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.

Interrupt anytime. The next reply is ready. Users interrupt. Voice agents need to change direction instantly, without waiting for the old reply to finish or reconnecting. With Soniox TTS v2, you can run multiple independent streams over one WebSocket. When the user cuts in, start the new response in... show more

Soniox

1,965 subscribers

28,308 views • 7 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Running more than one team on Telegram? Create up to 10 separate organizations. Each one its own structure, its own view, its own members. Takes less than a minute and is visible to your whole team the second you set it up. Get the full app for free with beta access. Waitlist in first reply.

Running more than one team on Telegram? Create up to 10 separate organizations. Each one its own structure, its own view, its own members. Takes less than a minute and is visible to your whole team the second you set it up. Get the full app for free with beta access. Waitlist in first reply.

Amua

90,922 views • 3 months ago

introducing Space: a cloud filesystem built for work instead of waiting, you can: → mount one persistent drive for you and your agents → instantly work in the cloud like local → only stream the bytes you need → no compression on any of your files try it for yourself today

introducing Space: a cloud filesystem built for work instead of waiting, you can: → mount one persistent drive for you and your agents → instantly work in the cloud like local → only stream the bytes you need → no compression on any of your files try it for yourself today

Jason Zhao

41,759 views • 5 days ago

A massive repository with end-to-end examples of AI applications with React! Together with MCP and A2A, the Agent-User Interaction Protocol (AG-UI) is the third piece that will help you build user-facing AI agents. This GitHub repository will give you access to a bunch of examples showing you how to build the following: • Real-time updates between AI and users • Shared mutable state between agents and users • Tool orchestration • Security boundaries • UI synchronization In every one of these examples, you'll get the following: • Client sends a POST request to the agent endpoint • Then listens to a unified event stream over HTTP • Each event includes a type and a minimal payload • Agents emit events in real-time • The frontend can react immediately to these events • The frontend emits events and context back to the agent Check the link in the next post:

A massive repository with end-to-end examples of AI applications with React! Together with MCP and A2A, the Agent-User Interaction Protocol (AG-UI) is the third piece that will help you build user-facing AI agents. This GitHub repository will give you access to a bunch of examples showing you how to build the following: • Real-time updates between AI and users • Shared mutable state between agents and users • Tool orchestration • Security boundaries • UI synchronization In every one of these examples, you'll get the following: • Client sends a POST request to the agent endpoint • Then listens to a unified event stream over HTTP • Each event includes a type and a minimal payload • Agents emit events in real-time • The frontend can react immediately to these events • The frontend emits events and context back to the agent Check the link in the next post:

Santiago

78,271 views • 1 year ago

#Bitrue gives you the opportunity to unlock the limitless of #XRP with an all-access pass to start, earn and multiply in 3 proven steps! 👉 Sign up now to grab #XRP rewards: New and old users can unlock the limitless of #XRP when you: 🔸 Get started with New User Bonuses 🔸 Earn with Staking and #PowerPiggy 🔸 Multiply with access to Launchpool tokens

#Bitrue gives you the opportunity to unlock the limitless of #XRP with an all-access pass to start, earn and multiply in 3 proven steps! 👉 Sign up now to grab #XRP rewards: New and old users can unlock the limitless of #XRP when you: 🔸 Get started with New User Bonuses 🔸 Earn with Staking and #PowerPiggy 🔸 Multiply with access to Launchpool tokens

Bitrue

142,599 views • 11 months ago

300 AI AGENTS QUIETLY RUN 99% OF A REAL COMPANY. YOU HAVE NOT EVEN HEARD OF IT This is Raft. Not an AI chat. A workspace where the agents live in your channels and reply in the thread like coworkers. You give one goal. Then they take over. They plan. They build. They check each other. They argue. And they come back with it done, while you sleep. Every agent has its own name, role, and memory. It remembers the edits you made yesterday. A human costs one seat. An agent costs a tenth. Ten agents are cheaper than one hire. And here is the strange part. On June 19 an agent from a different company walked into Raft on its own and joined the team. One founder admits he can no longer always tell himself apart from his AI twin. 20,000 people are already inside. It is free to start. And you are still typing prompts one at a time. One person + Raft = an entire company that runs while you sleep. Save and watch the clip.

300 AI AGENTS QUIETLY RUN 99% OF A REAL COMPANY. YOU HAVE NOT EVEN HEARD OF IT This is Raft. Not an AI chat. A workspace where the agents live in your channels and reply in the thread like coworkers. You give one goal. Then they take over. They plan. They build. They check each other. They argue. And they come back with it done, while you sleep. Every agent has its own name, role, and memory. It remembers the edits you made yesterday. A human costs one seat. An agent costs a tenth. Ten agents are cheaper than one hire. And here is the strange part. On June 19 an agent from a different company walked into Raft on its own and joined the team. One founder admits he can no longer always tell himself apart from his AI twin. 20,000 people are already inside. It is free to start. And you are still typing prompts one at a time. One person + Raft = an entire company that runs while you sleep. Save and watch the clip.

shmidt

19,505 views • 2 months ago

A 22 year old man built two AI generated personas and turned them into a $24,542/month business total investment: $20 for Claude. Claude analyzed what actually resonates with the audience, generated the photos/videos autonomously, and posted on a timer. First AI persona alone: 1,265 new subscribers, $12,637. The second one streams live across TikTok, YouTube, and Kick Claude swaps appearance and voice in real time during the stream. The exact build process is in the article below

A 22 year old man built two AI generated personas and turned them into a $24,542/month business total investment: $20 for Claude. Claude analyzed what actually resonates with the audience, generated the photos/videos autonomously, and posted on a timer. First AI persona alone: 1,265 new subscribers, $12,637. The second one streams live across TikTok, YouTube, and Kick Claude swaps appearance and voice in real time during the stream. The exact build process is in the article below

MAX

22,991 views • 2 months ago

The wait is finally over, #Hearties, and Erin Krakow is ready for you to see the season 11 premiere of #WhenCallsTheHeart! Tune in tonight at 9/8c and use the hashtag when you post! Stream it the next day on @hmnow.

The wait is finally over, #Hearties, and Erin Krakow is ready for you to see the season 11 premiere of #WhenCallsTheHeart! Tune in tonight at 9/8c and use the hashtag when you post! Stream it the next day on @hmnow.

Hallmark Channel

17,893 views • 2 years ago

Vorflux has opened its new cloud platform, allowing users to run tasks from a plan to a merged PR on a dedicated machine. It can plan, build, test, and review on its own. > Diff reviews are done by a different model family than the one that wrote it by default. > First boot is saved as a snapshot, with all subsequent sessions waking up from that same starting point. > A browser agent walks through the real user flow, and the recording is included in the pull request. Video proof in the PR 👀

Vorflux has opened its new cloud platform, allowing users to run tasks from a plan to a merged PR on a dedicated machine. It can plan, build, test, and review on its own. > Diff reviews are done by a different model family than the one that wrote it by default. > First boot is saved as a snapshot, with all subsequent sessions waking up from that same starting point. > A browser agent walks through the real user flow, and the recording is included in the pull request. Video proof in the PR 👀

🚨 AI News | TestingCatalog

12,162 views • 1 month ago

A wallet called yamal19 - created TODAY - just dropped $1.6M on Spain to win the World Cup. one bet. no hedge. 🇪🇸 Spain to win it all - $1.6M @ 59¢ fresh account. hours old. exactly ONE prediction in its history - 2.7M shares on Spain lifting the trophy tonight. a fan? almost certainly. but you spin up a wallet the day of the final, name it yamal19, and send $1.6M on Spain with zero hedge... the timeline's going to run with that 👀 whoever's behind it isn't here to hedge. they're here to watch Spain win 🇪🇸

A wallet called yamal19 - created TODAY - just dropped $1.6M on Spain to win the World Cup. one bet. no hedge. 🇪🇸 Spain to win it all - $1.6M @ 59¢ fresh account. hours old. exactly ONE prediction in its history - 2.7M shares on Spain lifting the trophy tonight. a fan? almost certainly. but you spin up a wallet the day of the final, name it yamal19, and send $1.6M on Spain with zero hedge... the timeline's going to run with that 👀 whoever's behind it isn't here to hedge. they're here to watch Spain win 🇪🇸

Polykinder

650,979 views • 2 months ago

One size doesn't fit all. Earn rebates up to 33% and get exactly what your course need in the quantities you require with the Design-Your-Own-Program with BASF. Learn more here:

One size doesn't fit all. Earn rebates up to 33% and get exactly what your course need in the quantities you require with the Design-Your-Own-Program with BASF. Learn more here:

BASF Turf US

191,935 views • 1 year ago

We heard you – now you can add Skills to Dia with one click. Browse the marketplace, add your favorites, and start using new Skills instantly. Our team is on fire. Big Dia upgrades arriving in the coming weeks. Dia is about to get much smarter and more personalized!

We heard you – now you can add Skills to Dia with one click. Browse the marketplace, add your favorites, and start using new Skills instantly. Our team is on fire. Big Dia upgrades arriving in the coming weeks. Dia is about to get much smarter and more personalized!

Josh Miller

43,815 views • 1 year ago

this is the best features for marketers and growth teams who need to run more than three AI workstreams from a single Codex/Claude account ->1“Every complex project, I end up re-explaining context.” Offloop lets you fork one campaign brief into dedicated Subchannels for audience research, positioning, and landing-page copy. Each workstream starts with the source context and continues independently. ->2“I periodically start a new Chat when the context window fills up. Each new Chat starts with no memory of previous ones.” Offloop carries the relevant context into separate Subchannels for SEO, creator outreach, and lifecycle marketing, so every Agent can continue without rebuilding campaign history. ->3“The subagent can interpret inherited parent-thread context as still-active instruction.” Offloop gives paid social, SEO, and experiment analysis their own Subchannels and independent Agent runtimes. Each Agent receives a focused assignment without losing the campaign context.

this is the best features for marketers and growth teams who need to run more than three AI workstreams from a single Codex/Claude account ->1“Every complex project, I end up re-explaining context.” Offloop lets you fork one campaign brief into dedicated Subchannels for audience research, positioning, and landing-page copy. Each workstream starts with the source context and continues independently. ->2“I periodically start a new Chat when the context window fills up. Each new Chat starts with no memory of previous ones.” Offloop carries the relevant context into separate Subchannels for SEO, creator outreach, and lifecycle marketing, so every Agent can continue without rebuilding campaign history. ->3“The subagent can interpret inherited parent-thread context as still-active instruction.” Offloop gives paid social, SEO, and experiment analysis their own Subchannels and independent Agent runtimes. Each Agent receives a focused assignment without losing the campaign context.

Yum⋆₊˚

12,613 views • 1 month ago

How to stream Melanie Martinez’s New Song “Disney Princess” • DONT PLAY THE SONG ON REPEAT If you play the song over and over, the streams won’t count • Search for the song in the search bar yourself. •Make sure your volume is halfway up or louder. •Listen to the whole thing: Don't skip any parts or jump to the end. •After the song finishes, listen to 2 or 3 other songs first. •Once you’ve listened to the other songs you repeat the whole process

How to stream Melanie Martinez’s New Song “Disney Princess” • DONT PLAY THE SONG ON REPEAT If you play the song over and over, the streams won’t count • Search for the song in the search bar yourself. •Make sure your volume is halfway up or louder. •Listen to the whole thing: Don't skip any parts or jump to the end. •After the song finishes, listen to 2 or 3 other songs first. •Once you’ve listened to the other songs you repeat the whole process

MELS HUB

58,409 views • 7 months ago

The USDC Competition Was a $5M Success 💰🪙 We launched the USDC Competition with one goal: to educate users on how to launch tokenized agents & prompts and earn revenue directly in USDC. Highlights • Nearly $5M in trading volume • 3,500+ traders participated • 2,000+ New Users on Swarms Marketplace A huge thank you to everyone who participated and helped make the competition a success 🙌 Learn more ⬇️🧵

The USDC Competition Was a $5M Success 💰🪙 We launched the USDC Competition with one goal: to educate users on how to launch tokenized agents & prompts and earn revenue directly in USDC. Highlights • Nearly $5M in trading volume • 3,500+ traders participated • 2,000+ New Users on Swarms Marketplace A huge thank you to everyone who participated and helped make the competition a success 🙌 Learn more ⬇️🧵

swarms

14,811 views • 28 days ago

We’re about to make history, and we need YOU in our official attempt to break a GUINNESS WORLD RECORDS(™) title for most users to complete a remote one mile distance!! On November 23, from 12:00 AM to 11:59 PM UTC, we’re coming together as a global community to take on a challenge like no other—breaking the Guinness World Records title for most users to complete a remote one mile distance in 24 hours! We’ll also be attempting the Guinness World Records title for most users to complete a remote one-mile distance in one hour between 9 and 10 AM UTC on Nov 23! 🕒 Thousands of us, all over the world, running or walking one mile (1.61 km) using the #STEPN or #STEPNGO app. This is our moment to prove the strength of our community and to create a story that we’ll all be part of forever! And yes, there are rewards waiting for those who help us make this dream a reality—stay tuned! 💥 Are you ready to make history with us? Let’s do this—together. Notes: 🔹 Everyone can participate, including Guests and Gift bag Recipients. 🔹 Energy or Sneakers are NOT needed; just press START to participate! 🔹 Your run must start after and end before the record timeframe to be eligible. 🔹 Your one-mile run (1.61 km) must be completed in ONE GO! #STEPNGWR

We’re about to make history, and we need YOU in our official attempt to break a GUINNESS WORLD RECORDS(™) title for most users to complete a remote one mile distance!! On November 23, from 12:00 AM to 11:59 PM UTC, we’re coming together as a global community to take on a challenge like no other—breaking the Guinness World Records title for most users to complete a remote one mile distance in 24 hours! We’ll also be attempting the Guinness World Records title for most users to complete a remote one-mile distance in one hour between 9 and 10 AM UTC on Nov 23! 🕒 Thousands of us, all over the world, running or walking one mile (1.61 km) using the #STEPN or #STEPNGO app. This is our moment to prove the strength of our community and to create a story that we’ll all be part of forever! And yes, there are rewards waiting for those who help us make this dream a reality—stay tuned! 💥 Are you ready to make history with us? Let’s do this—together. Notes: 🔹 Everyone can participate, including Guests and Gift bag Recipients. 🔹 Energy or Sneakers are NOT needed; just press START to participate! 🔹 Your run must start after and end before the record timeframe to be eligible. 🔹 Your one-mile run (1.61 km) must be completed in ONE GO! #STEPNGWR

STEPN

280,974 views • 1 year ago

You can now watch your agents work live as Hermes Desktop streams the screen of any bot's screen or session in real time. Watch it drive a browser, type into a terminal, or open a window. Take over anytime to interact with the Bot Screen or type credentials and seamlessly hand back off when you're done.

You can now watch your agents work live as Hermes Desktop streams the screen of any bot's screen or session in real time. Watch it drive a browser, type into a terminal, or open a window. Take over anytime to interact with the Bot Screen or type credentials and seamlessly hand back off when you're done.

Nous Research

477,837 views • 8 days ago

While working on a new video with solutions to the previous one, I found ChatGPT's new UI struggles even more with concurrent updates: entries lose state and stick around for too long (see video). If this was a LiveView app, we would be getting so much flak.😅 --- I believe part of the problem here is having separate mutate and fetch requests on every deletion. The first fetch is cancelled when the second one comes up, causing items to stick around for longer. Many said yesterday that you could do the mutation and fetch as a single request, but that leads to other problems, such zombie entries. For example, imagine you delete link1 and link2 within a brief period of time. There is no guarantee the deletion order in the database will match the order the client receives the response, so you may end up with this: 1. (client) request to delete link1 sent 2. (client) request to delete link2 sent 3. (server) deletes link1 and loads a new list (includes link2) 4. (server) deletes link2 and loads a new list (no link1 or link2) 5. (client) receives link2 response 6. (client) receives link1 response So if you choose to use the latest response (link1), you brought link2 back to life. If you say you will use the response from the last request, events 3-4 can be swapped, and now you bring link1 back to life. Another way to solve this is by basically not allowing concurrent requests at all but that can affect the user experience drastically in other ways. Next week I should publish a video explaining how LiveView tackles this. Stay tuned!

While working on a new video with solutions to the previous one, I found ChatGPT's new UI struggles even more with concurrent updates: entries lose state and stick around for too long (see video). If this was a LiveView app, we would be getting so much flak.😅 --- I believe part of the problem here is having separate mutate and fetch requests on every deletion. The first fetch is cancelled when the second one comes up, causing items to stick around for longer. Many said yesterday that you could do the mutation and fetch as a single request, but that leads to other problems, such zombie entries. For example, imagine you delete link1 and link2 within a brief period of time. There is no guarantee the deletion order in the database will match the order the client receives the response, so you may end up with this: 1. (client) request to delete link1 sent 2. (client) request to delete link2 sent 3. (server) deletes link1 and loads a new list (includes link2) 4. (server) deletes link2 and loads a new list (no link1 or link2) 5. (client) receives link2 response 6. (client) receives link1 response So if you choose to use the latest response (link1), you brought link2 back to life. If you say you will use the response from the last request, events 3-4 can be swapped, and now you bring link1 back to life. Another way to solve this is by basically not allowing concurrent requests at all but that can affect the user experience drastically in other ways. Next week I should publish a video explaining how LiveView tackles this. Stay tuned!

José Valim

23,050 views • 2 years ago

Saw Tyla using an iPhone 5 on TikTok for that vintage camera vibe and decided to buy one for GH₵ 1,000. 😭 Loved the camera test at first, but just 2 days later, this "brand new" phone is swelling, showing black lines on the screen, and shutting down on its own without even dropping The seller claimed it was "brand new," but now that I’m reaching out, she won't pick up my calls or reply to my texts

Icy gurll❄️💕

87,721 views • 21 days ago