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。

Our latest speech-to-speech model is faster, more accurate, and excels at function calling. Watch @promptshant and Brian Fioca build a realtime voice agent that can search the web and hand off tasks to reasoning models with full context.

OpenAI Developers

435,369 subscribers

81,863 次观看 • 1 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

7 条评论

OpenAI Developers 的头像

OpenAI Developers1 年前

Repo:

OpenAI Developers 的头像

OpenAI Developers1 年前

For more demos and tutorials on the latest product releases, sign up for Build Hours:

Evinstein 𝕏 的头像

Evinstein 𝕏1 年前

@promptshant @bfioca me after building my AI girlfriend 😏

Tom Bennet 的头像

Tom Bennet1 年前

@promptshant @bfioca Realtime voice agents? 🤯 My toddler already argues better than most AI. But impressive, I guess.

Laurence Bremner 的头像

Laurence Bremner1 年前

@promptshant @bfioca Reminds me of Jarvis from Iron Man

piantoni.eth 的头像

piantoni.eth1 年前

@promptshant @bfioca When is a new mini model version coming?

Patrick O 的头像

Patrick O1 年前

@promptshant @bfioca LoL

相关视频

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

135,145 次观看 • 4 个月前

Function calling is a powerful way to extend the capabilities of LLMs and AI agents by letting them use external tools. Our new short course Function calling and Data Extraction with LLMs, created with @NexusflowX and taught by Jiantao Jiao and Venkat, demonstrates how to prompt LLMs to form calls to external functions. You'll work with NexusRavenV2-13B, a 13B parameter open-source model that excels in function calling tasks while still being small enough to host locally. Learn to use function calling to extract structured data from unstructured text and access web APIs, and build an end-to-end application that processes customer service transcripts. You'll learn how to build LLM-powered applications that can analyze feedback, automate data entry, and enhance search. Please get started here:

Function calling is a powerful way to extend the capabilities of LLMs and AI agents by letting them use external tools. Our new short course Function calling and Data Extraction with LLMs, created with @NexusflowX and taught by Jiantao Jiao and Venkat, demonstrates how to prompt LLMs to form calls to external functions. You'll work with NexusRavenV2-13B, a 13B parameter open-source model that excels in function calling tasks while still being small enough to host locally. Learn to use function calling to extract structured data from unstructured text and access web APIs, and build an end-to-end application that processes customer service transcripts. You'll learn how to build LLM-powered applications that can analyze feedback, automate data entry, and enhance search. Please get started here:

Andrew Ng

110,703 次观看 • 2 年前

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

55,222 次观看 • 5 个月前

The Realtime API is officially out of beta and ready for your production voice agents! We’re also introducing gpt-realtime—our most advanced speech-to-speech model yet—plus new voices and API capabilities: 🔌 Remote MCPs 🖼️ Image input 📞 SIP phone calling ♻️ Reusable prompts

The Realtime API is officially out of beta and ready for your production voice agents! We’re also introducing gpt-realtime—our most advanced speech-to-speech model yet—plus new voices and API capabilities: 🔌 Remote MCPs 🖼️ Image input 📞 SIP phone calling ♻️ Reusable prompts

OpenAI Developers

562,288 次观看 • 1 年前

For questions that require web search, deeper reasoning, or more complex work, GPT-Live can delegate to our latest frontier model behind the scenes, and brings the result back into the conversation when it's ready.

For questions that require web search, deeper reasoning, or more complex work, GPT-Live can delegate to our latest frontier model behind the scenes, and brings the result back into the conversation when it's ready.

OpenAI

393,482 次观看 • 3 个月前

Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.

Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.

AK

290,517 次观看 • 3 年前

Cerebras inference is very fast. So fast that it changes how we think about configuring our LLMs for voice agent use cases. Kimi K2.6 is a 1T parameter reasoning model that Cerebras serves at 650 - 1,000 tokens per second (end-to-end throughput), with time to first token metrics as low as 150ms (latency). These numbers are two to three times faster than other similarly capable models. The biggest lever we get from this kind of speed is that we can use the model in reasoning mode, and still have excellent "time to first non-thinking token." This solves a big pain point we have in 2026 for voice agent use cases. Almost all recent innovation in post-training has focused on making models good at reasoning ("test time compute"). This is great, but it makes the user-facing model latency much, much slower. Which is a problem for conversational voice agents. We can run Kimi K2.6 with reasoning turned on, and get responses faster than other models produce with reasoning disabled. On my 30-turn voice agent benchmark, Kimi K2.6 with reasoning enabled ties GPT 5.1 and Haiku 4.5 with reasoning disabled, and is still about 200ms seconds faster! On my primary task agent benchmark, Kimi K2.6 is now the #2 model. It ranks just behind Gemini 3.5 Flash in "high" reasoning mode, and tied with GLM 5, Sonnet 4.6, and GPT 5.4 with reasoning set to "low." But Kimi K2.6 completes each turn in the agent loop in under 500ms. The other four models are all at least 3x slower. (Models only qualify for this benchmark if they can complete task turns at a P50 <4s.) A couple of other things that this speed buys us, for production voice agents: - Tool calls happen fast enough that we don't have to work around tool call latency in our pipeline design. - We can prompt the model to output structured data at the beginning of a response, followed by plain text for voice generation. This opens up possibilities like asking the model to do complex classification/generation tasks that influence the rest of the pipeline. For example, the model could create a detailed style prompt for a steerable TTS model, for each individual conversation turn. And, of course, you can use Kimi K2.6 with reasoning turned off. Cerebras calls this "instant" mode. Here's a video of a Cerebras Kimi K2.6 voice agent with voice-to-voice response time, measured at the client, under 500ms. This is the true response latency as perceived by the user, including all network and audio codec overhead, transcription and turn detection, Kimi K2.6 token generation, and voice generation. 500ms is, effectively, instant. So the Cerebras naming for this mode is a propos. :-)

Cerebras inference is very fast. So fast that it changes how we think about configuring our LLMs for voice agent use cases. Kimi K2.6 is a 1T parameter reasoning model that Cerebras serves at 650 - 1,000 tokens per second (end-to-end throughput), with time to first token metrics as low as 150ms (latency). These numbers are two to three times faster than other similarly capable models. The biggest lever we get from this kind of speed is that we can use the model in reasoning mode, and still have excellent "time to first non-thinking token." This solves a big pain point we have in 2026 for voice agent use cases. Almost all recent innovation in post-training has focused on making models good at reasoning ("test time compute"). This is great, but it makes the user-facing model latency much, much slower. Which is a problem for conversational voice agents. We can run Kimi K2.6 with reasoning turned on, and get responses faster than other models produce with reasoning disabled. On my 30-turn voice agent benchmark, Kimi K2.6 with reasoning enabled ties GPT 5.1 and Haiku 4.5 with reasoning disabled, and is still about 200ms seconds faster! On my primary task agent benchmark, Kimi K2.6 is now the #2 model. It ranks just behind Gemini 3.5 Flash in "high" reasoning mode, and tied with GLM 5, Sonnet 4.6, and GPT 5.4 with reasoning set to "low." But Kimi K2.6 completes each turn in the agent loop in under 500ms. The other four models are all at least 3x slower. (Models only qualify for this benchmark if they can complete task turns at a P50 <4s.) A couple of other things that this speed buys us, for production voice agents: - Tool calls happen fast enough that we don't have to work around tool call latency in our pipeline design. - We can prompt the model to output structured data at the beginning of a response, followed by plain text for voice generation. This opens up possibilities like asking the model to do complex classification/generation tasks that influence the rest of the pipeline. For example, the model could create a detailed style prompt for a steerable TTS model, for each individual conversation turn. And, of course, you can use Kimi K2.6 with reasoning turned off. Cerebras calls this "instant" mode. Here's a video of a Cerebras Kimi K2.6 voice agent with voice-to-voice response time, measured at the client, under 500ms. This is the true response latency as perceived by the user, including all network and audio codec overhead, transcription and turn detection, Kimi K2.6 token generation, and voice generation. 500ms is, effectively, instant. So the Cerebras naming for this mode is a propos. :-)

kwindla

40,593 次观看 • 4 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

351,956 次观看 • 2 年前

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.

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 次观看 • 1 年前

Voice is an interface, and I feel we’re going to see voice explode. OpenAI gpt-realtime is out and allows for native speech-to-speech and precise tool calling in real time. It can also take image inputs and place SIP phone calls - good for a quick triage before human handoff.

Voice is an interface, and I feel we’re going to see voice explode. OpenAI gpt-realtime is out and allows for native speech-to-speech and precise tool calling in real time. It can also take image inputs and place SIP phone calls - good for a quick triage before human handoff.

Allie K. Miller

80,345 次观看 • 1 年前

Sharing our latest short course: Building and Evaluating Data Agents, created in collaboration with Snowflake and taught by Anupam Datta (Anupam Datta) and Josh Reini (Josh Reini). A data agent extracts data from sources such as files or databases, analyzes it, and provides insights and visualizes its findings. But most data agents struggle with reliability or can't handle multi-step reasoning. In this course, you'll learn to build, trace, and evaluate a multi-agent workflow that plans tasks, pulls context from structured and unstructured data, performs web search, and summarizes or visualizes the final results. Learn more and enroll for free!

Sharing our latest short course: Building and Evaluating Data Agents, created in collaboration with Snowflake and taught by Anupam Datta (Anupam Datta) and Josh Reini (Josh Reini). A data agent extracts data from sources such as files or databases, analyzes it, and provides insights and visualizes its findings. But most data agents struggle with reliability or can't handle multi-step reasoning. In this course, you'll learn to build, trace, and evaluate a multi-agent workflow that plans tasks, pulls context from structured and unstructured data, performs web search, and summarizes or visualizes the final results. Learn more and enroll for free!

DeepLearning.AI

40,878 次观看 • 1 年前

Learn to build your own voice-activated AI assistant that can execute tasks like gathering recent AI news from the web, scripting out a podcast, and using tools to put all that into a multi-speaker podcast. See our new short course: "Building Live Voice Agents with Google’s ADK (Agent Development Kit),” taught by Google’s Lavi Nigam and Sita Lakshmi Sangameswaran. ADK provides modular components that make it easy to build and debug agents. It also includes a built-in web interface for tracing agentic reasoning. This course illustrates these concepts via building a live voice agent that can chain actions to complete a complex task like creating a podcast. This requires maintaining context, implementing guardrails, reasoning, and handling audio streaming, while keeping latency low. You’ll learn to: - Build voice agents that listen, reason, and respond - Guide your agent to follow a specific workflow to accomplish a task - Coordinate specialized agents to build an agentic podcast workflow that researches topics and produces multi-speaker audio - Understand how to deploy an agent into production Even if you’re not yet building voice systems, you'll find understanding how realtime agents stream data and maintain reliability useful for designing modern agentic applications. Please join here:

Learn to build your own voice-activated AI assistant that can execute tasks like gathering recent AI news from the web, scripting out a podcast, and using tools to put all that into a multi-speaker podcast. See our new short course: "Building Live Voice Agents with Google’s ADK (Agent Development Kit),” taught by Google’s Lavi Nigam and Sita Lakshmi Sangameswaran. ADK provides modular components that make it easy to build and debug agents. It also includes a built-in web interface for tracing agentic reasoning. This course illustrates these concepts via building a live voice agent that can chain actions to complete a complex task like creating a podcast. This requires maintaining context, implementing guardrails, reasoning, and handling audio streaming, while keeping latency low. You’ll learn to: - Build voice agents that listen, reason, and respond - Guide your agent to follow a specific workflow to accomplish a task - Coordinate specialized agents to build an agentic podcast workflow that researches topics and produces multi-speaker audio - Understand how to deploy an agent into production Even if you’re not yet building voice systems, you'll find understanding how realtime agents stream data and maintain reliability useful for designing modern agentic applications. Please join here:

Andrew Ng

118,297 次观看 • 11 个月前

pi-web-access is an extension that provides web search (and more) for Pi coding agent. The latest update introduces a new UX pattern: you can hit `Ctrl+S` to intercept agent searches mid-flight to inspect and curate exactly what makes it into the agent conversation. pi install npm:pi-web-access

pi-web-access is an extension that provides web search (and more) for Pi coding agent. The latest update introduces a new UX pattern: you can hit `Ctrl+S` to intercept agent searches mid-flight to inspect and curate exactly what makes it into the agent conversation. pi install npm:pi-web-access

Nico Bailon

29,352 次观看 • 7 个月前

Voice agents are awkward, and everyone notices: You ask a question. The agent thinks. You wait. And wait... Nobody wants this. I'd rather talk to a person. If your model's response time is over 300ms, you won't make it. Unfortunately, most text-to-speech models can't get anywhere close to that. I want you to take a look at the latest model released by : TTS-1.5. I built a simple voice agent using the model so you can see it in action and test it on your computer. You'll find the repository link below. The latency numbers of this model are wild: • Max model → under 250ms • Mini model → under 130ms That's 4x faster than prior generations and faster than human response times!

Voice agents are awkward, and everyone notices: You ask a question. The agent thinks. You wait. And wait... Nobody wants this. I'd rather talk to a person. If your model's response time is over 300ms, you won't make it. Unfortunately, most text-to-speech models can't get anywhere close to that. I want you to take a look at the latest model released by : TTS-1.5. I built a simple voice agent using the model so you can see it in action and test it on your computer. You'll find the repository link below. The latency numbers of this model are wild: • Max model → under 250ms • Mini model → under 130ms That's 4x faster than prior generations and faster than human response times!

Santiago

69,460 次观看 • 8 个月前

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale blog: Large-scale generative models such as GPT and DALL-E have revolutionized natural language processing and computer vision research. These models not only generate high fidelity text or image outputs, but are also generalists which can solve tasks not explicitly taught. In contrast, speech generative models are still primitive in terms of scale and task generalization. In this paper, we present Voicebox, the most versatile text-guided generative model for speech at scale. Voicebox is a non-autoregressive flow-matching model trained to infill speech, given audio context and text, trained on over 50K hours of speech that are neither filtered nor enhanced. Similar to GPT, Voicebox can perform many different tasks through in-context learning, but is more flexible as it can also condition on future context. Voicebox can be used for mono or cross-lingual zero-shot text-to-speech synthesis, noise removal, content editing, style conversion, and diverse sample generation. In particular, Voicebox outperforms the state-of-the-art zero-shot TTS model VALL-E on both intelligibility (5.9% vs 1.9% word error rates) and audio similarity (0.580 vs 0.681) while being up to 20 times faster.

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale blog: Large-scale generative models such as GPT and DALL-E have revolutionized natural language processing and computer vision research. These models not only generate high fidelity text or image outputs, but are also generalists which can solve tasks not explicitly taught. In contrast, speech generative models are still primitive in terms of scale and task generalization. In this paper, we present Voicebox, the most versatile text-guided generative model for speech at scale. Voicebox is a non-autoregressive flow-matching model trained to infill speech, given audio context and text, trained on over 50K hours of speech that are neither filtered nor enhanced. Similar to GPT, Voicebox can perform many different tasks through in-context learning, but is more flexible as it can also condition on future context. Voicebox can be used for mono or cross-lingual zero-shot text-to-speech synthesis, noise removal, content editing, style conversion, and diverse sample generation. In particular, Voicebox outperforms the state-of-the-art zero-shot TTS model VALL-E on both intelligibility (5.9% vs 1.9% word error rates) and audio similarity (0.580 vs 0.681) while being up to 20 times faster.

AK

429,355 次观看 • 3 年前

We need to build more homes, faster. And that’s what our government is laser-focused on doing – together with cities, towns, and Indigenous communities across the country. More from my speech at Ontario Chamber’s Economic Summit:

We need to build more homes, faster. And that’s what our government is laser-focused on doing – together with cities, towns, and Indigenous communities across the country. More from my speech at Ontario Chamber’s Economic Summit:

Justin Trudeau

206,558 次观看 • 2 年前

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

3,668,480 次观看 • 5 个月前

Excited about the launch of Amazon Nova Sonic, our new speech-to-speech model that helps make AI voice applications feel remarkably natural. It's designed to understand not just what people say, but how they say it – working with tone, style, and conversation flow including pauses and interruptions. Nova Sonic delivers speech understanding and generation through a single, unified model, making it easier for builders to develop voice applications that maintain important context and nuance for customer service, AI agents, and other use cases across industries. It’s available in Amazon Bedrock now. Look forward to seeing what teams build with Nova Sonic!

Excited about the launch of Amazon Nova Sonic, our new speech-to-speech model that helps make AI voice applications feel remarkably natural. It's designed to understand not just what people say, but how they say it – working with tone, style, and conversation flow including pauses and interruptions. Nova Sonic delivers speech understanding and generation through a single, unified model, making it easier for builders to develop voice applications that maintain important context and nuance for customer service, AI agents, and other use cases across industries. It’s available in Amazon Bedrock now. Look forward to seeing what teams build with Nova Sonic!

Andy Jassy

155,926 次观看 • 1 年前