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。

We're making building with the text-to-speech API even easier by adding it to the Playground! Just enter a message to generate audio in one of six preset voices.

OpenAI Developers

451,383 subscribers

125,173 次观看 • 2 年前 •via X (Twitter)

科学技术教育

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

Hindi Speech Model should be free and open-source. And we’re making it happen. >High quality >Multiple voices >UI to generate audio + API for deployment Follow me to get notified when it launches. Listen to the audio till the end!

Hindi Speech Model should be free and open-source. And we’re making it happen. >High quality >Multiple voices >UI to generate audio + API for deployment Follow me to get notified when it launches. Listen to the audio till the end!

Dheemanth Reddy

59,811 次观看 • 1 年前

Today, we're adding 21 new flagship voices to Grok via API.

Today, we're adding 21 new flagship voices to Grok via API.

SpaceX Super Intelligence

16,547,400 次观看 • 4 个月前

AudioLDM is a text-to-audio model by Haohe Liu et al. It is available in the 🧨 Diffusers library from v0.15.0 onwards, and is capable of generating realistic music, sound effects and speech Try it in this Colab to generate music for yourself:

AudioLDM is a text-to-audio model by Haohe Liu et al. It is available in the 🧨 Diffusers library from v0.15.0 onwards, and is capable of generating realistic music, sound effects and speech Try it in this Colab to generate music for yourself:

Sanchit Gandhi

27,143 次观看 • 3 年前

Today we're rolling out a redesigned navigation for the OpenAI API platform, making it easier to find what you're looking for.

Today we're rolling out a redesigned navigation for the OpenAI API platform, making it easier to find what you're looking for.

Hayden

123,197 次观看 • 5 个月前

UnitedHealth Group is eliminating 30% of prior authorization requirements, just one way we're making it easier to get care.

UnitedHealth Group is eliminating 30% of prior authorization requirements, just one way we're making it easier to get care.

UnitedHealth Group

2,587,095 次观看 • 3 个月前

Local AI Assistant on Smart Glasses Using our Wearables SDK to take a picture, ask a question with Whisper’s speech to text, and use Chrome’s Prompt API (powered by Gemini Nano) to generate a response, displaying the results back on the glasses’ display Works with compatible smart glasses (in this case the Brilliant Labs Frame running custom firmware)

Local AI Assistant on Smart Glasses Using our Wearables SDK to take a picture, ask a question with Whisper’s speech to text, and use Chrome’s Prompt API (powered by Gemini Nano) to generate a response, displaying the results back on the glasses’ display Works with compatible smart glasses (in this case the Brilliant Labs Frame running custom firmware)

Brilliant Wear

49,490 次观看 • 1 年前

👕 SIGNED JERSEY GIVEAWAY 👕 We're giving away 2 signed TL jerseys to celebrate making it to the Champions Stage of the Paris Major! All you have to do to enter is reply to this tweet with a "good luck" message to the team! 💪🇺🇸

👕 SIGNED JERSEY GIVEAWAY 👕 We're giving away 2 signed TL jerseys to celebrate making it to the Champions Stage of the Paris Major! All you have to do to enter is reply to this tweet with a "good luck" message to the team! 💪🇺🇸

Team Liquid CS

299,863 次观看 • 3 年前

the craziest unintentional foreshadowing is the voices in march to the sea sounding like they're saying "dema" iirc it's a logic preset which makes it even crazier

the craziest unintentional foreshadowing is the voices in march to the sea sounding like they're saying "dema" iirc it's a logic preset which makes it even crazier

jimbo

14,626 次观看 • 9 个月前

You direct the look. The motion. The sound. MiniMax H3 is now available in Luma Agents. Generate up to 15 seconds of 2K video with native stereo sound, guided by text, image, video, and audio references. More creative range. One continuous workflow with Luma. Try it today →

You direct the look. The motion. The sound. MiniMax H3 is now available in Luma Agents. Generate up to 15 seconds of 2K video with native stereo sound, guided by text, image, video, and audio references. More creative range. One continuous workflow with Luma. Try it today →

Luma

19,645 次观看 • 2 个月前

AI video is here and it's powerful. But it can be tricky to get the exact video you want. We've made it easier by adding video models to the Replicate playground. You can prompt for videos directly, or generate images and then animate them. Read more on on our blog. Link below

AI video is here and it's powerful. But it can be tricky to get the exact video you want. We've made it easier by adding video models to the Replicate playground. You can prompt for videos directly, or generate images and then animate them. Read more on on our blog. Link below

Replicate

29,168 次观看 • 1 年前

here's how to do this in 2 minutes: - upload monk image to gemini - ask it to generate a 1:1 json prompt - generate the voice with minimax audio - generate the image with nano banana pro - lipsync with infinitetalk (open-source) congrats you just saved $10k for a trip to china to find a monk.

here's how to do this in 2 minutes: - upload monk image to gemini - ask it to generate a 1:1 json prompt - generate the voice with minimax audio - generate the image with nano banana pro - lipsync with infinitetalk (open-source) congrats you just saved $10k for a trip to china to find a monk.

0x ROAS

242,758 次观看 • 9 个月前

“Republican” Curtis Sliwa just refused to commit to letting NYPD cooperate with the National Guard if Trump deploys them the New York City. What is the point of even having a Republican like this if he’s just making it easier for Mamdani to win?

“Republican” Curtis Sliwa just refused to commit to letting NYPD cooperate with the National Guard if Trump deploys them the New York City. What is the point of even having a Republican like this if he’s just making it easier for Mamdani to win?

johnny maga

656,331 次观看 • 1 年前

I just wanted to study in Barnard College’s library. I’m not even allowed to enter because of the protest. My friend just sent me this recording of the SHELTER IN PLACE ORDER issued to students inside the building:

I just wanted to study in Barnard College’s library. I’m not even allowed to enter because of the protest. My friend just sent me this recording of the SHELTER IN PLACE ORDER issued to students inside the building:

Shoshana Aufzien

41,760 次观看 • 1 年前

We're making it easier to check into your Airbnb. With smart lock integration, you’ll get a unique key code for your stay—right in the app

We're making it easier to check into your Airbnb. With smart lock integration, you’ll get a unique key code for your stay—right in the app

Brian Chesky

635,384 次观看 • 3 年前

I held a Spelling Bee for Twitch Chat, where they have to spell words one letter at a time with text-to-speech. I was absolutely broken by the end of the stream.

I held a Spelling Bee for Twitch Chat, where they have to spell words one letter at a time with text-to-speech. I was absolutely broken by the end of the stream.

shindigs

167,090 次观看 • 1 年前

WE’RE GOING EVEN BIGGER & BETTER THIS XMAS! We’re making it a Christmas to remember by inviting you to celebrate the start of the festive season with the chance to win a £2,000 Inspire TravelCard to be spent on the City Break of your dreams! ✈️ Read on to see how to enter… #UtilitaUnwrapped

WE’RE GOING EVEN BIGGER & BETTER THIS XMAS! We’re making it a Christmas to remember by inviting you to celebrate the start of the festive season with the chance to win a £2,000 Inspire TravelCard to be spent on the City Break of your dreams! ✈️ Read on to see how to enter… #UtilitaUnwrapped

Utilita

15,758 次观看 • 1 年前

Tsundere Malfoid slop will continue until morale improves. One thing I'm using is a 3D latent upscaling with minimax H3... and one of the great things is that it's faster to get high-resolution videos. I can generate quickly at low resolution and then upscale it to finish. The main problem is that it often garbles the text, so if I try anything with Japanese audio and English subtitles, it doesn't work. So in those cases, I have to generate at a relatively high resolution to begin with, which takes longer.

Tsundere Malfoid slop will continue until morale improves. One thing I'm using is a 3D latent upscaling with minimax H3... and one of the great things is that it's faster to get high-resolution videos. I can generate quickly at low resolution and then upscale it to finish. The main problem is that it often garbles the text, so if I try anything with Japanese audio and English subtitles, it doesn't work. So in those cases, I have to generate at a relatively high resolution to begin with, which takes longer.

Emerald Apple

45,336 次观看 • 27 天前