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。

Sound on! Today, we’re introducing Pika Audio models: 4 frontier foundation models that cover the full spectrum of generative sound. And we’ve made them less expensive than every audio model on the market—up to 20x times cheaper.* *There is literally no disclaimer

Pika

151,021 subscribers

338,293 次观看 • 1 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

68 条评论

Pika 的头像

Pika1 个月前

You can start using Pika Soundtrack, Pika Music, Pika SFX, and Pika Speech exclusively on the Pika API Club:

Pika 的头像

Pika1 个月前

We’re thrilled to be able offer prices this low, thanks to our team’s innovations in training and inference efficiency. A few highlights: • Pika Soundtrack is 0.617 / seconds and 2x more cost-efficient than Hunyuan Foley, the only model with comparable video-to-audio functionality. • Pika SFX is up to 20x more cost-efficient than alternatives. • Pika Speech is 9x more cost-efficient ElevenLabs v3, 4.5x more cost-efficient than Cartesia and ElevenLabs Turbo, and 2x more cost-efficient than Fish Audio. • Pika Music is up to 10x more cost-efficient than comparable music models.

Pika 的头像

Pika1 个月前

The Pika Audio model family is just one of the things we’ve been working on behind the scenes. Keep an eye on us for more ways we’ll be making gen media more accessible to more people…

Pika 的头像

Pika1 个月前

ICYMI

madpencil_ 的头像

madpencil_1 个月前

Thanks for the early access, had fun. 🙌

Pika 的头像

Pika1 个月前

Thank you! Glad you enjoy it 🙌

madpencil_ 的头像

madpencil_1 个月前

🫡

Fotachu - AR GUY 的头像

Fotachu - AR GUY1 个月前

I tested it in early access and the model is so great! Especially at SFXs Here are two videos

Pika 的头像

Pika1 个月前

Sounds amazing! 🔥

Fotachu - AR GUY 的头像

Fotachu - AR GUY1 个月前

"sounds" is the exact word 😂

aymiee 的头像

aymiee1 个月前

Had a chance to try this out! Added dialogue to a video using Pika Audio Models. Wow. Some of the least expensive models I’ve used for this.

Pika 的头像

Pika1 个月前

Amazing! Love that 🔥

aymiee 的头像

aymiee1 个月前

Pika API Club is where it's at!!

Kosta🌱 的头像

Kosta🌱1 个月前

That’s amazing 🤩 Exciting for the future ahead

Pika 的头像

Pika1 个月前

We are excited too!

Kosta🌱 的头像

Kosta🌱1 个月前

🌱🐇🔥

沐阳的头像

沐阳1 个月前

amazing！I tried this new model.

Pika 的头像

Pika1 个月前

Love it! 🔥

Daniel Scott 的头像

Daniel Scott1 个月前

Amazing!! I was really needing a tool like that!

Pika 的头像

Pika1 个月前

We got you!

AZIZ | AI 🇸🇦 的头像

AZIZ | AI 🇸🇦1 个月前

Insane hopefully it supports Arabic 👀

Sheetal Shinde 的头像

Sheetal Shinde1 个月前

Thank you for the early access team had a quick test with Pika Soundtrack 🥁👇 more to come....

Pika 的头像

Pika1 个月前

Thank you! Love how it sounds 🥁

Sheetal Shinde 的头像

Sheetal Shinde1 个月前

Haha, your launch announcement 📣 got me, I had to hit that drum roll and follow! 😍🔥

Vadim 的头像

Vadim1 个月前

Congrats team, this is lowkey impressive 🙌

Pika 的头像

Pika1 个月前

Thanks!!!

Shine by Nous ✨ 的头像

Shine by Nous ✨1 个月前

It's huge and so cheap😍 thanks for early access to try it myself

Pika 的头像

Pika1 个月前

Thank you! Appreciate it 🙌

Shine by Nous ✨ 的头像

Shine by Nous ✨1 个月前

😃🫶

B.M. Cifer 的头像

B.M. Cifer1 个月前

Congrats on launching the new models! 🚀

Pika 的头像

Pika1 个月前

Thank you so much!

Lars_Pragmata 的头像

Lars_Pragmata1 个月前

amazing new models pika, youre the bests

Pika 的头像

Pika1 个月前

No, you are! ☺️

Wesley 的头像

Wesley1 个月前

This is awesome! Pika’s new audio models are super cheap and handle music, sounds, speech and more. Gonna make adding audio to videos way easier.

Pika 的头像

Pika1 个月前

Thank you! Let's make some noise 🥁

Jahan Zaib 的头像

Jahan Zaib1 个月前

It's epic

Pika 的头像

Pika1 个月前

Thank you! *Epic triumphant sound effect* 🎺

Sharon Riley 的头像

Sharon Riley1 个月前

Audio generation just got seriously more accessible

Pika 的头像

Pika1 个月前

It sure did!

Genius💡💹🧲 🤖 的头像

Genius💡💹🧲 🤖1 个月前

Pika Audio covering the full generative sound spectrum at lower costs is huge

Pika 的头像

Pika1 个月前

That is huge!

AI Clips 的头像

AI Clips1 个月前

Vintage rocket capsule scene feels like black‑and‑white launch just auditioned for audio model hype

Pika 的头像

Pika1 个月前

Nailed the audition 🚀

AI Clips 的头像

AI Clips1 个月前

Absolutely crushed that audition! No notes, just vibes.

Agentic Adam - DeployAIWorkers.com 的头像

Agentic Adam - DeployAIWorkers.com1 个月前

I hope your rate limiting is set up because I’m about to abuse tf out all your endpoints… 😏

Pika 的头像

Pika1 个月前

Is that a threat or a promise? 😏

Captain HaHaa 的头像

Captain HaHaa1 个月前

Woooo! Alright alright alright 🥳

Alan Maranho 的头像

Alan Maranho1 个月前

Huge!!

Pika 的头像

Pika1 个月前

Go huge or go home 💪

Pharm_Henry 🇺🇸🇳🇬🇨🇦 的头像

Pharm_Henry 🇺🇸🇳🇬🇨🇦1 个月前

Thank you for making it affordable to all😍🎉

RAVI KUMAR SAHU 的头像

RAVI KUMAR SAHU1 个月前

Pika is making generative audio seriously accessible with this launch. Four models covering the full sound workflow at up to 20× lower cost is a pretty bold move.

Pika 的头像

Pika1 个月前

Had to make some noise! 🔊

RAVI KUMAR SAHU 的头像

RAVI KUMAR SAHU1 个月前

Ofcourse

Krista Gable 的头像

Krista Gable1 个月前

Thank you for early access.

Pika 的头像

Pika1 个月前

Your'e welcome! 🎶

ᴍᴜʀᴘʜʏ 的头像

ᴍᴜʀᴘʜʏ1 个月前

Audio generation got a good upgrade

Pika 的头像

Pika1 个月前

*Upgrade sound* 🥳

BAIJ 的头像

BAIJ1 个月前

Open source or GTFO

Marco "Shikoba" Riccetti 的头像

Marco "Shikoba" Riccetti1 个月前

amazing!!!! 🔥

Pika 的头像

Pika1 个月前

Thank you! 🔥

Ziwen 的头像

Ziwen1 个月前

congrats for the launch!! 🚀

Manish Bhati 的头像

Manish Bhati1 个月前

Thank you @pika_labs For giving early access and opportunity to test pika audio models.

Richard Chen 的头像

Richard Chen1 个月前

nb

Dangcing Chan 的头像

Dangcing Chan1 个月前

20x cheaper? Sounds like my kind of deal. Finally, high-end audio that doesn't break the bank.

Aditi 的头像

Aditi1 个月前

Just gave it a try & that so cheap man🫡

Mo Elattar 的头像

Mo Elattar1 个月前

Need early access please

Dreaming Tulpa 🥓👑 的头像

Dreaming Tulpa 🥓👑1 个月前

oooooh i definitely need to give pika music a try

Leti Liu 的头像

Leti Liu1 个月前

boutta launch my AI singing career with Pika Audio😎

相关视频

I gave my silent cinematic video to the new Pika Audio Models and let Pika Soundtrack build the entire audio layer 🎬🔊 Footsteps, rain, ambience, suspenseful music, and motion-aware SFX, all synced to the visuals. Pika just dropped four new Pika Audio Models for Soundtrack, SFX, Speech, and Music. They cover the full generative audio spectrum and are the least expensive audio models on the market, with pricing up to 20x cheaper. You can try it here 👇 Here’s the result :

I gave my silent cinematic video to the new Pika Audio Models and let Pika Soundtrack build the entire audio layer 🎬🔊 Footsteps, rain, ambience, suspenseful music, and motion-aware SFX, all synced to the visuals. Pika just dropped four new Pika Audio Models for Soundtrack, SFX, Speech, and Music. They cover the full generative audio spectrum and are the least expensive audio models on the market, with pricing up to 20x cheaper. You can try it here 👇 Here’s the result :

Ai Arainz

35,390 次观看 • 1 个月前

This is a big day. Meta is open-sourcing AudioCraft. You can now generate incredible music and sounds with a single prompt. It includes the most performant Generative AI Model (audio) on the market, the "Llama" of Audio. The research framework contains the weights and code of these models: ▸ MusicGen: controllable text-to-music model. ▸ AudioGen: text-to-sound model. ▸ EnCodec: high fidelity neural audio codec. ▸ Multi Band Diffusion: An EnCodec compatible decoder using diffusion. This is going to tremendously speed up audio research 👏

This is a big day. Meta is open-sourcing AudioCraft. You can now generate incredible music and sounds with a single prompt. It includes the most performant Generative AI Model (audio) on the market, the "Llama" of Audio. The research framework contains the weights and code of these models: ▸ MusicGen: controllable text-to-music model. ▸ AudioGen: text-to-sound model. ▸ EnCodec: high fidelity neural audio codec. ▸ Multi Band Diffusion: An EnCodec compatible decoder using diffusion. This is going to tremendously speed up audio research 👏

Lior Alexander

231,723 次观看 • 3 年前

.Decagon co-founder and CTO Ashwin Sreenivas says the choice between expensive frontier models and cheaper, less capable ones is a false trade-off: "Even if you have a 'dumber model,' you can get it to higher performance on that specific task." "When we fine-tune smaller, dumber models, it's that they're just not as general purpose, but on the specific task we want them to do, they actually outperform the large, smart, state-of-the-art models." "So we end up getting all three things. It is better at the task, it is cheaper, and it is faster." Ashwin Sreenivas

.Decagon co-founder and CTO Ashwin Sreenivas says the choice between expensive frontier models and cheaper, less capable ones is a false trade-off: "Even if you have a 'dumber model,' you can get it to higher performance on that specific task." "When we fine-tune smaller, dumber models, it's that they're just not as general purpose, but on the specific task we want them to do, they actually outperform the large, smart, state-of-the-art models." "So we end up getting all three things. It is better at the task, it is cheaper, and it is faster." Ashwin Sreenivas

a16z

36,067 次观看 • 2 个月前

Wave 9 is here: a frontier model built for software engineering. Introducing our new family of models: SWE-1, SWE-1-lite, and SWE-1-mini. Based on internal evals, it has performance nearing that of frontier models from the foundation labs. Available now, only in Windsurf!

Wave 9 is here: a frontier model built for software engineering. Introducing our new family of models: SWE-1, SWE-1-lite, and SWE-1-mini. Based on internal evals, it has performance nearing that of frontier models from the foundation labs. Available now, only in Windsurf!

Devin Desktop

743,273 次观看 • 1 年前

Today, we're launching Belvedir We're making private AI models cheap and easy so the world can have trillions of them. Private AI models are cheaper, better, faster, and protect your data from frontier labs, but they're still to expensive and difficult to make for startups and consumers. Belvedir makes private AI models autonomously with less than 5 minutes of setup, so that private AI can finally be accessible to everyone

Today, we're launching Belvedir We're making private AI models cheap and easy so the world can have trillions of them. Private AI models are cheaper, better, faster, and protect your data from frontier labs, but they're still to expensive and difficult to make for startups and consumers. Belvedir makes private AI models autonomously with less than 5 minutes of setup, so that private AI can finally be accessible to everyone

Zachary Yu

89,359 次观看 • 1 个月前

Today we’re excited to publicly launch Fish Audio S1, the most expressive and natural TTS model on the market. - 6x cheaper than elevenlabs - 20K active developers - 5M ARR (real ARR) Clone your own voice for free and get started 👇

Today we’re excited to publicly launch Fish Audio S1, the most expressive and natural TTS model on the market. - 6x cheaper than elevenlabs - 20K active developers - 5M ARR (real ARR) Clone your own voice for free and get started 👇

helena

526,390 次观看 • 11 个月前

$🇨🇳 CHINA IS ALMOST READY TO UNDERCUT THE WORLD'S BEST AI MODELS. Six months ago, that sounded impossible. Today GLM-5.2 is open source and costs a fraction of frontier models. Zhipu's co-founder says Fable-class Chinese AI comes even sooner than people think. This is the same playbook China ran on solar, on steel, on EVs. Build it cheaper. Give it away. Take the market. If China delivers frontier AI at a fraction of the price, the economics holding up the U.S. AI market start to crack.$

🇨🇳 CHINA IS ALMOST READY TO UNDERCUT THE WORLD'S BEST AI MODELS. Six months ago, that sounded impossible. Today GLM-5.2 is open source and costs a fraction of frontier models. Zhipu's co-founder says Fable-class Chinese AI comes even sooner than people think. This is the same playbook China ran on solar, on steel, on EVs. Build it cheaper. Give it away. Take the market. If China delivers frontier AI at a fraction of the price, the economics holding up the U.S. AI market start to crack.

CryptoGoos

46,784 次观看 • 3 个月前

The wait is over. WAN 3.0 is here—20 references, enhanced visual and audio realism, and 30-second generations. In fact, this entire video was one generation. Up to 35% less expensive than competitors on the Pika API Club. Always.

The wait is over. WAN 3.0 is here—20 references, enhanced visual and audio realism, and 30-second generations. In fact, this entire video was one generation. Up to 35% less expensive than competitors on the Pika API Club. Always.

Pika

686,934 次观看 • 1 个月前

Today we’re launching Stable Audio 2.5: The first audio model built for enterprise-grade sound production 🔊 Audio influences brand engagement by 86%, but few enterprises are leveraging audio as an extension of their brand, making customized sound an untapped differentiator. Stable Audio 2.5 is purpose-built for this opportunity to create customizable, high-quality audio at scale, with capabilities that include: ▶️ Improved musical composition: Generate full songs with multi-part structure, meaning a clear intro, middle, and outro. ▶️ Audio inpainting: Input audio, select where the track should start, and the model uses the context to generate the rest of the track. ▶️ Customization: Our team can fine-tune Stable Audio 2.5 to help enterprises create the right sound for their brand. ▶️ Faster inference: The model can generate up to three-minute long tracks in under two seconds on a GPU, outputting in just eight steps (compared to ~50 in the previous model). You can learn more here 👉

Stability AI

68,301 次观看 • 1 年前

A foundation model for aging biology 🧬 Our LFMs are now matching or beating frontier models across clinical data, genetics, methylation, transcriptomics, and proteomics – using a single model family across the full biological stack. Published today on the cover of Cell! Read more and play with the model 👉 Full paper 👉

A foundation model for aging biology 🧬 Our LFMs are now matching or beating frontier models across clinical data, genetics, methylation, transcriptomics, and proteomics – using a single model family across the full biological stack. Published today on the cover of Cell! Read more and play with the model 👉 Full paper 👉

Alexander Amini

44,441 次观看 • 15 天前

1/6 introducing whalebench. which frontier model is the best trader? we gave 18 models access to the stock market, the same rules, and $100k each. then we let reality grade them.

1/6 introducing whalebench. which frontier model is the best trader? we gave 18 models access to the stock market, the same rules, and $100k each. then we let reality grade them.

Whale Bench

251,121 次观看 • 1 个月前

🔉 Introducing SAM Audio, the first unified model that isolates any sound from complex audio mixtures using text, visual, or span prompts. We’re sharing SAM Audio with the community, along with a perception encoder model, benchmarks and research papers, to empower others to explore new forms of expression and build applications that were previously out of reach. 🔗 Learn more:

🔉 Introducing SAM Audio, the first unified model that isolates any sound from complex audio mixtures using text, visual, or span prompts. We’re sharing SAM Audio with the community, along with a perception encoder model, benchmarks and research papers, to empower others to explore new forms of expression and build applications that were previously out of reach. 🔗 Learn more:

AI at Meta

1,253,324 次观看 • 9 个月前

Researchers at Meta recently shared MAGNeT, a single non-autoregressive transformer model for text-to-music & text-to-sound generation capable of generating audio on-par with the quality of SOTA models — at 7x the speed. MAGNeT is open source as part of AudioCraft. Hear audio samples and get more details on this work ➡️

Researchers at Meta recently shared MAGNeT, a single non-autoregressive transformer model for text-to-music & text-to-sound generation capable of generating audio on-par with the quality of SOTA models — at 7x the speed. MAGNeT is open source as part of AudioCraft. Hear audio samples and get more details on this work ➡️

AI at Meta

122,001 次观看 • 2 年前

Introducing Universal-1: Our most powerful and accurate Speech AI model yet. ✅ Trained on 12.5M hours of multilingual speech data ✅ 13.5% more accurate than models like Whisper ✅ Up to 30% fewer hallucinations than seq2seq models ✅ Just 38 seconds to process 1 hour of audio

Introducing Universal-1: Our most powerful and accurate Speech AI model yet. ✅ Trained on 12.5M hours of multilingual speech data ✅ 13.5% more accurate than models like Whisper ✅ Up to 30% fewer hallucinations than seq2seq models ✅ Just 38 seconds to process 1 hour of audio

AssemblyAI

23,511,312 次观看 • 2 年前

…Sorry, we were on mute. Today we’re launching Sound Effects on Pika. Now you can seamlessly generate and integrate sound into your videos. Either prompt the sound you want, or let Pika automatically generate it based on the content of your video. If that sounds great, it’s because it is.

…Sorry, we were on mute. Today we’re launching Sound Effects on Pika. Now you can seamlessly generate and integrate sound into your videos. Either prompt the sound you want, or let Pika automatically generate it based on the content of your video. If that sounds great, it’s because it is.

Pika

252,087 次观看 • 2 年前

With the new MAI models and Frontier Tuning capabilities we announced today, we're focused on helping every company move from just consuming a frontier model to fully participating at the frontier.

With the new MAI models and Frontier Tuning capabilities we announced today, we're focused on helping every company move from just consuming a frontier model to fully participating at the frontier.

Satya Nadella

100,739 次观看 • 4 个月前

A fine-tuned model can outperform frontier models and be cheaper and faster to run. Literally, every company I've met wants this. I want you to see these results from fine-tuning Qwen3 4B on AWS. It smokes both the out-of-the-box model and Claude Sonnet 4.6.

A fine-tuned model can outperform frontier models and be cheaper and faster to run. Literally, every company I've met wants this. I want you to see these results from fine-tuning Qwen3 4B on AWS. It smokes both the out-of-the-box model and Claude Sonnet 4.6.

Santiago

76,568 次观看 • 1 天前

Here's a real-time audio-reactive (sound on 🔊) fire sim running in Unreal 5.6. Each of the small emitters is linked to a different frequency of the audio spectrum. I've been experimenting with audio-driven Niagara FX and will be sharing more soon.

Here's a real-time audio-reactive (sound on 🔊) fire sim running in Unreal 5.6. Each of the small emitters is linked to a different frequency of the audio spectrum. I've been experimenting with audio-driven Niagara FX and will be sharing more soon.

Jesse Pitela

26,780 次观看 • 1 年前

We’re excited to share our groundbreaking new audio-driven performance model, featuring hyper-real expressions in near real-time. Any length video, in any style, is ready in 6 seconds or less—in HD. And we’ve managed to make it 20x faster and cheaper 💅 It’s all part of our vision to make AI video accessible and fun for more people—a way for them to connect, not just create. Rolling out soon in the Pika social app.

We’re excited to share our groundbreaking new audio-driven performance model, featuring hyper-real expressions in near real-time. Any length video, in any style, is ready in 6 seconds or less—in HD. And we’ve managed to make it 20x faster and cheaper 💅 It’s all part of our vision to make AI video accessible and fun for more people—a way for them to connect, not just create. Rolling out soon in the Pika social app.

Pika

1,243,932 次观看 • 1 年前

Today, we're announcing that Comfy is the first and only commercial license distributor for MiniMax (official)'s generative media models. MiniMax open weight models have been downloaded through Comfy close to 20M times. Now you can license them for commercial work. → Full commercial rights to your outputs → Fine-tuning and LoRA training, fully allowed → Client and agency projects covered → MiniMax Audio & Music, not just video Professional and Enterprise plans, with Enterprise covering every H3 model version. Request a license with the link below today ⬇️

Today, we're announcing that Comfy is the first and only commercial license distributor for MiniMax (official)'s generative media models. MiniMax open weight models have been downloaded through Comfy close to 20M times. Now you can license them for commercial work. → Full commercial rights to your outputs → Fine-tuning and LoRA training, fully allowed → Client and agency projects covered → MiniMax Audio & Music, not just video Professional and Enterprise plans, with Enterprise covering every H3 model version. Request a license with the link below today ⬇️

ComfyUI

145,070 次观看 • 1 个月前