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。

Voice AI without the wait! ⏱️ Thanks to Hugging Face and Cerebras, developers can now use the Gemma 4 31B model as the brain for voice AI at ultra-fast inference speeds. Add it to a fully open-source, cascaded speech-to-speech stack that can be used to power existing voice apps! 🗣️

Google Gemma

94,449 subscribers

158,882 次观看 • 12 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

You can use Cerebras' gpt-oss-120b to build realistic speech-to-speech voice interfaces with emotion via Hume AI's new EVI 3. Perfect for your next voice ai project! Link to try below 👇

You can use Cerebras' gpt-oss-120b to build realistic speech-to-speech voice interfaces with emotion via Hume AI's new EVI 3. Perfect for your next voice ai project! Link to try below 👇

Cerebras

22,034 次观看 • 1 年前

The Moshi speech-to-speech model by kyutai, hosted on Modal, absolutely cranks! Near instantaneous voice chat AI, thanks to bidirectional streaming. Whole startups could be built on this stack.

The Moshi speech-to-speech model by kyutai, hosted on Modal, absolutely cranks! Near instantaneous voice chat AI, thanks to bidirectional streaming. Whole startups could be built on this stack.

Erik Dunteman

55,400 次观看 • 1 年前

Hacked today: A realtime voice-to-voice assistant for my Mac that runs in the background and helps me be productive. Stack - RealtimeTTS package (for python) - Groq for fast inference - Mac native text to speech Quite happy with this :)

Hacked today: A realtime voice-to-voice assistant for my Mac that runs in the background and helps me be productive. Stack - RealtimeTTS package (for python) - Groq for fast inference - Mac native text to speech Quite happy with this :)

Paras Chopra

19,316 次观看 • 2 年前

.Vogent just released Vogent-Turn-80M: an open-source, state-of-the-art turn-detection model for voice AI. It improves any voice AI stack by detecting when to wait and when to speak, reducing interruptions and making conversations more humanlike.

.Vogent just released Vogent-Turn-80M: an open-source, state-of-the-art turn-detection model for voice AI. It improves any voice AI stack by detecting when to wait and when to speak, reducing interruptions and making conversations more humanlike.

Y Combinator

18,913 次观看 • 9 个月前

SwiftUI: You can chain free and open-source STT, TTS, and LLMs to build voice/vision apps with Core AI. Here is a demo I was experimenting with: - Whisper: Speech-to-text - Kokoro-82M: Text-to-speech - Qwen3-VL 2B: Vision I converted Pocket TTS and VibeVoice to Core AI models and tried with Gemma 4. All is working great.

SwiftUI: You can chain free and open-source STT, TTS, and LLMs to build voice/vision apps with Core AI. Here is a demo I was experimenting with: - Whisper: Speech-to-text - Kokoro-82M: Text-to-speech - Qwen3-VL 2B: Vision I converted Pocket TTS and VibeVoice to Core AI models and tried with Gemma 4. All is working great.

Amos Gyamfi

79,756 次观看 • 1 个月前

Your app talks back. Lovable now supports text-to-speech and-speech-to-text, so you can seamlessly add AI voice features to your projects. Make a voice assistant, a hands-free tool, or an app you can literally speak to. Sound on:

Your app talks back. Lovable now supports text-to-speech and-speech-to-text, so you can seamlessly add AI voice features to your projects. Make a voice assistant, a hands-free tool, or an app you can literally speak to. Sound on:

Lovable

21,999 次观看 • 1 个月前

NVIDIA just released a new open source transcription model, Nemotron Speech ASR, designed from the ground up for low-latency use cases like voice agents. Here's a voice agent built with this new model. 24ms transcription finalization and total voice-to-voice inference time under 500ms. This agent actually uses *three* NVIDIA open source models: - Nemotron Speech ASR - Nemotron 3 Nano 30GB in a 4-bit quant (released in December) - A preview checkpoint of the upcoming Magpie text-to-speech model These models are all truly open source: weights, training data, training code, and inference code. This is a big deal! Jensen said in the CES keynote yesterday that he expects open source models to catch up to proprietary models this year in a number of categories. NVIDIA is putting their weight behind making this happen. (As Alan Kay said, the best way to predict the future is to invent it.) The code for this agent is open source too, of course. You can deploy it to production with Modal and Pipecat AI cloud, or run locally on an NVIDIA DGX Spark or RTX 5090.

NVIDIA just released a new open source transcription model, Nemotron Speech ASR, designed from the ground up for low-latency use cases like voice agents. Here's a voice agent built with this new model. 24ms transcription finalization and total voice-to-voice inference time under 500ms. This agent actually uses three NVIDIA open source models: - Nemotron Speech ASR - Nemotron 3 Nano 30GB in a 4-bit quant (released in December) - A preview checkpoint of the upcoming Magpie text-to-speech model These models are all truly open source: weights, training data, training code, and inference code. This is a big deal! Jensen said in the CES keynote yesterday that he expects open source models to catch up to proprietary models this year in a number of categories. NVIDIA is putting their weight behind making this happen. (As Alan Kay said, the best way to predict the future is to invent it.) The code for this agent is open source too, of course. You can deploy it to production with Modal and Pipecat AI cloud, or run locally on an NVIDIA DGX Spark or RTX 5090.

kwindla

274,562 次观看 • 6 个月前

🔊🔛🔥 ... Groq Inc launched voice generation today. GroqCloud now has realtime transcription, LLMs, *and* text-to-speech. You can build super-responsive, ultra low-latency voice agents end-to-end entirely on Groq! At Daily, we're big fans of Groq's fast, low-latency inference. Pipecat AI supports all the Groq models, including the new voice model. Lately, we've been obsessively playing a voice chat game that Mark Backman wrote. (My high score is 6, so far.) Here's Mark, with Groq's `Celeste-PlayAI` voice.

🔊🔛🔥 ... Groq Inc launched voice generation today. GroqCloud now has realtime transcription, LLMs, and text-to-speech. You can build super-responsive, ultra low-latency voice agents end-to-end entirely on Groq! At Daily, we're big fans of Groq's fast, low-latency inference. Pipecat AI supports all the Groq models, including the new voice model. Lately, we've been obsessively playing a voice chat game that Mark Backman wrote. (My high score is 6, so far.) Here's Mark, with Groq's `Celeste-PlayAI` voice.

kwindla

31,791 次观看 • 1 年前

You can run Kimi-K2-Thinking, the most strongest agentic model, in Jan through Hugging Face. Add it to your Hugging Face Inference models to use it.

You can run Kimi-K2-Thinking, the most strongest agentic model, in Jan through Hugging Face. Add it to your Hugging Face Inference models to use it.

👋 Jan

40,186 次观看 • 8 个月前

OpenAI shipped a new speech-to-speech model today: gpt-realtime-2 This is the first speech-to-speech model good enough to use in my voice agents that do "real work." Or real play, for that matter. Here's gpt-realtime-2 as the brain of the ship AI in Gradient Bang. The voice-to-voice response and tool calling times here are unedited, so you can see exactly what the interaction with the model is like in an agent with a very complex system instruction and frequent tool calls. (I did clip out the subagent task execution segments, after gpt-realtime-2 starts a subagent via a tool call. Subagents in this config used gpt-5.2 "medium" effort.)

OpenAI shipped a new speech-to-speech model today: gpt-realtime-2 This is the first speech-to-speech model good enough to use in my voice agents that do "real work." Or real play, for that matter. Here's gpt-realtime-2 as the brain of the ship AI in Gradient Bang. The voice-to-voice response and tool calling times here are unedited, so you can see exactly what the interaction with the model is like in an agent with a very complex system instruction and frequent tool calls. (I did clip out the subagent task execution segments, after gpt-realtime-2 starts a subagent via a tool call. Subagents in this config used gpt-5.2 "medium" effort.)

kwindla

54,912 次观看 • 2 个月前

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) 🏋️‍♂️

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

Introducing Speech Engine. Developers can now turn their existing chat agent into a full voice agent with one prompt. Speech Engine combines our leading speech, transcription, and voice orchestration models into a single pipeline - all custom built to work best together.

Introducing Speech Engine. Developers can now turn their existing chat agent into a full voice agent with one prompt. Speech Engine combines our leading speech, transcription, and voice orchestration models into a single pipeline - all custom built to work best together.

ElevenLabs

134,449 次观看 • 2 个月前

Build a real-time AI Voice Agent that can actually sell. In less than 30 minutes, you'll learn how to build a sophisticated real-time voice sales agent that can have natural conversations with potential customers. Includes a full code notebook, recorded tutorial, and docs The stack: ⚡ fast inference 🎙 LiveKit for real-time audio/video infrastructure 🗣 realistic speech synthesis (STT/TTS)

Build a real-time AI Voice Agent that can actually sell. In less than 30 minutes, you'll learn how to build a sophisticated real-time voice sales agent that can have natural conversations with potential customers. Includes a full code notebook, recorded tutorial, and docs The stack: ⚡ fast inference 🎙 LiveKit for real-time audio/video infrastructure 🗣 realistic speech synthesis (STT/TTS)

Sarah Chieng

452,438 次观看 • 10 个月前

New course: Add voice to your AI agents and applications, built with Vocal Bridge (disclosure: an AI Fund portfolio company) and taught by its CEO Ashwyn Sharma. Voice applications historically required making a hard tradeoff: using fast voice-to-voice models that sacrifice reliability, or accurate speech-to-text pipelines that add latency. This course teaches you how to build voice agents that are both reliable and fast. You'll build three types of voice-enabled applications: a voice-interactive game where voice commands and mouse clicks work together over a single channel, an agent that gains a voice in about 10 lines of code without touching its prompts or tools, and an agent that places outbound phone calls using a make_phone_call function. Skills you'll gain: - Add a voice layer to an existing agent without rewriting your prompts, RAG pipeline, or tools - Give an agent the ability to place outbound calls and stream transcripts back live - Set up voice evaluation to score calls, catch regressions, and improve quality before deployment Join and add voice to your agents without overhauling your architecture:

New course: Add voice to your AI agents and applications, built with Vocal Bridge (disclosure: an AI Fund portfolio company) and taught by its CEO Ashwyn Sharma. Voice applications historically required making a hard tradeoff: using fast voice-to-voice models that sacrifice reliability, or accurate speech-to-text pipelines that add latency. This course teaches you how to build voice agents that are both reliable and fast. You'll build three types of voice-enabled applications: a voice-interactive game where voice commands and mouse clicks work together over a single channel, an agent that gains a voice in about 10 lines of code without touching its prompts or tools, and an agent that places outbound phone calls using a make_phone_call function. Skills you'll gain: - Add a voice layer to an existing agent without rewriting your prompts, RAG pipeline, or tools - Give an agent the ability to place outbound calls and stream transcripts back live - Set up voice evaluation to score calls, catch regressions, and improve quality before deployment Join and add voice to your agents without overhauling your architecture:

Andrew Ng

87,140 次观看 • 1 个月前

Today we’re excited to introduce Bland TTS, the first voice AI to cross the uncanny valley. Several months ago, our team solved one-shot style transfer of human speech. That means, from a single, brief MP3, you can clone any voice or remix another clone’s style (tone, cadence, or pronunciations, etc.). With Bland TTS: • Creatives can turn text into realistic sound effects or AI voice tracks with precise control over style and emotion. • Developers can plug in our TTS API to build voice apps fully customized to their liking. • Enterprises can launch AI-driven support lines that sound so natural — customers will save you as a contact (try talking to it on our site). 🧵Check out the thread below or visit our website to get started for free

Today we’re excited to introduce Bland TTS, the first voice AI to cross the uncanny valley. Several months ago, our team solved one-shot style transfer of human speech. That means, from a single, brief MP3, you can clone any voice or remix another clone’s style (tone, cadence, or pronunciations, etc.). With Bland TTS: • Creatives can turn text into realistic sound effects or AI voice tracks with precise control over style and emotion. • Developers can plug in our TTS API to build voice apps fully customized to their liking. • Enterprises can launch AI-driven support lines that sound so natural — customers will save you as a contact (try talking to it on our site). 🧵Check out the thread below or visit our website to get started for free

Bland

45,967,683 次观看 • 1 年前

I built a service desk agent using ElevenLabs’ new Conversational AI Agents feature. Watch the video to see how responsive it is! Previously, I used ElevenLabs for cloning my voice and used my generated voice for narrations in some of my youtube videos. This feature takes elevenlabs' voice AI to a whole new level! It simplifies systems that used to require separate TTS (text-to-speech) and STT (speech-to-text) processes for both sides of the conversation. Now, it’s much simpler! Create your own agent here What will you create with this?

I built a service desk agent using ElevenLabs’ new Conversational AI Agents feature. Watch the video to see how responsive it is! Previously, I used ElevenLabs for cloning my voice and used my generated voice for narrations in some of my youtube videos. This feature takes elevenlabs' voice AI to a whole new level! It simplifies systems that used to require separate TTS (text-to-speech) and STT (speech-to-text) processes for both sides of the conversation. Now, it’s much simpler! Create your own agent here What will you create with this?

Melvin Vivas

27,722 次观看 • 1 年前

How to build the world's fastest voice AI bot: - Self-host speech-to-text, LLM inference, and text-to-speech all together in the same container/cluster. - Route audio over the internet using WebRTC and edge networking. - Configure timings for voice activity detection, phrase endpointing, and other parts of the pipeline to optimize for latency. (There are trade-offs to doing this!) Here's a LLama 3 voice bot that has voice-to-voice response times of ~500ms. We used Deepgram's STT and TTS for this bot, and everything is hosted on cerebriumai's serverless GPU infrastructure.

How to build the world's fastest voice AI bot: - Self-host speech-to-text, LLM inference, and text-to-speech all together in the same container/cluster. - Route audio over the internet using WebRTC and edge networking. - Configure timings for voice activity detection, phrase endpointing, and other parts of the pipeline to optimize for latency. (There are trade-offs to doing this!) Here's a LLama 3 voice bot that has voice-to-voice response times of ~500ms. We used Deepgram's STT and TTS for this bot, and everything is hosted on cerebriumai's serverless GPU infrastructure.

kwindla

282,617 次观看 • 2 年前

Your AI visuals can finally stop being silent. Now in text-to-speech + music generation. Make the image. Animate it. Give it a voice. Add a soundtrack. Tiny workflow upgrade. Very dangerous for your free time.

Your AI visuals can finally stop being silent. Now in text-to-speech + music generation. Make the image. Animate it. Give it a voice. Add a soundtrack. Tiny workflow upgrade. Very dangerous for your free time.

getimg.ai

454,344 次观看 • 1 个月前

SPEECH-TO-TEXT STARTUPS ARE OFFICIALLY SWEATING RIGHT NOW. Google just dropped its own AI voice dictation app for macOS and iOS. You get all the premium feats of a paid speech-to-text app without any subscription. 100% FREE. Runs offline. Powered by Gemma 4. Download link in 🧵↓

SPEECH-TO-TEXT STARTUPS ARE OFFICIALLY SWEATING RIGHT NOW. Google just dropped its own AI voice dictation app for macOS and iOS. You get all the premium feats of a paid speech-to-text app without any subscription. 100% FREE. Runs offline. Powered by Gemma 4. Download link in 🧵↓

Charly Wargnier

68,640 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.

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

351,739 次观看 • 1 年前