Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Soniox TTS pronounces critical information precisely across all 60+ supported languages. Alphanumerics, email addresses, phone numbers, street addresses, IDs, and other structured information are spoken clearly and accurately, whether in German, Japanese, or any other supported language. This level of precision is critical in real-world applications, where getting a... show more

Soniox

1,953 subscribers

216,710 views • 1 month ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

13 Comments

AI Mastery Guide1 month ago

Getting one character wrong actually matters, good point.

Elara AI1 month ago

Soniox TTS nails precise pronunciation of IDs and addresses in 60 languages

Mujeeb Ahmed1 month ago

Soniox TTS looks really impressive for real-world voice applications.

Claire Bennett1 month ago

Impressive advancement in AI voice technology! Accurate pronunciation across languages opens new possibilities for global communication

Alice The Ai Expert1 month ago

Soniox TTS nails the details. 60+ languages, every number + address spot on. Critical info, zero guesswork

GP1 month ago

@grok does Soniox provide MCP to interact with service through Codex, Claude Code?

Nathan Roll1 month ago

Now do it in reverse

Soniox1 month ago

.oediv eht gnihctaw rof sknahT ⏪

Jacob1 month ago

Is there any way to control pronunciation? In Hebrew, unvocalized text leaves heteronyms (ספר = book/barber/counted) and names ambiguous, so they often come out wrong. Inline phoneme/IPA input via tags or similar, would solve this for any language. Happy to send examples.

Soniox1 month ago

Not yet, but we will see if we can bring it in since this feature is being requested a lot. Thanks for feedback.

Rao Umair1 month ago

Accurately speaking structured information across 60+ languages is a serious capability. Getting every number, symbol, and character right can make a huge difference in real world voice applications.

Aurora Lux1 month ago

Precision matters when every digit and character counts—multilingual TTS that gets structured information right is a huge win for real-world voice AI. 🔥🌍

Aaliya1 month ago

This kind of accuracy makes voice agents much more useful.

Related Videos

🚨 THIS IS INSANE A developer has released a free AI voice studio capable of cloning almost any voice in just a few seconds. It's called Voicebox. And it has already surpassed 50,500 stars on GitHub. Here's how it works: 1.- Upload a short audio sample and clone a voice in seconds. 2.- Generate speech in 23 different languages using multiple TTS engines. 3.- Run everything locally for greater privacy, and you can integrate it into your own applications. It also includes voice dictation, support for AI agents, and MCP integration. All in a single open-source tool. Save this tool. I've left the link in the next comment 👇

🚨 THIS IS INSANE A developer has released a free AI voice studio capable of cloning almost any voice in just a few seconds. It's called Voicebox. And it has already surpassed 50,500 stars on GitHub. Here's how it works: 1.- Upload a short audio sample and clone a voice in seconds. 2.- Generate speech in 23 different languages using multiple TTS engines. 3.- Run everything locally for greater privacy, and you can integrate it into your own applications. It also includes voice dictation, support for AI agents, and MCP integration. All in a single open-source tool. Save this tool. I've left the link in the next comment 👇

Nova

26,530 views • 1 month ago

BREAKING: Starting today, we are launching a Big Update to our Voice stack in Fo. We are the only agent in the market that you can call, and that makes calls for you. You can - Call Fo on it's phone number and be hands free - You can talk to it in your native language and make it call in local languages. This is big for our users across the world - You can have it speak bi-lingually, this was big for me, I speak Hinglish a lot, and it just makes the experience so personal. Agents that meet you where you are, your personal experiences, your local languages are the future. Wajo is building agents for the world. Welcome to the future.

BREAKING: Starting today, we are launching a Big Update to our Voice stack in Fo. We are the only agent in the market that you can call, and that makes calls for you. You can - Call Fo on it's phone number and be hands free - You can talk to it in your native language and make it call in local languages. This is big for our users across the world - You can have it speak bi-lingually, this was big for me, I speak Hinglish a lot, and it just makes the experience so personal. Agents that meet you where you are, your personal experiences, your local languages are the future. Wajo is building agents for the world. Welcome to the future.

Shivani Poddar

70,958 views • 17 days ago

Right now the main paradigm that we think of agents in is chatting back and forth, but the biggest use of tokens will come from agents that are just always on running in the background doing work for us, or ones triggered from a workflow. Agents will be working 24/7 in our workflows processing data, reviewing and generating documents, moving data between systems, writing code, accelerating decision making steps, and more. In Claude's new Managed Agents feature, in a couple minutes you can wire up an agent that can read contracts when they come into Box to review them, and then assign a task in Linear with the critical information from the contract. But this could have been any workflow, like reviewing documents for client onboarding, invoice processing, M&A due-diligence, data extraction pipelines, and millions of other use-cases. And integrating data across any system. This is only possible when you can have long-running agents that can complete real work in the background, accurately. Agents have the ability to execute code safely, leverage tools, access a compute sandbox, and connect across systems is clearly the architecture of the future. The industry is now making it easier and easier for enterprises to build and deploy these agents.

Right now the main paradigm that we think of agents in is chatting back and forth, but the biggest use of tokens will come from agents that are just always on running in the background doing work for us, or ones triggered from a workflow. Agents will be working 24/7 in our workflows processing data, reviewing and generating documents, moving data between systems, writing code, accelerating decision making steps, and more. In Claude's new Managed Agents feature, in a couple minutes you can wire up an agent that can read contracts when they come into Box to review them, and then assign a task in Linear with the critical information from the contract. But this could have been any workflow, like reviewing documents for client onboarding, invoice processing, M&A due-diligence, data extraction pipelines, and millions of other use-cases. And integrating data across any system. This is only possible when you can have long-running agents that can complete real work in the background, accurately. Agents have the ability to execute code safely, leverage tools, access a compute sandbox, and connect across systems is clearly the architecture of the future. The industry is now making it easier and easier for enterprises to build and deploy these agents.

Aaron Levie

17,543 views • 5 months ago

Meet the new Soniox voice library. Soniox Text-to-Speech now includes more than 200 built-in voices, carefully curated for different applications, styles, accents, ages, and voice characteristics. Every voice works across 60+ languages, so you can choose the voice that fits your product and use that same voice globally while preserving its identity and character. You can now browse and filter voices by: • Gender • Age • Accent • Use case, such as conversational, narration, or social media • Style, such as warm, confident, friendly, calm, energetic, or deep This makes it much easier to find a voice for a specific application, for example: • Conversational + warm + middle-aged • Narration + deep + confident • Social media + young + energetic • Educational + calm + friendly We manually selected, reviewed, and tagged the voices so the metadata reflects how the voices actually sound and where they work well. We also redesigned the TTS Playground to make it easier to browse, filter, compare, and test voices with your own text and languages. Learn more:

Meet the new Soniox voice library. Soniox Text-to-Speech now includes more than 200 built-in voices, carefully curated for different applications, styles, accents, ages, and voice characteristics. Every voice works across 60+ languages, so you can choose the voice that fits your product and use that same voice globally while preserving its identity and character. You can now browse and filter voices by: • Gender • Age • Accent • Use case, such as conversational, narration, or social media • Style, such as warm, confident, friendly, calm, energetic, or deep This makes it much easier to find a voice for a specific application, for example: • Conversational + warm + middle-aged • Narration + deep + confident • Social media + young + energetic • Educational + calm + friendly We manually selected, reviewed, and tagged the voices so the metadata reflects how the voices actually sound and where they work well. We also redesigned the TTS Playground to make it easier to browse, filter, compare, and test voices with your own text and languages. Learn more:

Soniox

126,350 views • 22 days ago

I'm willing to die on this hill: The best voice models are those with the best accuracy with key entities, not those that optimize for WER (Word Error Rate). Most speech-to-text providers optimize for WER, but in production applications, WER is not that relevant. Getting 95% of the words right is useless if you miss the customer's name, their phone number, or the street address they just spelled out letter by letter. The team at Gladia ran a very cool benchmark: • 1,000+ call center conversations • Lots of background noise • Focus on extracting names, phone numbers, addresses, locations, etc. The Gladia model outperformed every other state-of-the-art model by up to 17%! This is exactly the data that matters to companies using these models. You get this wrong, and everything downstream breaks. A few other things worth mentioning: • Latency on partials: < 150ms • 100+ languages supported • Dynamic language detection • Overall WER at 5.97% Definitely worth checking for anyone using voice models: Thanks to the Gladia team for collaborating with me on this post.

I'm willing to die on this hill: The best voice models are those with the best accuracy with key entities, not those that optimize for WER (Word Error Rate). Most speech-to-text providers optimize for WER, but in production applications, WER is not that relevant. Getting 95% of the words right is useless if you miss the customer's name, their phone number, or the street address they just spelled out letter by letter. The team at Gladia ran a very cool benchmark: • 1,000+ call center conversations • Lots of background noise • Focus on extracting names, phone numbers, addresses, locations, etc. The Gladia model outperformed every other state-of-the-art model by up to 17%! This is exactly the data that matters to companies using these models. You get this wrong, and everything downstream breaks. A few other things worth mentioning: • Latency on partials: < 150ms • 100+ languages supported • Dynamic language detection • Overall WER at 5.97% Definitely worth checking for anyone using voice models: Thanks to the Gladia team for collaborating with me on this post.

Santiago

25,204 views • 8 months ago

Today, Search Live is available in English in the U.S. — no Labs opt-in required. ✨ You can now have a free-flowing, back-and-forth conversation with Search using your voice and phone camera. Live in Search combines the power of Google Lens and AI Mode to see and accurately identify objects in front of you. This allows Search to understand exactly what you are looking at and help you find the most relevant information across the web to respond to your questions in real time. Try it today by tapping Live in the Google app (iOS and Android) or Lens, and let us know what you think!

Today, Search Live is available in English in the U.S. — no Labs opt-in required. ✨ You can now have a free-flowing, back-and-forth conversation with Search using your voice and phone camera. Live in Search combines the power of Google Lens and AI Mode to see and accurately identify objects in front of you. This allows Search to understand exactly what you are looking at and help you find the most relevant information across the web to respond to your questions in real time. Try it today by tapping Live in the Google app (iOS and Android) or Lens, and let us know what you think!

Google AI

48,572 views • 1 year ago

Lindsay Clancy trial day 22 Instructions given to the jury BEFORE deliberations started. "During your deliberations, you must not communicate with or provide any information to anyone by any means about this case. You may not use any electronic device or media such as a computer or a phone to communicate to anyone any information about this case or to conduct any research about this case until I accept your verdict. Kind of want to make that real clear. So, if somebody has a question in that jury room, you are NOT ALLOWED to try and answer it by anything other than through the exhibits and evidence you've heard. So I just kind of want want to make that real clear. Nobody is to use a phone to communicate to try and look. Don't talk to anybody while you're deliberating. Don't try and look up anything things like that. All right? Just kind of make that as clear as I can

Lindsay Clancy trial day 22 Instructions given to the jury BEFORE deliberations started. "During your deliberations, you must not communicate with or provide any information to anyone by any means about this case. You may not use any electronic device or media such as a computer or a phone to communicate to anyone any information about this case or to conduct any research about this case until I accept your verdict. Kind of want to make that real clear. So, if somebody has a question in that jury room, you are NOT ALLOWED to try and answer it by anything other than through the exhibits and evidence you've heard. So I just kind of want want to make that real clear. Nobody is to use a phone to communicate to try and look. Don't talk to anybody while you're deliberating. Don't try and look up anything things like that. All right? Just kind of make that as clear as I can

Ivanka Gog

10,759 views • 8 days ago

OSINT Tool: Investigate Unknown Phone Numbers 📱🔎 Phone numbers are powerful investigation pivots. With the right tools, a single number can reveal location clues, carrier info, and possible owner signals 🌐 One of the tools I like using when starting a phone investigation is a simple reverse phone lookup platform. Instead of manually searching everywhere, you can quickly check information linked to the number. With this tool you can often discover: 📞 Caller ID name (CNAM) 🌍 The country or calling area linked to the number 📡 Carrier or numbering plan information 🧩 Additional clues to continue your investigation The platform works by collecting public phone number data from multiple sources and compiling it into a simple lookup report for researchers. This kind of information is often the first pivot before searching social media, leaks, or messaging apps. One thing to remember though: caller information should always be treated as a clue, not a confirmed identity, because phone data can sometimes be inaccurate or spoofed. Still, tools like this are a great first step when investigating unknown calls. 🔗 Website link: In the next post, I’ll show you another method OSINT investigators use to uncover information from phone numbers. 📱🕵️‍♂️

OSINT Tool: Investigate Unknown Phone Numbers 📱🔎 Phone numbers are powerful investigation pivots. With the right tools, a single number can reveal location clues, carrier info, and possible owner signals 🌐 One of the tools I like using when starting a phone investigation is a simple reverse phone lookup platform. Instead of manually searching everywhere, you can quickly check information linked to the number. With this tool you can often discover: 📞 Caller ID name (CNAM) 🌍 The country or calling area linked to the number 📡 Carrier or numbering plan information 🧩 Additional clues to continue your investigation The platform works by collecting public phone number data from multiple sources and compiling it into a simple lookup report for researchers. This kind of information is often the first pivot before searching social media, leaks, or messaging apps. One thing to remember though: caller information should always be treated as a clue, not a confirmed identity, because phone data can sometimes be inaccurate or spoofed. Still, tools like this are a great first step when investigating unknown calls. 🔗 Website link: In the next post, I’ll show you another method OSINT investigators use to uncover information from phone numbers. 📱🕵️‍♂️

CyberSudo

13,768 views • 4 months ago

"The economy has turned the corner. It's no longer on the edge of bankruptcy. It has taken off for growth. And for us, we owe it to you, whether in Nigeria, the diaspora, or no matter where you are as a Nigerian, to break through and to lead. To all the students and other professionals, the promise of today is that Nigeria will be governed transparently and consistently, with value for progress among every Africans." - President Bola Tinubu addresses Nigerians in Rwanda.

"The economy has turned the corner. It's no longer on the edge of bankruptcy. It has taken off for growth. And for us, we owe it to you, whether in Nigeria, the diaspora, or no matter where you are as a Nigerian, to break through and to lead. To all the students and other professionals, the promise of today is that Nigeria will be governed transparently and consistently, with value for progress among every Africans." - President Bola Tinubu addresses Nigerians in Rwanda.

Office of the SA on Social Media to PBAT🇳🇬

13,426 views • 4 months ago

Kogta Financial, one of India's fastest growing retail-focused NBFCs, serves 100,000+ borrowers across 300+ branches pan India. Debt collection in India is incredibly diverse. Borrowers switch between languages, dialects, and local ways of speaking. Even a single mispronounced number can change the outcome of a call. That's exactly the challenge they set out to solve. Kogta Financial (I) Ltd built their collections agents entirely on Smallest AI's voice stack, giving them native support for rural accents, mixed-language speech, and numbers spoken in regional languages. The impact: - 15M+ calls placed, with high value EMIs settled during the call itself. - 130+ concurrent calls at a 0.2% failure rate.

Kogta Financial, one of India's fastest growing retail-focused NBFCs, serves 100,000+ borrowers across 300+ branches pan India. Debt collection in India is incredibly diverse. Borrowers switch between languages, dialects, and local ways of speaking. Even a single mispronounced number can change the outcome of a call. That's exactly the challenge they set out to solve. Kogta Financial (I) Ltd built their collections agents entirely on Smallest AI's voice stack, giving them native support for rural accents, mixed-language speech, and numbers spoken in regional languages. The impact: - 15M+ calls placed, with high value EMIs settled during the call itself. - 130+ concurrent calls at a 0.2% failure rate.

smallest.ai

319,226 views • 1 month ago

these guys are making Claude, Hermes, and DeepSeek argue with each other instead of just agreeing with you. this is the practical future of agent teams. with Bloome you just pick a task template, and it spins up a full agent team in a group chat to collaborate and get the job done. research, review, writing, market analysis, or anything you want. they brainstorm, review, and plan together. meanwhile, you or other human teammates can steer them or jump in, and stay in the same conversation so nothing gets lost across tools. since this is actual work, Bloome works across web, mobile, and desktop. try the desktop app first if you're using it seriously. same flexibility on the agent side too, you can connect any agents you want: ChatGPT, OpenClaw, Gemini… check them out →

these guys are making Claude, Hermes, and DeepSeek argue with each other instead of just agreeing with you. this is the practical future of agent teams. with Bloome you just pick a task template, and it spins up a full agent team in a group chat to collaborate and get the job done. research, review, writing, market analysis, or anything you want. they brainstorm, review, and plan together. meanwhile, you or other human teammates can steer them or jump in, and stay in the same conversation so nothing gets lost across tools. since this is actual work, Bloome works across web, mobile, and desktop. try the desktop app first if you're using it seriously. same flexibility on the agent side too, you can connect any agents you want: ChatGPT, OpenClaw, Gemini… check them out →

ℏεsam

62,794 views • 2 months ago

We Accel are excited to have led the pre-seed round in Ando, and deepen our partnership with Sara Du as they announce their seed round and $20M in total funding led by our friends at Index Ventures and Emergence Capital. Ando is a new team messaging product, built for a world where humans and agents work side by side. Agents are now very capable partners across software development, customer support, legal, finance, and many other functions. And as AI-native work becomes more multiplayer, coordinating context, memory, and activity across a growing number of agents is the new bottleneck. Today, Ando is opening up access to more teams, and you can sign up at More in the video and comments below on what makes Ando so unique.

We Accel are excited to have led the pre-seed round in Ando, and deepen our partnership with Sara Du as they announce their seed round and $20M in total funding led by our friends at Index Ventures and Emergence Capital. Ando is a new team messaging product, built for a world where humans and agents work side by side. Agents are now very capable partners across software development, customer support, legal, finance, and many other functions. And as AI-native work becomes more multiplayer, coordinating context, memory, and activity across a growing number of agents is the new bottleneck. Today, Ando is opening up access to more teams, and you can sign up at More in the video and comments below on what makes Ando so unique.

Ivan Zhou

25,370 views • 7 days ago

President of Poland Andrzej Duda: "Russia has shown in an unambiguous way that, unfortunately, this evil is still there, this Russian imperialism. I always emphasize this - it doesn't matter whether it's Tsarist, whether it's Soviet, Stalinist, Brezhnevist, or, last of all, Putinist imperialism. It is always the same imperialism that wants to enslave other nations, take their lands, take their natural resources, that wants to exploit them. And this is what is happening today in Ukraine, where they do not hesitate to kill, to murder civilians, to demolish cities. This is precisely Russian imperialism. I have no doubt that the world and wise people in America clearly see this."

President of Poland Andrzej Duda: "Russia has shown in an unambiguous way that, unfortunately, this evil is still there, this Russian imperialism. I always emphasize this - it doesn't matter whether it's Tsarist, whether it's Soviet, Stalinist, Brezhnevist, or, last of all, Putinist imperialism. It is always the same imperialism that wants to enslave other nations, take their lands, take their natural resources, that wants to exploit them. And this is what is happening today in Ukraine, where they do not hesitate to kill, to murder civilians, to demolish cities. This is precisely Russian imperialism. I have no doubt that the world and wise people in America clearly see this."

Anton Gerashchenko

196,990 views • 1 year ago

Sanders: Why is the whole country looking at this election? In fact, people all over the world are watching what’s going on here in Michigan. And the answer is that this is an election that will show the nation whether AIPAC and other billionaire-funded super PACs can spend tens and tens and tens of millions of dollars to buy a U.S. Senate seat, or whether, within a corrupt campaign finance system, the voices of ordinary Americans—the people of Michigan—can prevail. That is what this campaign is all about. It is about democracy versus oligarchy, and we are on the side of democracy.

Sanders: Why is the whole country looking at this election? In fact, people all over the world are watching what’s going on here in Michigan. And the answer is that this is an election that will show the nation whether AIPAC and other billionaire-funded super PACs can spend tens and tens and tens of millions of dollars to buy a U.S. Senate seat, or whether, within a corrupt campaign finance system, the voices of ordinary Americans—the people of Michigan—can prevail. That is what this campaign is all about. It is about democracy versus oligarchy, and we are on the side of democracy.

Acyn

41,373 views • 2 months ago

World Labs' Dr. Fei-Fei Li on why the 3D world and spatial intelligence are fundamentally different from language models: "Language is fundamentally a purely generated signal. There's no language out there. You don't go out in the nature and there's words written in the sky for you." "Whatever data you feed in, you pretty much can just somehow regurgitate with enough generalizability the same data out, and that's language to language." "But the 3D world is not. There is a 3D world out there that follows laws of physics, that has its own structures due to materials and many other things. And to fundamentally back that information out and be able to represent it and be able to generate it is just fundamentally quite a different problem." "We will be borrowing similar ideas or useful ideas from language and LLMs, but this is fundamentally philosophically, to me, a different problem." Fei-Fei Li

World Labs' Dr. Fei-Fei Li on why the 3D world and spatial intelligence are fundamentally different from language models: "Language is fundamentally a purely generated signal. There's no language out there. You don't go out in the nature and there's words written in the sky for you." "Whatever data you feed in, you pretty much can just somehow regurgitate with enough generalizability the same data out, and that's language to language." "But the 3D world is not. There is a 3D world out there that follows laws of physics, that has its own structures due to materials and many other things. And to fundamentally back that information out and be able to represent it and be able to generate it is just fundamentally quite a different problem." "We will be borrowing similar ideas or useful ideas from language and LLMs, but this is fundamentally philosophically, to me, a different problem." Fei-Fei Li

a16z

51,559 views • 3 days ago

introducing momo, the CRM for AI agents. it gives agents its own CRM, like Salseforce/Hubspot for humans. every AI native company will need dev agents, sales agents, customer support agents, HR, legal, finance, design agents. we're starting from customer relationships. we hypothesize that every important decision ever made in a company all derives from understanding customer data. even if dev agents are good at building things out in a day, if they don't have any customer signals on which features are working or where people are churning, it's no use. Momo does the following: 1) sets up your CRM with posthog + gmail data (or other web analytics tool) 2) analyzes the features your dev agents push 3) detects power users and churning users, aggregates CS tickets 4) sets up auto outreach email workflows & collects reponses 5) builds out list of issues to fix & next steps for your dev agent setting up custom onboarding for a few teams right now, please dm if interested :)

introducing momo, the CRM for AI agents. it gives agents its own CRM, like Salseforce/Hubspot for humans. every AI native company will need dev agents, sales agents, customer support agents, HR, legal, finance, design agents. we're starting from customer relationships. we hypothesize that every important decision ever made in a company all derives from understanding customer data. even if dev agents are good at building things out in a day, if they don't have any customer signals on which features are working or where people are churning, it's no use. Momo does the following: 1) sets up your CRM with posthog + gmail data (or other web analytics tool) 2) analyzes the features your dev agents push 3) detects power users and churning users, aggregates CS tickets 4) sets up auto outreach email workflows & collects reponses 5) builds out list of issues to fix & next steps for your dev agent setting up custom onboarding for a few teams right now, please dm if interested :)

Cailyn Y.

189,870 views • 5 months ago

Walmart updated their new AI call system for when customer call in It now says, “This call and your voice may be recorded for quality or other business purposes” You won’t believe what their “other business serves” are… It is not limited to AI training, voice cloning datasets, emotion tracking, behavioral analysis, customer profiling, speech recognition systems So when you call into Walmart they are literally recording. then storing your voice. It can possibly be used for things like “voice cloning” and more This is horrifying and it’s really happening Here are some of the more controversial uses: - behavioral profiling - emotion detection - cross-linking voice data with customer profiles - long-term biometric storage - AI model training without clear opt-in transparency (You are literally just calling in to talk to customer service) Even worse, modern AI systems can extract a lot more information from speech than people realize: - accent - emotional state - stress - probable age range - speaking habits - identity likelihood - purchase intent - deception indicators (though these systems are often unreliable) All this and voice cloning…. Some states have started to pass legislation to stop this but it’s still in the early stages so companies are getting away with it

Walmart updated their new AI call system for when customer call in It now says, “This call and your voice may be recorded for quality or other business purposes” You won’t believe what their “other business serves” are… It is not limited to AI training, voice cloning datasets, emotion tracking, behavioral analysis, customer profiling, speech recognition systems So when you call into Walmart they are literally recording. then storing your voice. It can possibly be used for things like “voice cloning” and more This is horrifying and it’s really happening Here are some of the more controversial uses: - behavioral profiling - emotion detection - cross-linking voice data with customer profiles - long-term biometric storage - AI model training without clear opt-in transparency (You are literally just calling in to talk to customer service) Even worse, modern AI systems can extract a lot more information from speech than people realize: - accent - emotional state - stress - probable age range - speaking habits - identity likelihood - purchase intent - deception indicators (though these systems are often unreliable) All this and voice cloning…. Some states have started to pass legislation to stop this but it’s still in the early stages so companies are getting away with it

Wall Street Apes

113,313 views • 4 months ago

New short course: Serverless Agentic Workflows with Amazon Bedrock. Learn to build and deploy serverless agents in this course created with Amazon Web Services and taught by Mike G Chambers, a Senior Developer Advocate at AWS specializing in GenAI. (Disclosure: I serve on Amazon's board.) Generative AI applications are becoming more complex, sophisticated, and agentic. Agentic applications have workloads that can be hard to predict in advance -- for example, what tools will it decide to call? -- and a serverless architecture helps you efficiently providing on-demand resources. This course teaches you to build and deploy a serverless agentic application. You’ll learn to create agents with tools, code execution, and guardrails, and build responsible agents for business use cases: - Build a customer service bot for a fictional tea mug business that can answering questions, retrieve information, and process orders. - Connect your customer service agent to a CRM to get customer info and log support tickets in real-time. - Explore how you invoke the agent, and see the trace to review the agent’s thought process and observation loop until it reaches its final output. - Attach a code interpreter to your agent, giving it the ability to perform accurate calculations by writing and running its own Python code. - Implement guardrails to prevent your agent from revealing sensitive information or using inappropriate language. By the end, you will have built a sophisticated AI agent capable of handling real-world customer support scenarios. Please sign up here!

New short course: Serverless Agentic Workflows with Amazon Bedrock. Learn to build and deploy serverless agents in this course created with Amazon Web Services and taught by Mike G Chambers, a Senior Developer Advocate at AWS specializing in GenAI. (Disclosure: I serve on Amazon's board.) Generative AI applications are becoming more complex, sophisticated, and agentic. Agentic applications have workloads that can be hard to predict in advance -- for example, what tools will it decide to call? -- and a serverless architecture helps you efficiently providing on-demand resources. This course teaches you to build and deploy a serverless agentic application. You’ll learn to create agents with tools, code execution, and guardrails, and build responsible agents for business use cases: - Build a customer service bot for a fictional tea mug business that can answering questions, retrieve information, and process orders. - Connect your customer service agent to a CRM to get customer info and log support tickets in real-time. - Explore how you invoke the agent, and see the trace to review the agent’s thought process and observation loop until it reaches its final output. - Attach a code interpreter to your agent, giving it the ability to perform accurate calculations by writing and running its own Python code. - Implement guardrails to prevent your agent from revealing sensitive information or using inappropriate language. By the end, you will have built a sophisticated AI agent capable of handling real-world customer support scenarios. Please sign up here!

Andrew Ng

81,048 views • 1 year ago