 年前

Grok's new Speech to Text model is SO CHEAP and SO ACCURATE 50¢ to transcribe our last 150 videos. We said AI 1,053 times
4:38

Grok's new Speech to Text model is SO CHEAP and SO ACCURATE 50¢ to transcribe our last 150 videos. We said AI 1,053 times

Wes Bos

49,138 次观看 • 2 个月前

Introducing SeamlessM4T, the first all-in-one, multilingual multimodal translation model. This single model can perform tasks across speech-to-text, speech-to-speech, text-to-text translation & speech recognition for up to 100 languages depending on the task. Details ⬇️
0:56

Introducing SeamlessM4T, the first all-in-one, multilingual multimodal translation model. This single model can perform tasks across speech-to-text, speech-to-speech, text-to-text translation & speech recognition for up to 100 languages depending on the task. Details ⬇️

AI at Meta

592,704 次观看 • 2 年前

🎙️Do you know you now have all the building blocks for full speech-to-speech? - Voxtral Realtime: High-quality, real-time speech-to-text. - Mistral Small 4: Fast, efficient, general-purpose agentic model. - Voxtral TTS: Realistic customizable text-to-speech with streaming output.
0:50

🎙️Do you know you now have all the building blocks for full speech-to-speech? - Voxtral Realtime: High-quality, real-time speech-to-text. - Mistral Small 4: Fast, efficient, general-purpose agentic model. - Voxtral TTS: Realistic customizable text-to-speech with streaming output.

Mistral AI for Developers

27,647 次观看 • 3 个月前

The wait is over! With 60M+ minutes transcribed, our next-gen speech-to-text model Nova-2 is now available. What's new? ✅ Expanded languages: Spanish, Hindi, German, French, Portuguese ✅ Custom model training ✅ On-prem deployment Let's dive in...🧵
0:30

The wait is over! With 60M+ minutes transcribed, our next-gen speech-to-text model Nova-2 is now available. What's new? ✅ Expanded languages: Spanish, Hindi, German, French, Portuguese ✅ Custom model training ✅ On-prem deployment Let's dive in...🧵

Deepgram

1,385,276 次观看 • 2 年前

🔥 Ming-UniAudio: The 「Nano Banana」moment for speech is here! A single model for universal understanding, generation & free-form editing. First Unified Continuous Tokenizer 「MingTok-Audio」and Unified Und & Gen Speech LLM built on it. First Universal Free-form Speech Editing Model Without Timestamp Condition. First FreeForm Audio Editing Benchmark. 💻 GitHub: 🤗 Tokenizer: 🤗 Model: base: edit: 🤗 Benchmark: 🌍 blog: #AI #Speech #SpeechLLM #LLM #GenerativeAI #Audio #ASR #TTS #SpeechEditing
2:52

🔥 Ming-UniAudio: The 「Nano Banana」moment for speech is here! A single model for universal understanding, generation & free-form editing. First Unified Continuous Tokenizer 「MingTok-Audio」and Unified Und & Gen Speech LLM built on it. First Universal Free-form Speech Editing Model Without Timestamp Condition. First FreeForm Audio Editing Benchmark. 💻 GitHub: 🤗 Tokenizer: 🤗 Model: base: edit: 🤗 Benchmark: 🌍 blog: #AI #Speech #SpeechLLM #LLM #GenerativeAI #Audio #ASR #TTS #SpeechEditing

Ant Ling

21,365 次观看 • 9 个月前

Gemini 3.1 Flash TTS is our most controllable text-to-speech model yet. With new Audio Tags, you can easily direct vocal style, delivery, and pace through text commands. 🧵
0:33

Gemini 3.1 Flash TTS is our most controllable text-to-speech model yet. With new Audio Tags, you can easily direct vocal style, delivery, and pace through text commands. 🧵

Google DeepMind

468,982 次观看 • 2 个月前

Today we released Meta Spirit LM — our first open source multimodal language model that freely mixes text and speech. Many existing AI voice experiences today use ASR to techniques to process speech before synthesizing with an LLM to generate text — but these approaches compromise the expressive aspects of speech. Using phonetic, pitch and tone tokens, Spirit LM models can overcome these limitations for both inputs and outputs to generate more natural sounding speech while also learning new tasks across ASR, TTS and speech classification. We hope that sharing this work will enable the research community to further new approaches for text and speech integration.
0:36

Today we released Meta Spirit LM — our first open source multimodal language model that freely mixes text and speech. Many existing AI voice experiences today use ASR to techniques to process speech before synthesizing with an LLM to generate text — but these approaches compromise the expressive aspects of speech. Using phonetic, pitch and tone tokens, Spirit LM models can overcome these limitations for both inputs and outputs to generate more natural sounding speech while also learning new tasks across ASR, TTS and speech classification. We hope that sharing this work will enable the research community to further new approaches for text and speech integration.

AI at Meta

351,698 次观看 • 1 年前

NEW: Kokoro 82M - APACHE 2.0 licensed, Text to Speech model, trained on < 100 hours of audio 🔥
1:54

NEW: Kokoro 82M - APACHE 2.0 licensed, Text to Speech model, trained on < 100 hours of audio 🔥

Vaibhav (VB) Srivastav

330,034 次观看 • 1 年前

Experimenting with OpenAI's new Text to Speech model 💬 Punctuation is powerful here 🤯
0:25

Experimenting with OpenAI's new Text to Speech model 💬 Punctuation is powerful here 🤯

Miguel | AP

202,867 次观看 • 2 年前

🚨 New model alert! Dialog by vibx — a leading text-to-speech model — now runs on GroqCloud™. That means natural-sounding speech with ultra-low latency, making real-time voice applications smoother and more responsive. Learn more & build fast — links in the comments!
1:12

🚨 New model alert! Dialog by vibx — a leading text-to-speech model — now runs on GroqCloud™. That means natural-sounding speech with ultra-low latency, making real-time voice applications smoother and more responsive. Learn more & build fast — links in the comments!

Groq Inc

47,183 次观看 • 1 年前

Here's how to make your iPhone dictation 11 times better using Apple Shortcuts, and OpenAI Advantages? 1. Most accurate Speech to Text model 2. If you make a mistake, just say the correction 3. It automatically adds line breaks and formatting
1:20

Here's how to make your iPhone dictation 11 times better using Apple Shortcuts, and OpenAI Advantages? 1. Most accurate Speech to Text model 2. If you make a mistake, just say the correction 3. It automatically adds line breaks and formatting

Luke Harries

36,389 次观看 • 1 年前

The new open-source Text to Speech model: Fish Speech 1.4 is brilliant! Trained on a massive 700K hours of multilingual speech data in 8 languages - Instant voice cloning 🗣️ - Ultra-low latency ⚡ - Compact model (~1GB weights) 🏋️‍♂️
1:23

The new open-source Text to Speech model: Fish Speech 1.4 is brilliant! Trained on a massive 700K hours of multilingual speech data in 8 languages - Instant voice cloning 🗣️ - Ultra-low latency ⚡ - Compact model (~1GB weights) 🏋️‍♂️

Rohan Paul

228,836 次观看 • 1 年前

Here are the best practices for using Eleven v3 (alpha) - the most expressive Text to Speech model.
3:55

Here are the best practices for using Eleven v3 (alpha) - the most expressive Text to Speech model.

ElevenLabs

43,692 次观看 • 1 年前

Did xAI just mass-murder the entire voice AI industry? 🤯 Grok just launched two voice APIs. Speech-to-Text and Text-to-Speech. Built on the same stack powering Tesla cars and Starlink support. And priced at 10x cheaper than ElevenLabs. Speech-to-Text: $0.10/hr batch. $0.20/hr streaming. Text-to-Speech: $4.20 per million characters. 25+ languages. Real-time streaming. Speaker diarization. Already outperforming ElevenLabs, Deepgram, and AssemblyAI on word error rate. TTS ships with expressive tags like [laugh], [sigh], , . Voices that don't sound like robots reading a script. ElevenLabs spent years building a voice AI company. xAI built voice AI for cars and satellites.
0:27

Did xAI just mass-murder the entire voice AI industry? 🤯 Grok just launched two voice APIs. Speech-to-Text and Text-to-Speech. Built on the same stack powering Tesla cars and Starlink support. And priced at 10x cheaper than ElevenLabs. Speech-to-Text: $0.10/hr batch. $0.20/hr streaming. Text-to-Speech: $4.20 per million characters. 25+ languages. Real-time streaming. Speaker diarization. Already outperforming ElevenLabs, Deepgram, and AssemblyAI on word error rate. TTS ships with expressive tags like [laugh], [sigh], , . Voices that don't sound like robots reading a script. ElevenLabs spent years building a voice AI company. xAI built voice AI for cars and satellites.

Vaibhav Sisinty

24,524,944 次观看 • 2 个月前

This is "Whisper.cpp" a local lightweight AI model that can be run on mobile phones to convert speech to text with real time streaming
0:30

This is "Whisper.cpp" a local lightweight AI model that can be run on mobile phones to convert speech to text with real time streaming

Abdelhamed M.

143,177 次观看 • 1 年前