Loading video...

Video Failed to Load

Go Home

Have been doing some stem remixing work with Stable Audio 3. 📦 Medium model 🔉 init_audio holding the original audio file 😶‍🌫️ init_noise_level between 0.4-0.5 seems to be the sweet spot 🪄 Empty promps

teropa's profile picture

Tero Parviainen

9,816 subscribers

26,716 views • 4 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Using Stable Audio 3 to generate variations of an existing loop. Unconditional generation (no prompt), renoising the latents to 0.5, and just using different seeds seems to generate a nice neighbourhood around the original. Generally keeps the harmonic context and feel.
3:13

Using Stable Audio 3 to generate variations of an existing loop. Unconditional generation (no prompt), renoising the latents to 0.5, and just using different seeds seems to generate a nice neighbourhood around the original. Generally keeps the harmonic context and feel.

Tero Parviainen

10,894 views • 5 months ago

Did some color correction work and paired it with the original English audio yesterday
0:35

Did some color correction work and paired it with the original English audio yesterday

Zac

12,764 views • 7 months ago

Raw and unedited with original audio. Me and wife doing some shooting next to Virgin Tableview.
0:20

Raw and unedited with original audio. Me and wife doing some shooting next to Virgin Tableview.

GertFITNESS

15,805 views • 8 months ago

Stable Audio 2.5 in ComfyUI — the first audio generation model built for enterprise-grade sound production 🎶 ✨ Highlights: Generate 3-min tracks in 2s Multi-part compositions Audio inpainting / extensions Fully licensed dataset for commercial use 👉 Update ComfyUI → search “Stable Audio API”
1:07

Stable Audio 2.5 in ComfyUI — the first audio generation model built for enterprise-grade sound production 🎶 ✨ Highlights: Generate 3-min tracks in 2s Multi-part compositions Audio inpainting / extensions Fully licensed dataset for commercial use 👉 Update ComfyUI → search “Stable Audio API”

ComfyUI

20,846 views • 1 year ago

CW: Sweat, feet, audio only Just a quick little verbal macro foot tease audio while I catch up on some stuff! I’ll have to make a full foot audio eventually 😶‍🌫️😶‍🌫️
0:21

CW: Sweat, feet, audio only Just a quick little verbal macro foot tease audio while I catch up on some stuff! I’ll have to make a full foot audio eventually 😶‍🌫️😶‍🌫️

WbDubs (Wubbie🤡)

16,487 views • 2 years ago

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 👉
0:50

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

68,341 views • 1 year ago

The Israel Defence Forces have released audio claimed to be a conversation between Hamas operatives discussing an explosion at a hospital in Gaza. Sky News has not been able to verify the authenticity of the audio.
1:14

The Israel Defence Forces have released audio claimed to be a conversation between Hamas operatives discussing an explosion at a hospital in Gaza. Sky News has not been able to verify the authenticity of the audio.

Sky News

859,689 views • 3 years ago

I've been really wanting to work on video game audio as of recently, so I re-designed ALL of the audio for this VALORANT short. I deleted the original audio and re-imagined it with my own sounds, music, and brought on voice actors. Wouldn't it be cool if Riot Games saw this?
1:07

I've been really wanting to work on video game audio as of recently, so I re-designed ALL of the audio for this VALORANT short. I deleted the original audio and re-imagined it with my own sounds, music, and brought on voice actors. Wouldn't it be cool if Riot Games saw this?

Luke Dimond

16,509 views • 3 years ago

With the original audio 🤣
1:26

With the original audio 🤣

OasisCentral

32,060 views • 11 months ago

Over 10 years ago I downloaded a Flash file, consisting of a video and audio. Unfortunately, SWF is now dead. I've extracted the video and gotten the source file of the audio, and reconstructed them. The audio is already famous, but I wanted to restore the original meme format.
1:39

Over 10 years ago I downloaded a Flash file, consisting of a video and audio. Unfortunately, SWF is now dead. I've extracted the video and gotten the source file of the audio, and reconstructed them. The audio is already famous, but I wanted to restore the original meme format.

SwiftOnSecurity

621,550 views • 3 years ago

F5-TTS Finetune Web UI The E2-F5-TTS project has a huge update. Now anyone can easily finetune the model with their own audio using a Gradio app! It automatically transcribes the audio clips using whipser, and seems to work for most languages. Here's a Korean example.
1:21

F5-TTS Finetune Web UI The E2-F5-TTS project has a huge update. Now anyone can easily finetune the model with their own audio using a Gradio app! It automatically transcribes the audio clips using whipser, and seems to work for most languages. Here's a Korean example.

cocktail peanut

45,339 views • 2 years ago

🔉 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:
1:09

🔉 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

1,253,770 views • 10 months ago

Blue Archive Shirasu Azusa cosplay shoes wearing tutorial Due to the fact that the video was recorded quite a while ago, the original audio file has been lost, so we can only use BGM as a substitute :3
0:33

Blue Archive Shirasu Azusa cosplay shoes wearing tutorial Due to the fact that the video was recorded quite a while ago, the original audio file has been lost, so we can only use BGM as a substitute :3

ChinaDD老师🐼

181,703 views • 13 days ago

FSD V14.3 Destination Parking at Costco Surprised to see the car go past an empty spot exactly where the P icon was and then navigate into an adjacent parking lot that is not open to Costco shoppers. Sorry about the audio; the full version will have better audio - just trying to get some clips out in the mean time.
1:10

FSD V14.3 Destination Parking at Costco Surprised to see the car go past an empty spot exactly where the P icon was and then navigate into an adjacent parking lot that is not open to Costco shoppers. Sorry about the audio; the full version will have better audio - just trying to get some clips out in the mean time.

Devin Olsen

18,791 views • 6 months ago

(Leak) Suppressed weapon gameplay #Helldivers2 - The suppressor attachment seems to work for the most part, audio is unfinished
3:49

(Leak) Suppressed weapon gameplay #Helldivers2 - The suppressor attachment seems to work for the most part, audio is unfinished

IronS1ghts

156,005 views • 1 year ago

We’ve released our full paper on on the Stable Audio model 💿 arXiv: Code: Metrics: Demo: 🧵
1:30

We’ve released our full paper on on the Stable Audio model 💿 arXiv: Code: Metrics: Demo: 🧵

Stable Audio

132,325 views • 2 years ago

Gemini 3.1 Flash Live just dropped and it's available with LiveKit today. This is the first Gemini 3 native audio model on the Live API. Better instruction following, improved tool calling, reduced speaker drift, and support for 70+ languages. Audio in, audio out. No text conversion in between.
1:23

Gemini 3.1 Flash Live just dropped and it's available with LiveKit today. This is the first Gemini 3 native audio model on the Live API. Better instruction following, improved tool calling, reduced speaker drift, and support for 70+ languages. Audio in, audio out. No text conversion in between.

LiveKit

40,277 views • 7 months ago

AUDIO | The idea may have been good, but the execution was terrible. This is an alleged leaked audio recording of a conversation between Presidential Advisor Paul Tungwarara and a journalist.
2:51

AUDIO | The idea may have been good, but the execution was terrible. This is an alleged leaked audio recording of a conversation between Presidential Advisor Paul Tungwarara and a journalist.

𝐂𝐫𝐢𝐦𝐞 𝐖𝐚𝐭𝐜𝐡 𝐙𝐖

31,574 views • 2 months ago