<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>AI Picks &#8211; Firethering</title>
	<atom:link href="https://firethering.com/tech/tech-picks/ai-picks/feed/" rel="self" type="application/rss+xml" />
	<link>https://firethering.com</link>
	<description>Firethering is Your Hub for AI, Open Source and Tech That Actually Matters</description>
	<lastBuildDate>Sat, 11 Apr 2026 08:39:56 +0000</lastBuildDate>
	<language>en-US</language>
	<sy:updatePeriod>
	hourly	</sy:updatePeriod>
	<sy:updateFrequency>
	1	</sy:updateFrequency>
	<generator>https://wordpress.org/?v=6.6.5</generator>

<image>
	<url>https://firethering.com/wp-content/uploads/2024/10/cropped-firethering-FTR-favicon-32x32.png</url>
	<title>AI Picks &#8211; Firethering</title>
	<link>https://firethering.com</link>
	<width>32</width>
	<height>32</height>
</image> 
	<item>
		<title>4 Open-Source TTS Models That Can Clone Voices and Actually Sound Human</title>
		<link>https://firethering.com/open-source-tts-voice-cloning/</link>
					<comments>https://firethering.com/open-source-tts-voice-cloning/#respond</comments>
		
		<dc:creator><![CDATA[Mohit Geryani]]></dc:creator>
		<pubDate>Sun, 05 Apr 2026 14:30:17 +0000</pubDate>
				<category><![CDATA[AI Picks]]></category>
		<category><![CDATA[Tech]]></category>
		<category><![CDATA[AI]]></category>
		<category><![CDATA[AI Models]]></category>
		<category><![CDATA[TTS]]></category>
		<guid isPermaLink="false">https://firethering.com/?p=6057</guid>

					<description><![CDATA[Voice cloning used to mean expensive studio software, proprietary APIs with per-character pricing, or models so heavy they needed server infrastructure just to run. That changed quietly over the last few months.

Four open source models exist right now that do something the previous generation struggled with. They do not just generate speech. They clone a voice from a short audio sample and produce output that is genuinely difficult to compare from the original speaker. 

The gap between open source and commercial TTS has been closing for a while. These four models suggest it has effectively closed for voice cloning specifically. Here is what each one actually does and who it is for.]]></description>
		
					<wfw:commentRss>https://firethering.com/open-source-tts-voice-cloning/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		<enclosure url="https://zhu-han.github.io/omnivoice/audios/seedtts/generated/seedtts_ref_en_3_gen_en.wav" length="629838" type="audio/wav" />
<enclosure url="https://aria-k-alethia.github.io/LongCat-AudioDiT-demo/audio/main/audio/5.wav" length="335916" type="audio/wav" />
<enclosure url="https://fireredteam.github.io/demos/firered_tts_2/audios/zero-shot-podcast-generation_samples/en_1_fireredtts.wav" length="3156524" type="audio/wav" />
<enclosure url="https://raw.githubusercontent.com/NextGenToolbox/AIdemvids/refs/heads/main/fishaudios2demo.mp3" length="118646" type="audio/mpeg" />

			</item>
		<item>
		<title>5 open source AI agentic models built for real autonomous work</title>
		<link>https://firethering.com/best-open-source-ai-agent-models/</link>
					<comments>https://firethering.com/best-open-source-ai-agent-models/#respond</comments>
		
		<dc:creator><![CDATA[Mohit Geryani]]></dc:creator>
		<pubDate>Tue, 31 Mar 2026 09:03:06 +0000</pubDate>
				<category><![CDATA[AI Picks]]></category>
		<category><![CDATA[Tech]]></category>
		<category><![CDATA[AI]]></category>
		<category><![CDATA[AI Agents]]></category>
		<category><![CDATA[AI Models]]></category>
		<guid isPermaLink="false">https://firethering.com/?p=5929</guid>

					<description><![CDATA[Getting an AI agent to start a task is easy. Getting it to finish one properly is a different story. Most agents fall apart somewhere in the middle. A tool returns unexpected output, the model misreads it, and everything that follows builds on that mistake. By step thirty you are looking at something that has completely lost track of what it was supposed to do.

The five AI models here were built with that specific problem in mind. They handle complex multi-step tasks, real browser control, deep research and coding workflows. All open source &#038; self hostable.]]></description>
		
					<wfw:commentRss>https://firethering.com/best-open-source-ai-agent-models/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
			</item>
		<item>
		<title>4 Open Source AI Video Models for Editing and Generation</title>
		<link>https://firethering.com/open-source-ai-video-editing-models/</link>
					<comments>https://firethering.com/open-source-ai-video-editing-models/#respond</comments>
		
		<dc:creator><![CDATA[Mohit Geryani]]></dc:creator>
		<pubDate>Thu, 19 Mar 2026 17:01:13 +0000</pubDate>
				<category><![CDATA[AI Picks]]></category>
		<category><![CDATA[AI]]></category>
		<category><![CDATA[AI Models]]></category>
		<guid isPermaLink="false">https://firethering.com/?p=5739</guid>

					<description><![CDATA[If you have been looking for open source tools to work with video using AI you have probably noticed something. Most of what gets covered is generation like creating new videos from scratch. The editing side, actually modifying existing footage with AI, has been much quieter. That is starting to change.

There are now open source models that can swap outfits, replace backgrounds, remove objects, change characters and apply styles to existing video using plain text instructions. Some are built specifically for editing. Others are generation models that fit naturally into a creative video workflow.

This list covers both honestly. Three models built specifically for video editing and two generation models worth knowing about if you are working with video content. All open source, all available today.]]></description>
		
					<wfw:commentRss>https://firethering.com/open-source-ai-video-editing-models/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		<enclosure url="https://raw.githubusercontent.com/NextGenToolbox/AIdemvids/refs/heads/main/kiwiedit.mp4" length="6155021" type="video/mp4" />
<enclosure url="https://d2drjpuinn46lb.cloudfront.net/man_jacket_snow_edit.mp4" length="2342584" type="video/mp4" />

			</item>
		<item>
		<title>7 Open Source LLMs That Rival ChatGPT and Claude</title>
		<link>https://firethering.com/best-open-source-llms/</link>
					<comments>https://firethering.com/best-open-source-llms/#respond</comments>
		
		<dc:creator><![CDATA[Mohit Geryani]]></dc:creator>
		<pubDate>Sun, 15 Mar 2026 18:13:50 +0000</pubDate>
				<category><![CDATA[AI Picks]]></category>
		<category><![CDATA[Tech]]></category>
		<category><![CDATA[AI]]></category>
		<category><![CDATA[AI Models]]></category>
		<guid isPermaLink="false">https://firethering.com/?p=5655</guid>

					<description><![CDATA[Two years ago if you wanted a genuinely capable AI model your options were basically ChatGPT, Claude, Gemini or Grok. Open source existed but the gap was real and everyone knew it.

That gap is closing faster than most people expected. In some areas it is already gone.

Today open source models do not just compete with closed source. Some of them beat closed source on specific benchmarks that actually matter. And the list of categories where that is true keeps getting longer.

If you are curious about what open source AI actually looks like at full power or you are building something serious and evaluating your options this list is for you.

One thing worth saying upfront, these are not consumer GPU friendly models. You will need serious hardware to run them at full capacity. Quantized versions exist for most of them but expect performance and quality to reflect that. I went through a lot of options to put this list together. These seven are the ones that actually made me stop and pay attention.]]></description>
		
					<wfw:commentRss>https://firethering.com/best-open-source-llms/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
			</item>
		<item>
		<title>5 Open Source TTS Models So Small and Capable You Can Run Local Voice AI on Almost Anything</title>
		<link>https://firethering.com/best-lightweight-open-source-tts-models/</link>
					<comments>https://firethering.com/best-lightweight-open-source-tts-models/#respond</comments>
		
		<dc:creator><![CDATA[Mohit Geryani]]></dc:creator>
		<pubDate>Fri, 13 Mar 2026 14:44:36 +0000</pubDate>
				<category><![CDATA[AI Picks]]></category>
		<category><![CDATA[Tech]]></category>
		<category><![CDATA[AI]]></category>
		<category><![CDATA[AI Models]]></category>
		<guid isPermaLink="false">https://firethering.com/?p=5607</guid>

					<description><![CDATA[If you are looking for a lightweight AI voice model that actually sounds good, I found six that genuinely impressed me. Small, open source, and free to run locally. Some need almost no GPU at all. 

For their size they sound closer to paid platforms like ElevenLabs than anyone would expect.]]></description>
		
					<wfw:commentRss>https://firethering.com/best-lightweight-open-source-tts-models/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		<enclosure url="https://raw.githubusercontent.com/NextGenToolbox/AIdemvids/refs/heads/main/kittentts.mp4" length="1828630" type="video/mp4" />
<enclosure url="https://huggingface.co/hexgrad/Kokoro-82M/resolve/main/samples/HEARME.wav" length="258" type="audio/wav" />
<enclosure url="https://raw.githubusercontent.com/NextGenToolbox/AIdemvids/refs/heads/main/luxtts.mp4" length="1957341" type="video/mp4" />
<enclosure url="https://funaudiollm.github.io/cosyvoice2/audios/1.ZeroShot/EN_2_2.wav" length="586604" type="audio/wav" />
<enclosure url="https://myshell-public-repo-host.s3.amazonaws.com/myshellttsbase/examples/en/EN-Default/speed_1.0/sent_000.wav" length="247142" type="audio/wav" />

			</item>
		<item>
		<title>6 Open Source AI Image Editing Models That Challenge Google&#8217;s Nano Banana</title>
		<link>https://firethering.com/best-open-source-ai-image-editing-models/</link>
					<comments>https://firethering.com/best-open-source-ai-image-editing-models/#respond</comments>
		
		<dc:creator><![CDATA[Mohit Geryani]]></dc:creator>
		<pubDate>Sun, 08 Mar 2026 16:19:30 +0000</pubDate>
				<category><![CDATA[AI Models]]></category>
		<category><![CDATA[AI Picks]]></category>
		<category><![CDATA[Picks]]></category>
		<category><![CDATA[Tech]]></category>
		<category><![CDATA[AI]]></category>
		<guid isPermaLink="false">https://firethering.com/?p=5462</guid>

					<description><![CDATA[When people talk about AI image editing, the same names come up. Nano Banana, GPT Image or Maybe one or two others. And they're good, no argument there.

But they all have something in common. You're on their servers, their terms &#038; some generates watermark along with your image.

What if I told you the open source community has been building real alternatives? Models you can actually run on your own hardware with no watermarks &#038; no usage limits. Some of them are hitting benchmark scores that are really impressive. A few of them you can even build on top of, fine tune, or deploy in your own products.

I went through what's out there and narrowed it down to six that are genuinely worth your time]]></description>
		
					<wfw:commentRss>https://firethering.com/best-open-source-ai-image-editing-models/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
			</item>
		<item>
		<title>7 Small But Powerful AI Models You Can Run Locally on Your System — No Cloud Needed</title>
		<link>https://firethering.com/small-powerful-ai-models-run-locally/</link>
					<comments>https://firethering.com/small-powerful-ai-models-run-locally/#respond</comments>
		
		<dc:creator><![CDATA[Mohit Geryani]]></dc:creator>
		<pubDate>Thu, 05 Mar 2026 17:57:15 +0000</pubDate>
				<category><![CDATA[AI Models]]></category>
		<category><![CDATA[AI Picks]]></category>
		<category><![CDATA[Picks]]></category>
		<category><![CDATA[Tech]]></category>
		<category><![CDATA[AI]]></category>
		<guid isPermaLink="false">https://firethering.com/?p=5393</guid>

					<description><![CDATA[Most small AI models come with a catch. They're either too slow, too limited, or need hardware that feels impractical. But a handful of models have changed that conversation completely, they're small enough to run locally, capable enough to outperform models like GPT-4o on specific tasks.

I went through the benchmarks, the docs, and the community feedback on dozens of models to find the ones actually worth your time. These seven made the cut.]]></description>
		
					<wfw:commentRss>https://firethering.com/small-powerful-ai-models-run-locally/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
			</item>
		<item>
		<title>5 Open-Source AI 3D Generators Most People Don&#8217;t Know Exist</title>
		<link>https://firethering.com/open-source-ai-3d-generators/</link>
					<comments>https://firethering.com/open-source-ai-3d-generators/#respond</comments>
		
		<dc:creator><![CDATA[Mohit Geryani]]></dc:creator>
		<pubDate>Fri, 27 Feb 2026 15:53:31 +0000</pubDate>
				<category><![CDATA[AI Models]]></category>
		<category><![CDATA[AI Picks]]></category>
		<category><![CDATA[Picks]]></category>
		<category><![CDATA[Tech]]></category>
		<category><![CDATA[AI]]></category>
		<guid isPermaLink="false">https://firethering.com/?p=5255</guid>

					<description><![CDATA[A few months ago I ignored local 3D generation completely. The results weren't there yet.

That changed faster than I expected.

If you're a creator who works with 3D, a game developer, or just someone who wants to use AI for 3D model generation, these open source tools are worth your time. Most people have no idea they exist, let alone what they're actually capable of.

Here are 5 that genuinely surprised me.]]></description>
		
					<wfw:commentRss>https://firethering.com/open-source-ai-3d-generators/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		<enclosure url="https://microsoft.github.io/TRELLIS.2/assets/trellis2.mp4" length="31328439" type="video/mp4" />
<enclosure url="https://wukailu.github.io/Unique3D/static/videos/demo-safe.mp4" length="18781537" type="video/mp4" />
<enclosure url="https://raw.githubusercontent.com/TencentARC/InstantMesh/refs/heads/main/assets/teaser.mp4" length="7384098" type="video/mp4" />

			</item>
		<item>
		<title>5 Open-Source AI World Models You Can Use for Free</title>
		<link>https://firethering.com/ai-world-models/</link>
					<comments>https://firethering.com/ai-world-models/#respond</comments>
		
		<dc:creator><![CDATA[Mohit Geryani]]></dc:creator>
		<pubDate>Tue, 24 Feb 2026 12:19:07 +0000</pubDate>
				<category><![CDATA[AI Models]]></category>
		<category><![CDATA[AI Picks]]></category>
		<category><![CDATA[Picks]]></category>
		<category><![CDATA[Tech]]></category>
		<category><![CDATA[AI]]></category>
		<guid isPermaLink="false">https://firethering.com/?p=5090</guid>

					<description><![CDATA[We've watched open source absolutely run through video generation, image generation, audio. Every few months another closed model gets matched, then beaten, by something free on GitHub.

But world generation always felt different. Like that was the one thing that needed a Google-sized lab behind it.

I thought so too, until I actually went looking.

Turns out there are open source models right now that take a text prompt and build you an explorable, interactive world. Some go even further — hand them a single image and they'll construct an entire environment around it. The quality on a few of these genuinely caught me off guard.]]></description>
		
					<wfw:commentRss>https://firethering.com/ai-world-models/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		<enclosure url="https://matrix-game-v2.github.io/static/videos/unreals/wild4.mp4" length="2120415" type="video/mp4" />

			</item>
		<item>
		<title>5 Open-Source AI Text-to-Speech Generators You Can Run Locally for Natural, Human-Like Voice</title>
		<link>https://firethering.com/best-open-source-tts-models/</link>
					<comments>https://firethering.com/best-open-source-tts-models/#respond</comments>
		
		<dc:creator><![CDATA[Mohit Geryani]]></dc:creator>
		<pubDate>Sat, 21 Feb 2026 15:03:06 +0000</pubDate>
				<category><![CDATA[AI Models]]></category>
		<category><![CDATA[AI Picks]]></category>
		<category><![CDATA[Picks]]></category>
		<category><![CDATA[Tech]]></category>
		<category><![CDATA[AI]]></category>
		<guid isPermaLink="false">https://firethering.com/?p=4926</guid>

					<description><![CDATA[If you’re creating content or building products then relying entirely on cloud APIs isn’t your only option anymore.

Open-source text-to-speech models have improved dramatically. Some now produce voices that sound surprisingly natural with lower long-term cost, and full ownership over your deployment.

If you’re generating narration for YouTube, building an AI assistant, or integrating voice into your next app, running a powerful TTS model locally can give you flexibility the cloud simply can’t.

Here are five open-source AI voice models worth knowing.]]></description>
		
					<wfw:commentRss>https://firethering.com/best-open-source-tts-models/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		<enclosure url="https://raw.githubusercontent.com/NextGenToolbox/voiceai/refs/heads/main/qwen3tts.wav" length="1328698" type="audio/wav" />
<enclosure url="https://raw.githubusercontent.com/NextGenToolbox/voiceai/refs/heads/main/glmtts.wav" length="363918" type="audio/wav" />
<enclosure url="https://microsoft.github.io/VibeVoice/assets/audio/2p_see_u_again.mp3" length="1228365" type="audio/mpeg" />
<enclosure url="https://huggingface.co/hexgrad/Kokoro-82M/resolve/main/samples/HEARME.wav" length="258" type="audio/wav" />
<enclosure url="https://storage.googleapis.com/chatterbox-demo-samples/samples/duff_stewie.wav" length="745004" type="audio/wav" />
<enclosure url="https://raw.githubusercontent.com/NextGenToolbox/voiceai/refs/heads/main/tada%20audio.mp3" length="373224" type="audio/mpeg" />

			</item>
	</channel>
</rss>
