Well folks, Qwen did it again. They have released a new, fresh update for their Qwen 3.8 Max model, version 0902. This latest iteration from Alibaba is being described as a significant leap forward in capabilities.
The previous Qwen 3.8 Max was already impressive, but this new release is said to be sharper at understanding real-world codebases, more stable during extended agentic tasks, and genuinely strong in multimodal reasoning. To put these claims to the test, the model was challenged with several real-world scenarios.
First, it tackled a critical bug in a New South Wales State Emergency Services (SES NSW) control center application. The issue involved incorrect prioritization of emergency incidents, where P2 priority cases were being sorted by the smallest number of affected people instead of the largest. This could have serious real-world consequences. The model, after an initial API key adjustment, successfully identified and fixed the bug, ensuring incidents are now correctly prioritized. This was a remarkable demonstration of its ability to handle complex, Docker-based full-stack applications.
Next, Qwen 3.8 Max faced a tough multimodal reasoning challenge: analyzing a WhatsApp chat screenshot and a complex prompt describing a difficult employee-boss situation. The model had to navigate misinterpretations and choose the least disastrous response from three options, justifying its choice. It didn't fall for the obvious traps, instead demonstrating impressive "risk modeling" by understanding the subtle human dynamics and selecting the safest, most discreet reply.
Its multilingual capabilities were also put to the test, asking it to name famous writers and their works in nearly 80 languages, including some with no established literary tradition. Qwen 3.8 Max delivered an outstanding performance, accurately rendering titles in native scripts and honestly stating when no literary tradition existed for certain languages.
Finally, the model was presented with a hard scientific research question about the failures of recent room-temperature superconductivity claims. It provided an expert-level answer, correctly identifying the core, non-negotiable measurement for true superconductivity and explaining why other indicators can be mimicked by ordinary materials.
This update truly showcases Qwen 3.8 Max's enhanced reasoning, coding, multimodal, and multilingual abilities. It's a significant step forward for open-weight models.
For those interested in exploring this model, keep an eye on its official Hugging Face page for future weight releases.
What are your thoughts on Qwen 3.8 Max's latest update? Have you tried any of the Qwen models before?
To stay updated with the latest in AI, consider subscribing to the t.me/iaosai channel.
The previous Qwen 3.8 Max was already impressive, but this new release is said to be sharper at understanding real-world codebases, more stable during extended agentic tasks, and genuinely strong in multimodal reasoning. To put these claims to the test, the model was challenged with several real-world scenarios.
First, it tackled a critical bug in a New South Wales State Emergency Services (SES NSW) control center application. The issue involved incorrect prioritization of emergency incidents, where P2 priority cases were being sorted by the smallest number of affected people instead of the largest. This could have serious real-world consequences. The model, after an initial API key adjustment, successfully identified and fixed the bug, ensuring incidents are now correctly prioritized. This was a remarkable demonstration of its ability to handle complex, Docker-based full-stack applications.
Next, Qwen 3.8 Max faced a tough multimodal reasoning challenge: analyzing a WhatsApp chat screenshot and a complex prompt describing a difficult employee-boss situation. The model had to navigate misinterpretations and choose the least disastrous response from three options, justifying its choice. It didn't fall for the obvious traps, instead demonstrating impressive "risk modeling" by understanding the subtle human dynamics and selecting the safest, most discreet reply.
Its multilingual capabilities were also put to the test, asking it to name famous writers and their works in nearly 80 languages, including some with no established literary tradition. Qwen 3.8 Max delivered an outstanding performance, accurately rendering titles in native scripts and honestly stating when no literary tradition existed for certain languages.
Finally, the model was presented with a hard scientific research question about the failures of recent room-temperature superconductivity claims. It provided an expert-level answer, correctly identifying the core, non-negotiable measurement for true superconductivity and explaining why other indicators can be mimicked by ordinary materials.
This update truly showcases Qwen 3.8 Max's enhanced reasoning, coding, multimodal, and multilingual abilities. It's a significant step forward for open-weight models.
For those interested in exploring this model, keep an eye on its official Hugging Face page for future weight releases.
What are your thoughts on Qwen 3.8 Max's latest update? Have you tried any of the Qwen models before?
To stay updated with the latest in AI, consider subscribing to the t.me/iaosai channel.
Telegram
International Advancements in Open Source Artificial Intelligence
A channel to provide news about new advancements and updates in the open source AI arena internationally.
one should not forget the contributions of meta in the open source AI. after a period of silence, it seems that meta is making a come back which is good for the open models. Meta just announced Muse Spark 1.3, a new multimodal reasoning model designed for complex, long-horizon agentic work, coding, and general computer use.
This release is particularly noteworthy because Meta plans to open-weight the model very soon, which is exciting news for the open-source community. Muse Spark 1.3 features an impressive 1 million token context window and is priced competitively at $1.25 per million tokens for input and $4.25 for output.
Meta claims this model stands toe-to-toe with leading models like GPT-5.6 and Opus 5 on agentic and coding benchmarks. Tests have shown Muse Spark 1.3 performs strongly in professional tool use and agentic computer tasks, often outperforming competitors. It particularly shines in long context retrieval, maintaining high accuracy in the high 90s, while other models tend to decline significantly.
In practical demonstrations, the model successfully handled complex tasks. For example, when given a goal to build and deploy a self-contained animation website to AWS S3 and CloudFront, it autonomously planned and executed all necessary steps, including creating the S3 bucket, uploading the HTML file, and configuring the CloudFront distribution, resulting in a fully working website. It also showcased strong vision capabilities by accurately interpreting a WhatsApp conversation, understanding nuanced double meanings and situational awareness. Furthermore, it provided a flawless, step-by-step solution to a challenging chemistry and math problem, demonstrating robust scientific reasoning. Its multilingual capabilities are also impressive, generating culturally aware drink lists across 80 languages with correct native scripts.
This model was run using an agent like Hermes, where it plans and executes commands based on a single prompt, highlighting its autonomous capabilities.
For more details, you can read the official announcement here: https://research.meta.com/blog/introducing-muse-spark-1-3/
This release from Meta underscores their commitment to advancing AI research and making powerful tools accessible. It will be interesting to see how the community leverages its capabilities once it is open-weighted.
What are your thoughts on Muse Spark 1.3 and its potential impact on agentic AI?
Please subscribe to t.me/iaosai for more updates and discussions.
This release is particularly noteworthy because Meta plans to open-weight the model very soon, which is exciting news for the open-source community. Muse Spark 1.3 features an impressive 1 million token context window and is priced competitively at $1.25 per million tokens for input and $4.25 for output.
Meta claims this model stands toe-to-toe with leading models like GPT-5.6 and Opus 5 on agentic and coding benchmarks. Tests have shown Muse Spark 1.3 performs strongly in professional tool use and agentic computer tasks, often outperforming competitors. It particularly shines in long context retrieval, maintaining high accuracy in the high 90s, while other models tend to decline significantly.
In practical demonstrations, the model successfully handled complex tasks. For example, when given a goal to build and deploy a self-contained animation website to AWS S3 and CloudFront, it autonomously planned and executed all necessary steps, including creating the S3 bucket, uploading the HTML file, and configuring the CloudFront distribution, resulting in a fully working website. It also showcased strong vision capabilities by accurately interpreting a WhatsApp conversation, understanding nuanced double meanings and situational awareness. Furthermore, it provided a flawless, step-by-step solution to a challenging chemistry and math problem, demonstrating robust scientific reasoning. Its multilingual capabilities are also impressive, generating culturally aware drink lists across 80 languages with correct native scripts.
This model was run using an agent like Hermes, where it plans and executes commands based on a single prompt, highlighting its autonomous capabilities.
For more details, you can read the official announcement here: https://research.meta.com/blog/introducing-muse-spark-1-3/
This release from Meta underscores their commitment to advancing AI research and making powerful tools accessible. It will be interesting to see how the community leverages its capabilities once it is open-weighted.
What are your thoughts on Muse Spark 1.3 and its potential impact on agentic AI?
Please subscribe to t.me/iaosai for more updates and discussions.
ElevenReader Ultra — 1 Year ($0)
ElevenLabs is offering 12 months of ElevenReader Ultra for free to students and educators. Turn PDFs, ePubs, docs, and web links into ultra-realistic AI voice audio .
How to Claim:
1. Head over to: elevenreader.io/students
2. Sign up using your school email.
3. Verify your email to unlock 1 year free.
NO CARD NEEDED
ElevenLabs is offering 12 months of ElevenReader Ultra for free to students and educators. Turn PDFs, ePubs, docs, and web links into ultra-realistic AI voice audio .
How to Claim:
1. Head over to: elevenreader.io/students
2. Sign up using your school email.
3. Verify your email to unlock 1 year free.
NO CARD NEEDED
ElevenReader
Student Discount | ElevenReader
Students get one year of ElevenReader for free ($99 value). Perfect for studying, learning, and reading aloud.
ok, this is wild. I thought that I might have to wait for this to happen, but its already here. I am talking about GPT6, a real breakthrough in the AI space.
OpenAI has reportedly unveiled GPT-6 Astra, which they are positioning as their most capable and aligned model to date. This new release appears to be a significant leap forward in AI capabilities, demonstrating impressive performance across several critical areas.
One of the key highlights is Astra's reported ability to excel in complex, learning-on-the-fly tasks, achieving near-perfect scores on benchmarks like ARC-AGI-3, where human performance is considerably lower. It is also said to feature enhanced safety, demonstrating an understanding of boundaries during safety tests, unlike some predecessors.
The creative potential of Astra is particularly noteworthy. Demos include generating a walkable 3D house model in Blender and Unreal Engine 5, and even creating a complete kart racing game from a simple prompt, including menus, characters, and tracks. This suggests a powerful capability for content generation and interactive experiences. Astra also reportedly exhibits improved judgment, asking clarifying questions when presented with ambiguous prompts, rather than simply guessing.
In terms of cost-efficiency, Astra consistently shows higher accuracy for lower API expenditure compared to other models on various benchmarks. While its coding performance is strong on some tasks like Terminal Bench 4.0, it is not an outright leader across all coding benchmarks. However, Astra truly shines in long-context understanding and abstract reasoning, adept at extracting facts from vast amounts of information and excelling in complex logical tasks.
API access for GPT-6 Astra is currently rolling out in stages, so wider hands-on testing by the community is still eagerly anticipated.
The advancements demonstrated by GPT-6 Astra are truly remarkable, suggesting a future where AI can handle increasingly complex, unsupervised tasks. It appears this model is designed to be a versatile and powerful tool for various applications beyond just coding.
The official page for OpenAI can be found at: https://openai.com/
What kind of creative or problem-solving applications do members of the community envision for a model with these advanced capabilities?
For more updates on AI breakthroughs and detailed analyses, consider subscribing to t.me/iaosai.
OpenAI has reportedly unveiled GPT-6 Astra, which they are positioning as their most capable and aligned model to date. This new release appears to be a significant leap forward in AI capabilities, demonstrating impressive performance across several critical areas.
One of the key highlights is Astra's reported ability to excel in complex, learning-on-the-fly tasks, achieving near-perfect scores on benchmarks like ARC-AGI-3, where human performance is considerably lower. It is also said to feature enhanced safety, demonstrating an understanding of boundaries during safety tests, unlike some predecessors.
The creative potential of Astra is particularly noteworthy. Demos include generating a walkable 3D house model in Blender and Unreal Engine 5, and even creating a complete kart racing game from a simple prompt, including menus, characters, and tracks. This suggests a powerful capability for content generation and interactive experiences. Astra also reportedly exhibits improved judgment, asking clarifying questions when presented with ambiguous prompts, rather than simply guessing.
In terms of cost-efficiency, Astra consistently shows higher accuracy for lower API expenditure compared to other models on various benchmarks. While its coding performance is strong on some tasks like Terminal Bench 4.0, it is not an outright leader across all coding benchmarks. However, Astra truly shines in long-context understanding and abstract reasoning, adept at extracting facts from vast amounts of information and excelling in complex logical tasks.
API access for GPT-6 Astra is currently rolling out in stages, so wider hands-on testing by the community is still eagerly anticipated.
The advancements demonstrated by GPT-6 Astra are truly remarkable, suggesting a future where AI can handle increasingly complex, unsupervised tasks. It appears this model is designed to be a versatile and powerful tool for various applications beyond just coding.
The official page for OpenAI can be found at: https://openai.com/
What kind of creative or problem-solving applications do members of the community envision for a model with these advanced capabilities?
For more updates on AI breakthroughs and detailed analyses, consider subscribing to t.me/iaosai.
OpenAI
OpenAI | Research & Deployment
We believe our research will eventually lead to artificial general intelligence, a system that can solve human-level problems.
Forwarded from Noname
Forwarded from Noname
Hello everyone!
Finally, we can enjoy Once in a Lifetime with a screen reader!
First of all, I'm sorry for the delay. It took longer than expected to patch this. The game was built on an older Python version (specifically Python 3.7.7 from 2021), and I had to install and tinker with that on top of the latest Python version to get it working.
However, the wait has paid off!
So, what is this game?
If you loved Eternum, you absolutely have to check out the creator's completed classic, Once in a Lifetime! You play as an ordinary guy living in the quiet town of Mistbury, but things get weird fast. Before you know it, you're uncovering wild town conspiracies, navigating crazy twists, and meeting incredible characters.
Once in a Lifetime is a phenomenal choice-based mystery visual novel. Dive into a world of hidden factions, supernatural symbols, and an overarching plot that keeps you guessing until the final credits roll. If you want a perfectly balanced mix of a gripping story, laugh-out-loud humor, and romance, this is it.
How to install the mod:
1. First, download the game files I shared above.
(Note: You need to download all 3 files. I couldn't share the whole file in one go due to Telegram's size limits, so I had to split it into 3 parts when compressing).
2. Extract the game files.
3. Download the patch files: zzz_accessibility.rpic and NVDA client32bit.dll.
4. Put both of those files into the game folder inside your Once in a Lifetime directory.
If you need more information, please read the instructions.txt file included. Enjoy the game!
Finally, we can enjoy Once in a Lifetime with a screen reader!
First of all, I'm sorry for the delay. It took longer than expected to patch this. The game was built on an older Python version (specifically Python 3.7.7 from 2021), and I had to install and tinker with that on top of the latest Python version to get it working.
However, the wait has paid off!
So, what is this game?
If you loved Eternum, you absolutely have to check out the creator's completed classic, Once in a Lifetime! You play as an ordinary guy living in the quiet town of Mistbury, but things get weird fast. Before you know it, you're uncovering wild town conspiracies, navigating crazy twists, and meeting incredible characters.
Once in a Lifetime is a phenomenal choice-based mystery visual novel. Dive into a world of hidden factions, supernatural symbols, and an overarching plot that keeps you guessing until the final credits roll. If you want a perfectly balanced mix of a gripping story, laugh-out-loud humor, and romance, this is it.
How to install the mod:
1. First, download the game files I shared above.
(Note: You need to download all 3 files. I couldn't share the whole file in one go due to Telegram's size limits, so I had to split it into 3 parts when compressing).
2. Extract the game files.
3. Download the patch files: zzz_accessibility.rpic and NVDA client32bit.dll.
4. Put both of those files into the game folder inside your Once in a Lifetime directory.
If you need more information, please read the instructions.txt file included. Enjoy the game!
Forwarded from Noname
hello guys, here you can find the guyds for the ones in a life time.
https://www.followchain.org/once-in-a-lifetime-walkthrough/
:
and this is the other none intrusive guyd without explanations
https://www.yekbot.com/once-in-a-lifetime-walkthrough-guide/
:
though the first one is quite clear, eassy to follow and contains point screen explanations if you familiar with the concept of points in eternum...
https://www.followchain.org/once-in-a-lifetime-walkthrough/
:
and this is the other none intrusive guyd without explanations
https://www.yekbot.com/once-in-a-lifetime-walkthrough-guide/
:
though the first one is quite clear, eassy to follow and contains point screen explanations if you familiar with the concept of points in eternum...
Followchain
Once in a Lifetime Walkthrough
This article contains the Once in a Lifetime game walkthrough guide from version 0.1 to 1.0 and wiki (by Caribdis).
Greetings everyone, and a huge shoutout and heartfelt thanks to @hasajaza for creating the original House Access mod!
Many of you know that the original mod was developed for older versions of House Party using MelonLoader. When House Party updated to its current single-assembly IL2CPP architecture, the old build stopped working.
I've worked on bringing this project back to life: updating the architecture, retargeting all the hooks, and porting it to BepInEx 6 (IL2CPP x64) so blind players can experience current versions of House Party smoothly. While I can't test every single branch or purchase every DLC combination myself, the foundation is completely rebuilt, and I would love for the community to test it out and share your thoughts!
Here is what is new and improved in version 1.1.3:
1. Compatible with Modern Game Builds:
- Built and tested against current 64-bit builds (including GOG v1.1.7 on Unity 2020.3.47f1).
- Replaced MelonLoader with BepInEx 6 IL2CPP.
2. Responsive Spoken Menus:
- Sliders, checkboxes, and dropdowns now announce their values in real time as you adjust them (not just when you first land on them).
- Menus speak your selected item immediately upon opening rather than dropping into silence.
- Clean names: In-game elements now read by their visible text rather than internal engine IDs (fewer raw names like "btnHolder").
3. Universal Number Key Navigation:
- Press 1–9 or 0 (and Ctrl + Number to pick) across all 11 in-game lists: dialogue options, inventory, action wheels, search results, radial menus, and settings.
- Works on both the top number row and numeric keypad.
4. 3D Spatial Awareness:
- Room Radar (Alt+R), Exit locator (Ctrl+D), and the 3D Audio Beacon (Ctrl+B) guide you naturally through rooms and party guests.
5. Painless 1-Click Startup Fix:
- BepInEx 6 has a known bug where "UnityLogListening = true" crashes the game at the engine level before any screen reader or mod can wake up.
- To save everyone from having to manually find and edit config files in Notepad, I’ve included a simple helper script:
Downloads & Full Documentation:
- GitHub Release v1.1.3 (Download the ready-to-use zip or standalone DLL):
https://github.com/swarup-developer/house-access/releases/tag/v1.1.3
- Full Repository & Comprehensive Keybind Guide:
https://github.com/swarup-developer/house-access
Special thanks once again to @hasajaza for pioneering this project and creating the original groundwork. Please give it a spin, let me know how it runs with your screen reader (NVDA, JAWS, SAPI), and report any bugs or suggestions!
Have fun at the party!
Many of you know that the original mod was developed for older versions of House Party using MelonLoader. When House Party updated to its current single-assembly IL2CPP architecture, the old build stopped working.
I've worked on bringing this project back to life: updating the architecture, retargeting all the hooks, and porting it to BepInEx 6 (IL2CPP x64) so blind players can experience current versions of House Party smoothly. While I can't test every single branch or purchase every DLC combination myself, the foundation is completely rebuilt, and I would love for the community to test it out and share your thoughts!
Here is what is new and improved in version 1.1.3:
1. Compatible with Modern Game Builds:
- Built and tested against current 64-bit builds (including GOG v1.1.7 on Unity 2020.3.47f1).
- Replaced MelonLoader with BepInEx 6 IL2CPP.
2. Responsive Spoken Menus:
- Sliders, checkboxes, and dropdowns now announce their values in real time as you adjust them (not just when you first land on them).
- Menus speak your selected item immediately upon opening rather than dropping into silence.
- Clean names: In-game elements now read by their visible text rather than internal engine IDs (fewer raw names like "btnHolder").
3. Universal Number Key Navigation:
- Press 1–9 or 0 (and Ctrl + Number to pick) across all 11 in-game lists: dialogue options, inventory, action wheels, search results, radial menus, and settings.
- Works on both the top number row and numeric keypad.
4. 3D Spatial Awareness:
- Room Radar (Alt+R), Exit locator (Ctrl+D), and the 3D Audio Beacon (Ctrl+B) guide you naturally through rooms and party guests.
5. Painless 1-Click Startup Fix:
- BepInEx 6 has a known bug where "UnityLogListening = true" crashes the game at the engine level before any screen reader or mod can wake up.
- To save everyone from having to manually find and edit config files in Notepad, I’ve included a simple helper script:
fix-bepinex-config.bat. Just double-click it once in your game folder, and it fixes the setting automatically!Downloads & Full Documentation:
- GitHub Release v1.1.3 (Download the ready-to-use zip or standalone DLL):
https://github.com/swarup-developer/house-access/releases/tag/v1.1.3
- Full Repository & Comprehensive Keybind Guide:
https://github.com/swarup-developer/house-access
Special thanks once again to @hasajaza for pioneering this project and creating the original groundwork. Please give it a spin, let me know how it runs with your screen reader (NVDA, JAWS, SAPI), and report any bugs or suggestions!
Have fun at the party!
GitHub
Release House Access v1.1.3 · swarup-developer/house-access
House Access 1.1.3 — Complete Screen Reader Mod for House Party
Welcome to version 1.1.3 of House Access! This update provides screen reader support for current builds of House Party (Unity IL2CPP ...
Welcome to version 1.1.3 of House Access! This update provides screen reader support for current builds of House Party (Unity IL2CPP ...
Source Code Hub
Greetings everyone, and a huge shoutout and heartfelt thanks to @hasajaza for creating the original House Access mod! Many of you know that the original mod was developed for older versions of House Party using MelonLoader. When House Party updated to its…
You can download game from here
https://files.ashuchoudhury.in/games/house.party.zip
https://files.ashuchoudhury.in/games/house.party.zip
Hello everyone,I hope you are all doing well!
IMPORTANT: STRICT 18+ MATURE CONTENT WARNING
Please read this carefully before downloading or checking out this project.Class of '09 is strictly an Adults-Only (18+) visual novel. It contains explicit profanity, harsh dark satire, references to drugs and prescription pills, alcohol abuse, self-harm, and very sensitive adult themes.I want to be completely honest and clear with our community: this game is not for everyone. If you are under 18, if you are sensitive to cynical or dark comedy, or if you prefer family-friendly games, please do not download or play this game. This mod is provided only for mature adult players who already enjoy this specific genre of adult comedy.
What is Class of '09?
For adults who enjoy satirical comedy, Class of '09 feels like an interactive audio drama. What makes it unique from an accessibility perspective is that every single character and dialogue line has 100% full professional voice acting.The story is packed with chaotic high school social choices that branch into over fifteen completely different endings. Because it runs on the lightweight Ren'Py engine, it performs smoothly at full speed on virtually any low-end PC, budget laptop, or integrated graphics chip without lagging.
What the Accessibility Mod Does
While the voice acting carries the story, the default game has serious visual roadblocks: the main menu buttons are silent transparent images, decision points give no spoken feedback, and settings and save slots cannot be read.Class of '09 Access connects the entire game directly to your screen reader:
• Direct, lag-free speech exclusively through NVDA, with automatic fallback to Tolk (for JAWS / SuperNova) and Windows SAPI.
• Spoken decision points that announce available choices as you browse them using the Up and Down arrow keys.
• Press C at any time to re-hear all current decision choices on screen.
• Spoken character names and dialogue lines in real-time as the story advances.
• Press H whenever you want to repeat the last spoken dialogue line.
• Press D if you want to mute the screen reader reading dialogue and listen solely to the game's voice cast.
• Accessible Main Menu with quick numeric shortcuts (keys 1 through 5).
• Fully accessible Settings and Preferences: NVDA announces active display mode (Window or Fullscreen, selected) and reads exact volume percentages (e.g. Scene Volume: 80%, UI Volume: 100%) with dedicated increase and decrease controls.
• Accessible Save and Load slots announcing exact dates, timestamps, and empty status.
• Accessible About and Credits menus with full spoken actor and artist lists.
How to Install the Mod
• Download Class09-Access-v1.0.0.zip from the mod release link below.
• Extract the files from the archive.
• Copy all the extracted files into your game's game folder (for example, Steam\steamapps\common\Class of '09\game$.
• Start the game executable, and NVDA will begin reading the menus and options right away.
This mod is fully compatible with both Class of '09 and Class of '09: The Re-Up.
Download Links
• Download Accessibility Mod: https://github.com/swarup-developer/class09-access/releases/tag/v1.0.0
Game Download Page: https://ankergames.net/game/class-of-09
Thank you, and feel free to share your thoughts, questions, or feedback on the GitHub project page!
IMPORTANT: STRICT 18+ MATURE CONTENT WARNING
Please read this carefully before downloading or checking out this project.Class of '09 is strictly an Adults-Only (18+) visual novel. It contains explicit profanity, harsh dark satire, references to drugs and prescription pills, alcohol abuse, self-harm, and very sensitive adult themes.I want to be completely honest and clear with our community: this game is not for everyone. If you are under 18, if you are sensitive to cynical or dark comedy, or if you prefer family-friendly games, please do not download or play this game. This mod is provided only for mature adult players who already enjoy this specific genre of adult comedy.
What is Class of '09?
For adults who enjoy satirical comedy, Class of '09 feels like an interactive audio drama. What makes it unique from an accessibility perspective is that every single character and dialogue line has 100% full professional voice acting.The story is packed with chaotic high school social choices that branch into over fifteen completely different endings. Because it runs on the lightweight Ren'Py engine, it performs smoothly at full speed on virtually any low-end PC, budget laptop, or integrated graphics chip without lagging.
What the Accessibility Mod Does
While the voice acting carries the story, the default game has serious visual roadblocks: the main menu buttons are silent transparent images, decision points give no spoken feedback, and settings and save slots cannot be read.Class of '09 Access connects the entire game directly to your screen reader:
• Direct, lag-free speech exclusively through NVDA, with automatic fallback to Tolk (for JAWS / SuperNova) and Windows SAPI.
• Spoken decision points that announce available choices as you browse them using the Up and Down arrow keys.
• Press C at any time to re-hear all current decision choices on screen.
• Spoken character names and dialogue lines in real-time as the story advances.
• Press H whenever you want to repeat the last spoken dialogue line.
• Press D if you want to mute the screen reader reading dialogue and listen solely to the game's voice cast.
• Accessible Main Menu with quick numeric shortcuts (keys 1 through 5).
• Fully accessible Settings and Preferences: NVDA announces active display mode (Window or Fullscreen, selected) and reads exact volume percentages (e.g. Scene Volume: 80%, UI Volume: 100%) with dedicated increase and decrease controls.
• Accessible Save and Load slots announcing exact dates, timestamps, and empty status.
• Accessible About and Credits menus with full spoken actor and artist lists.
How to Install the Mod
• Download Class09-Access-v1.0.0.zip from the mod release link below.
• Extract the files from the archive.
• Copy all the extracted files into your game's game folder (for example, Steam\steamapps\common\Class of '09\game$.
• Start the game executable, and NVDA will begin reading the menus and options right away.
This mod is fully compatible with both Class of '09 and Class of '09: The Re-Up.
Download Links
• Download Accessibility Mod: https://github.com/swarup-developer/class09-access/releases/tag/v1.0.0
Game Download Page: https://ankergames.net/game/class-of-09
Thank you, and feel free to share your thoughts, questions, or feedback on the GitHub project page!
GitHub
Release Class of '09 Access v1.0.0 - Initial Release · swarup-developer/class09-access
⚠️ STRICT CONTENT WARNING (18+ ADULT CONTENT)
🛑 MATURE AUDIENCES ONLY (18+)
Class of '09 is an explicit, unfiltered dark comedy visual novel intended strictly for adult audiences. It contains:...
🛑 MATURE AUDIENCES ONLY (18+)
Class of '09 is an explicit, unfiltered dark comedy visual novel intended strictly for adult audiences. It contains:...
Class of '09 Access — v1.0.1 is out
A quick follow-up patch for the Class of '09 Access
game mod. The biggest issue from the initial v1.0.0 release was that several menus opened in complete silence — this update fixes that and makes the confirm dialogs fully keyboard-answerable.
🔽 Grab v1.0.1 here: https://github.com/swarup-developer/class09-access/releases/tag/v1.0.1
A quick follow-up patch for the Class of '09 Access
game mod. The biggest issue from the initial v1.0.0 release was that several menus opened in complete silence — this update fixes that and makes the confirm dialogs fully keyboard-answerable.
🔽 Grab v1.0.1 here: https://github.com/swarup-developer/class09-access/releases/tag/v1.0.1
GitHub
Release Class of '09 Access v1.0.1 · swarup-developer/class09-access
📢 What's New in v1.0.1
This update fixes the menus that opened in complete silence and makes every dialog keyboard-answerable.
🆕 Menu announcements (were silent before)
Pause menu now speaks w...
This update fixes the menus that opened in complete silence and makes every dialog keyboard-answerable.
🆕 Menu announcements (were silent before)
Pause menu now speaks w...
House Access 1.1.13 — Released
The compatibility issue affecting the Steam version of House Party has been
fixed. The mod no longer loses all functionality when a game type is missing
from a build; each feature now loads independently, so the mod starts and
runs even if some hooks are unavailable on a particular version.
New: All-in-One Bundle
A complete package is now available in a single download. It includes
BepInEx 6, the .NET runtime, all speech libraries (UniversalSpeech,
NVDA Controller Client, and ZDSR), and the mod itself, fully configured
in advance. Extract the zip into your House Party installation folder —
the one containing HouseParty.exe — and the setup is ready. No separate
downloads are required.
New Keyboard Commands
Ctrl+F7 — Generates a hook report (hooks.txt) in the
UserData\HouseAccess folder. This file lists every hook the mod attempted,
with the exact type and method names it searched for.
Ctrl+F2 — Produces a full diagnostics dump, which now includes the hook
report.
Download Links
New installation (recommended for everyone):
HouseAccess-v1.1.13-Full-Bundle.zip
https://github.com/swarup-developer/house-access/releases/download/v1.1.13/HouseAccess-v1.1.13-Full-Bundle.zip
Already using an older version of House Access (BepInEx already working):
HouseAccess.dll — copy it into your BepInEx/plugins folder
https://github.com/swarup-developer/house-access/releases/download/v1.1.13/HouseAccess.dll
Full release page (notes and all files):
https://github.com/swarup-developer/house-access/releases/tag/v1.1.13
Request to Steam Users
Please test this release on the Steam version. If any feature remains
silent, press Ctrl+F7 and share the generated hooks.txt file. The report
shows precisely which game-side names need to be added, which makes fixes
fast and accurate.
Thank you for your continued testing and feedback. Enjoy the party.
The key change: the Download section now names each file with its direct download link and says exactly who each one is for — new users grab the bundle zip, existing users grab the DLL. The release page link stays at the bottom for anyone who wants the full notes.
The compatibility issue affecting the Steam version of House Party has been
fixed. The mod no longer loses all functionality when a game type is missing
from a build; each feature now loads independently, so the mod starts and
runs even if some hooks are unavailable on a particular version.
New: All-in-One Bundle
A complete package is now available in a single download. It includes
BepInEx 6, the .NET runtime, all speech libraries (UniversalSpeech,
NVDA Controller Client, and ZDSR), and the mod itself, fully configured
in advance. Extract the zip into your House Party installation folder —
the one containing HouseParty.exe — and the setup is ready. No separate
downloads are required.
New Keyboard Commands
Ctrl+F7 — Generates a hook report (hooks.txt) in the
UserData\HouseAccess folder. This file lists every hook the mod attempted,
with the exact type and method names it searched for.
Ctrl+F2 — Produces a full diagnostics dump, which now includes the hook
report.
Download Links
New installation (recommended for everyone):
HouseAccess-v1.1.13-Full-Bundle.zip
https://github.com/swarup-developer/house-access/releases/download/v1.1.13/HouseAccess-v1.1.13-Full-Bundle.zip
Already using an older version of House Access (BepInEx already working):
HouseAccess.dll — copy it into your BepInEx/plugins folder
https://github.com/swarup-developer/house-access/releases/download/v1.1.13/HouseAccess.dll
Full release page (notes and all files):
https://github.com/swarup-developer/house-access/releases/tag/v1.1.13
Request to Steam Users
Please test this release on the Steam version. If any feature remains
silent, press Ctrl+F7 and share the generated hooks.txt file. The report
shows precisely which game-side names need to be added, which makes fixes
fast and accurate.
Thank you for your continued testing and feedback. Enjoy the party.
The key change: the Download section now names each file with its direct download link and says exactly who each one is for — new users grab the bundle zip, existing users grab the DLL. The release page link stays at the bottom for anyone who wants the full notes.
Audio editing and speech generation just got a complete upgrade. Tencent has just released AuK, an open-source foundational model for speech generation and editing that truly stands out.
This model is an all-in-one audio powerhouse. It offers zero-shot voice cloning, allowing users to replicate a voice from a short audio sample and generate new speech in that voice. It also features instruct-based TTS, where speech can be generated from text with specific vocal design instructions.
What makes AuK particularly impressive is its comprehensive editing capabilities. It can perform speech content editing, letting users seamlessly add, delete, or replace words in existing spoken audio. It extends this to lyric content editing, maintaining the original melody while altering sung words, which is quite remarkable for music production.
Beyond content, AuK delves into paralinguistic editing, enabling changes in emotion, vocal timbre (e.g., male to female voice), and even stripping away heavy accents. Users can also inject non-verbal sounds like sneezes or laughs, or convert normal speech directly into a whisper.
For audio quality, AuK includes full speech enhancement, denoising, and multi-speaker separation, effectively cleaning up and clarifying audio. It also supports vocal extraction from music and general quality improvement.
Looking at the benchmarks, AuK is a strong performer, beating many state-of-the-art models in various speech generation and editing tasks. Its word error rate is impressively low, and its speaker similarity scores are high. However, it's worth noting that features like de-accenting, while a massive improvement, might not always achieve 100% perfection, and some non-verbal sound insertions are decent but not entirely flawless.
AuK is available in two versions: a 1.5 billion parameter base model for high-quality generation, and AuK-Flash, a distilled model for faster inference with near-teacher quality in just four steps. Both models should be easily runnable locally on systems with under 12GB of VRAM.
This model represents a significant leap forward in audio manipulation, offering a suite of tools that previously required multiple different applications, all integrated into one coherent system.
You can explore the AuK model and its capabilities on GitHub and Hugging Face:
https://github.com/TencentARC/AuK
What are your thoughts on this comprehensive audio editing and generation model? How do you see yourself using such a tool?
For more cutting-edge AI news and developments, make sure to subscribe to t.me/iaosai.
This model is an all-in-one audio powerhouse. It offers zero-shot voice cloning, allowing users to replicate a voice from a short audio sample and generate new speech in that voice. It also features instruct-based TTS, where speech can be generated from text with specific vocal design instructions.
What makes AuK particularly impressive is its comprehensive editing capabilities. It can perform speech content editing, letting users seamlessly add, delete, or replace words in existing spoken audio. It extends this to lyric content editing, maintaining the original melody while altering sung words, which is quite remarkable for music production.
Beyond content, AuK delves into paralinguistic editing, enabling changes in emotion, vocal timbre (e.g., male to female voice), and even stripping away heavy accents. Users can also inject non-verbal sounds like sneezes or laughs, or convert normal speech directly into a whisper.
For audio quality, AuK includes full speech enhancement, denoising, and multi-speaker separation, effectively cleaning up and clarifying audio. It also supports vocal extraction from music and general quality improvement.
Looking at the benchmarks, AuK is a strong performer, beating many state-of-the-art models in various speech generation and editing tasks. Its word error rate is impressively low, and its speaker similarity scores are high. However, it's worth noting that features like de-accenting, while a massive improvement, might not always achieve 100% perfection, and some non-verbal sound insertions are decent but not entirely flawless.
AuK is available in two versions: a 1.5 billion parameter base model for high-quality generation, and AuK-Flash, a distilled model for faster inference with near-teacher quality in just four steps. Both models should be easily runnable locally on systems with under 12GB of VRAM.
This model represents a significant leap forward in audio manipulation, offering a suite of tools that previously required multiple different applications, all integrated into one coherent system.
You can explore the AuK model and its capabilities on GitHub and Hugging Face:
https://github.com/TencentARC/AuK
What are your thoughts on this comprehensive audio editing and generation model? How do you see yourself using such a tool?
For more cutting-edge AI news and developments, make sure to subscribe to t.me/iaosai.
Please help me click this invite link for Freebuff
https://freebuff.com/get-started?ref=ref-55b32564-1521-4ad4-80e8-a75648129a1b&referrer=swarup+baral
https://freebuff.com/get-started?ref=ref-55b32564-1521-4ad4-80e8-a75648129a1b&referrer=swarup+baral
Freebuff
Get Started with Freebuff
Freebuff is the free coding agent: a free CLI coding agent and Freebuff Web, the free way to build full-stack apps. No subscription, no setup, no lock-in. The free alternative to Claude Code, Cursor, Codex, Lovable, Replit, Bolt, Windsurf, and Devin.
Here is a new tts model, extremely lightweight. and one of if not the smallest neural tts models yet.
This new model, called sanoTTS by ampixa, is truly something to talk about simply because of its size. It clocks in at a remarkable 1.4MB, which is incredibly tiny for a neural text-to-speech system. This makes it a potential game-changer for applications where every megabyte counts, or where processing power is very limited.
The model boasts fast inference and is multi-speaker, having been trained on the LibriTTS dataset. What's even more interesting is its ability to use speaker embeddings, meaning it can synthesize speech in the style of voices it hasn't directly encountered during training. That's quite a feat for such a compact model.
Now, it's important to be realistic about its performance. While the size is groundbreaking, the audio quality isn't going to blow anyone away. The creators themselves openly state that the sound is "not good," though acceptable for specific uses. Expect speech that might sound a bit artificial or less natural compared to the high-fidelity voices we hear from larger, more resource-intensive models. This is the trade-off for its extreme leanness.
So, where does sanoTTS shine? It's perfect for embedded systems, edge devices, or any low-resource environment where you need basic voice output and size or speed are priorities over pristine audio quality. Think of simple notifications, basic voice prompts on small devices, or quick prototyping where you just need to hear something spoken without much overhead.
If you want to try it out, here are some simple steps using Python:
pip install sanotts
sanotts say "Hello" --voice heart -o hello.wav
The main link to learn more and access the model is on Hugging Face:
https://huggingface.co/ampixa/sanoTTS
It is genuinely impressive to see how far researchers are pushing the boundaries of model compression. While sanoTTS won't replace your favorite high-quality voice assistant, it opens up new possibilities for AI on very constrained hardware.
What are your thoughts on models that prioritize extreme lightness over audio fidelity? Have you encountered any situations where such a tiny TTS model would be incredibly useful?
Remember to subscribe to t.me/iaosai for more updates on AI models and tools.
This new model, called sanoTTS by ampixa, is truly something to talk about simply because of its size. It clocks in at a remarkable 1.4MB, which is incredibly tiny for a neural text-to-speech system. This makes it a potential game-changer for applications where every megabyte counts, or where processing power is very limited.
The model boasts fast inference and is multi-speaker, having been trained on the LibriTTS dataset. What's even more interesting is its ability to use speaker embeddings, meaning it can synthesize speech in the style of voices it hasn't directly encountered during training. That's quite a feat for such a compact model.
Now, it's important to be realistic about its performance. While the size is groundbreaking, the audio quality isn't going to blow anyone away. The creators themselves openly state that the sound is "not good," though acceptable for specific uses. Expect speech that might sound a bit artificial or less natural compared to the high-fidelity voices we hear from larger, more resource-intensive models. This is the trade-off for its extreme leanness.
So, where does sanoTTS shine? It's perfect for embedded systems, edge devices, or any low-resource environment where you need basic voice output and size or speed are priorities over pristine audio quality. Think of simple notifications, basic voice prompts on small devices, or quick prototyping where you just need to hear something spoken without much overhead.
If you want to try it out, here are some simple steps using Python:
pip install sanotts
sanotts say "Hello" --voice heart -o hello.wav
The main link to learn more and access the model is on Hugging Face:
https://huggingface.co/ampixa/sanoTTS
It is genuinely impressive to see how far researchers are pushing the boundaries of model compression. While sanoTTS won't replace your favorite high-quality voice assistant, it opens up new possibilities for AI on very constrained hardware.
What are your thoughts on models that prioritize extreme lightness over audio fidelity? Have you encountered any situations where such a tiny TTS model would be incredibly useful?
Remember to subscribe to t.me/iaosai for more updates on AI models and tools.
huggingface.co
ampixa/sanoTTS · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
So, like I promised, I am here with another promotional offer. This time its a platform called CodeCraft API.
This platform is designed to make accessing a wide range of powerful AI models much simpler and more affordable. It brings together popular models like GPT-4, Gemini Pro, Claude 3 Opus, and even Stable Diffusion, all under one roof. The idea is to provide a unified API endpoint, which can be really convenient for developers, startups, and small businesses that might find direct access to these models either too complex or too expensive.
What stands out about CodeCraft API is its focus on competitive pricing and ease of integration. It aims to reduce the barriers to entry for using advanced AI in various projects. One can genuinely appreciate how it simplifies the process of switching between different models without needing to manage multiple API keys or accounts. This flexibility can be a significant time-saver.
Setting up with CodeCraft API is straightforward. After signing up, one generates an API key from their dashboard. Then, it's about integrating that key into one's application or project. They provide documentation to guide users through connecting to their chosen AI models, which helps make the process smooth.
For those interested in giving it a try, there is a special promotional offer: using the referral link provided, new users can get 20% extra credit on their first recharge. It is a nice way to explore the platform's capabilities without a huge initial investment.
It's honestly good to see platforms like this emerge, making sophisticated AI tools more accessible to a broader audience.
Here is the link to check it out:
https://codecraftapi.com/?ref=CCTLETG5
Has anyone here already used CodeCraft API or similar consolidated AI API platforms? What have your experiences been like?
Do consider subscribing to t.me/iaosai for more updates and offers.
This platform is designed to make accessing a wide range of powerful AI models much simpler and more affordable. It brings together popular models like GPT-4, Gemini Pro, Claude 3 Opus, and even Stable Diffusion, all under one roof. The idea is to provide a unified API endpoint, which can be really convenient for developers, startups, and small businesses that might find direct access to these models either too complex or too expensive.
What stands out about CodeCraft API is its focus on competitive pricing and ease of integration. It aims to reduce the barriers to entry for using advanced AI in various projects. One can genuinely appreciate how it simplifies the process of switching between different models without needing to manage multiple API keys or accounts. This flexibility can be a significant time-saver.
Setting up with CodeCraft API is straightforward. After signing up, one generates an API key from their dashboard. Then, it's about integrating that key into one's application or project. They provide documentation to guide users through connecting to their chosen AI models, which helps make the process smooth.
For those interested in giving it a try, there is a special promotional offer: using the referral link provided, new users can get 20% extra credit on their first recharge. It is a nice way to explore the platform's capabilities without a huge initial investment.
It's honestly good to see platforms like this emerge, making sophisticated AI tools more accessible to a broader audience.
Here is the link to check it out:
https://codecraftapi.com/?ref=CCTLETG5
Has anyone here already used CodeCraft API or similar consolidated AI API platforms? What have your experiences been like?
Do consider subscribing to t.me/iaosai for more updates and offers.
CodeCraft API
30M Tokens for $1.20 — 33 AI Models — CodeCraft API
Get 30M tokens for $1.20/month on any of 33 models — Claude Fable 5 included. Or go unlimited for $50/month. Free 1M tokens to start, OpenAI-compatible API, works with Kilo Code, Cursor, opencode, and Claude Code.