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。

OuteTTS 1.0: Upgrades in Quality, Cloning, and 20 Languages - Best Performance: Generate audio around 42 seconds in a single run (approximately 8,192 tokens). It is recomended not to near the limits of this windows when generating. Usually, the best results are up to 7,000 tokens. - Context Reduction... show more

Chubby♨️

141,435 subscribers

25,779 次观看 • 1 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

6 条评论

AssemblyAI 的头像

AssemblyAI2 年前

Our speech-to-text models are the most accurate on the market with top rankings across industry benchmarks. - The highest accuracy rates—up to 95% - Up to 30% fewer hallucinations than other leaders - Low latency—63 minutes converts in 35 seconds Try via API for free today 👇

Momo 的头像

Momo1 年前

Weird that no model yet caught up to elevenlabs in overall cosistency

qTask 的头像

qTask1 年前

"OuteTTS 1.0 is redefining TTS innovation! High-quality multilingual speech synthesis across 20 languages, improved speaker cloning, and generating 42 seconds of audio (up to 8,192 tokens) are major milestones. Staying around 7,000 tokens ensures the best quality. This sets a new benchmark for adaptable, expressive TTS systems. 🚀 #TTS #Innovation"

Figure 的头像

Figure1 年前

ai talk faster than me

Muyiwa Moses 的头像

Muyiwa Moses1 年前

Just checked this out on Huggingface where it had a non commercial license. Am I missing something

Dmitry 的头像

Dmitry1 年前

list of languages and more

相关视频

Gemma 4 31B is way too slow on my MacBook Pro M5 Max with 128GB of unified memory. 42 seconds to generate the first line of code. 21 tokens per second after that. Uses 26GB of memory when loaded. I sat there waiting nearly a minute before it even started writing code. The output? Actually decent. The lava lamp it generated looks good. But 42 seconds to first token is a dealbreaker. Claude Opus 4.7 starts generating in under 2 seconds. GPT 5.5 is instant. Good model. Unusable speed. Local inference on a $5,399 machine still can't match the cloud.

Gemma 4 31B is way too slow on my MacBook Pro M5 Max with 128GB of unified memory. 42 seconds to generate the first line of code. 21 tokens per second after that. Uses 26GB of memory when loaded. I sat there waiting nearly a minute before it even started writing code. The output? Actually decent. The lava lamp it generated looks good. But 42 seconds to first token is a dealbreaker. Claude Opus 4.7 starts generating in under 2 seconds. GPT 5.5 is instant. Good model. Unusable speed. Local inference on a $5,399 machine still can't match the cloud.

BridgeMind

40,380 次观看 • 4 个月前

I’m testing the new 4-step Turbo LoRA for MiniMax. With just 16GB of VRAM, I can generate 15 seconds of 480p video in around 1 minute and 30 seconds! I also noticed something pretty funny if you use a song as an audio reference and tell the character to dance to it, the character actually follows the rhythm of the music surprisingly well.

I’m testing the new 4-step Turbo LoRA for MiniMax. With just 16GB of VRAM, I can generate 15 seconds of 480p video in around 1 minute and 30 seconds! I also noticed something pretty funny if you use a song as an audio reference and tell the character to dance to it, the character actually follows the rhythm of the music surprisingly well.

Alex

50,293 次观看 • 1 个月前

Audio Transcription with Google Gemini 1.5 Flash In this video, Gemini-Flash was able to transcribe 13 minutes of audio in 50-60 seconds. I have tested this with multiple audio files, and the transcription accuracy is close to 99%. If the audio is clear, you get 100% correct transcription. Even if the audio is really bad with a lot of noise, you still get around 95-96% accuracy. The code for this is available on GitHub. If you're interested, you can download and run it. You just need a Google API key.

Audio Transcription with Google Gemini 1.5 Flash In this video, Gemini-Flash was able to transcribe 13 minutes of audio in 50-60 seconds. I have tested this with multiple audio files, and the transcription accuracy is close to 99%. If the audio is clear, you get 100% correct transcription. Even if the audio is really bad with a lot of noise, you still get around 95-96% accuracy. The code for this is available on GitHub. If you're interested, you can download and run it. You just need a Google API key.

AshutoshShrivastava

123,061 次观看 • 2 年前

Seedream 5.0 Pro is now in Runway. Generate highly detailed images from a prompt or reference, with legible in-image text in up to 14 different languages. Try it now at the link below.

Seedream 5.0 Pro is now in Runway. Generate highly detailed images from a prompt or reference, with legible in-image text in up to 14 different languages. Try it now at the link below.

Runway

21,780 次观看 • 2 个月前

Seed Audio 1.0 is now available on Runway for all paid plans. Generate up to 120 seconds of dynamic speech, sound design and music with simple text prompts. Try it now at the link below.

Seed Audio 1.0 is now available on Runway for all paid plans. Generate up to 120 seconds of dynamic speech, sound design and music with simple text prompts. Try it now at the link below.

Runway

32,302 次观看 • 3 个月前

This is macro economics in a couple of seconds.. if you understand this.. you RUN to the goldshop

This is macro economics in a couple of seconds.. if you understand this.. you RUN to the goldshop

freegolds frontrunning central banks

41,620 次观看 • 1 年前

When it comes down to it, it's all about how you tell the story and not what model you use. BUT it is nice to be able to generate in 4K and up to 20 seconds. 😉

When it comes down to it, it's all about how you tell the story and not what model you use. BUT it is nice to be able to generate in 4K and up to 20 seconds. 😉

OpenArt

15,913 次观看 • 9 个月前

The 5 min BTC up/down market on Polymarket is usually manipulated in the last 3 seconds to flip the result. See video. If the price is close to the target, it will be flipped in the last seconds. You can 5-10x your money betting it flips. Does not work if volatility spikes.

The 5 min BTC up/down market on Polymarket is usually manipulated in the last 3 seconds to flip the result. See video. If the price is close to the target, it will be flipped in the last seconds. You can 5-10x your money betting it flips. Does not work if volatility spikes.

Duo Nine ⚡ YCC

22,884 次观看 • 7 个月前

How to extend videos using Seedance 2.0 in 3 easy steps 🦄 1. Generate video 1 (e.g. 15 seconds). 2. Use video 1 as a reference when generating video 2. 3. In the prompt for video two, start with "Continue this video". Both videos should have reference images of your characters. Here's a 30 second clip made with two 15 second generations. Workflow in comments below.

How to extend videos using Seedance 2.0 in 3 easy steps 🦄 1. Generate video 1 (e.g. 15 seconds). 2. Use video 1 as a reference when generating video 2. 3. In the prompt for video two, start with "Continue this video". Both videos should have reference images of your characters. Here's a 30 second clip made with two 15 second generations. Workflow in comments below.

Martin LeBlanc

25,133 次观看 • 4 个月前

🚨 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 次观看 • 1 个月前

Is it a hot take to say these 50 seconds are the best visuals in any opening for 2025

Is it a hot take to say these 50 seconds are the best visuals in any opening for 2025

𝕍𝕁 ☆

86,580 次观看 • 11 个月前

MICROSOFT OPEN SOURCED A 7B PARAMETER MODEL THAT TRANSCRIBES 60 MINUTES OF AUDIO IN A SINGLE PASS and it's completely free VIBEVOICE ASR no chunking, no context loss, full speaker diarization baked in not just speech to text..not a basic wrapper who spoke, when they spoke, exactly what they said..all in one shot and it handles the hard stuff too..50+ languages, custom hotwords, long form audio that breaks every other tool the model doesn't know what "context window" means apparently Available on macOS and Windows right now. Free to use. Free to fine tune. Free to build on.

MICROSOFT OPEN SOURCED A 7B PARAMETER MODEL THAT TRANSCRIBES 60 MINUTES OF AUDIO IN A SINGLE PASS and it's completely free VIBEVOICE ASR no chunking, no context loss, full speaker diarization baked in not just speech to text..not a basic wrapper who spoke, when they spoke, exactly what they said..all in one shot and it handles the hard stuff too..50+ languages, custom hotwords, long form audio that breaks every other tool the model doesn't know what "context window" means apparently Available on macOS and Windows right now. Free to use. Free to fine tune. Free to build on.

Rahul

1,375,300 次观看 • 5 个月前

Nick Fuentes talks about the price of success "If you want to be the best, that's just how it is… you can't have anything in your life that you're not willing to walk away from in 30 seconds when you feel the heat around the corner."

Nick Fuentes talks about the price of success "If you want to be the best, that's just how it is… you can't have anything in your life that you're not willing to walk away from in 30 seconds when you feel the heat around the corner."

S.clips

22,110 次观看 • 2 个月前

This store made $5K in 24 hours It was created in 32 seconds with AI Ecom is a matter of being fast I’ve written a process to set up a store in 20 seconds RT + Comment “20” and I’ll send it over (must follow to get dm)

This store made $5K in 24 hours It was created in 32 seconds with AI Ecom is a matter of being fast I’ve written a process to set up a store in 20 seconds RT + Comment “20” and I’ll send it over (must follow to get dm)

Henry

12,205 次观看 • 1 年前

GPT-5.4 is here. Native computer-use capabilities. Up to 1M tokens of context in Codex and the API. Best-in-class agentic coding for complex tasks. Scalable tool search across larger ecosystems. More efficient reasoning for long, tool-heavy workflows.

GPT-5.4 is here. Native computer-use capabilities. Up to 1M tokens of context in Codex and the API. Best-in-class agentic coding for complex tasks. Scalable tool search across larger ecosystems. More efficient reasoning for long, tool-heavy workflows.

OpenAI Developers

1,075,852 次观看 • 6 个月前