Loading video...

Video Failed to Load

Go Home

Introducing Lightning V3 - it beats every model we tested against. ElevenLabs, Cartesia, OpenAI. Lightning sets a new SOTA with V3 in conversational text-to-speech. → Highest MOS score for conversational TTS at 3.9 → ~76% win rate vs gpt-4o-mini-tts on naturalness → 15 languages with mid-sentence code-switching → Built...

kamath_sutra's profile picture

Sudarshan Kamath

21,655 subscribers

71,298 views • 6 months ago •via X (Twitter)

EducationNews & PoliticsScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

NEW: Higgs Audio V2 from BosonAI open, unified TTS model w/ voice cloning, beats GPT 4o mini tts and ElevenLabs v2 🔥 > Trained on 10M hours (speech, music, events) > Built on top of Llama 3.2 3B > Works real-time and on edge > Beats GPT-4o-mini-tts, ElevenLabs v2 in prosody & emotion Multi-speaker dialog > Zero-shot voice cloning 🤩 > Available on Hugging Face Kudos to folks at Boson AI for releasing such a brilliant work and all the details around the model! 🤗
2:10

NEW: Higgs Audio V2 from BosonAI open, unified TTS model w/ voice cloning, beats GPT 4o mini tts and ElevenLabs v2 🔥 > Trained on 10M hours (speech, music, events) > Built on top of Llama 3.2 3B > Works real-time and on edge > Beats GPT-4o-mini-tts, ElevenLabs v2 in prosody & emotion Multi-speaker dialog > Zero-shot voice cloning 🤩 > Available on Hugging Face Kudos to folks at Boson AI for releasing such a brilliant work and all the details around the model! 🤗

Vaibhav (VB) Srivastav

79,645 views • 1 year ago

I built a service desk agent using ElevenLabs’ new Conversational AI Agents feature. Watch the video to see how responsive it is! Previously, I used ElevenLabs for cloning my voice and used my generated voice for narrations in some of my youtube videos. This feature takes elevenlabs' voice AI to a whole new level! It simplifies systems that used to require separate TTS (text-to-speech) and STT (speech-to-text) processes for both sides of the conversation. Now, it’s much simpler! Create your own agent here What will you create with this?
3:29

I built a service desk agent using ElevenLabs’ new Conversational AI Agents feature. Watch the video to see how responsive it is! Previously, I used ElevenLabs for cloning my voice and used my generated voice for narrations in some of my youtube videos. This feature takes elevenlabs' voice AI to a whole new level! It simplifies systems that used to require separate TTS (text-to-speech) and STT (speech-to-text) processes for both sides of the conversation. Now, it’s much simpler! Create your own agent here What will you create with this?

Melvin Vivas

27,722 views • 1 year ago

Introducing Soniox TTS v2, our most powerful text-to-speech model yet. Soniox TTS v2 brings extraordinary voice quality, expressive control through audio tags, exceptional precision, high-fidelity voice cloning, more than 60 languages, natural language mixing, and low-latency streaming together in one model. Built from the ground up with a new model architecture, audio codec, and highly optimized inference engine, Soniox TTS v2 delivers frontier TTS at just $0.70 per generated hour. Available globally today as tts-rt-v2. Try it out: Turn the sound on and hear what’s possible. 🔊
2:13

Introducing Soniox TTS v2, our most powerful text-to-speech model yet. Soniox TTS v2 brings extraordinary voice quality, expressive control through audio tags, exceptional precision, high-fidelity voice cloning, more than 60 languages, natural language mixing, and low-latency streaming together in one model. Built from the ground up with a new model architecture, audio codec, and highly optimized inference engine, Soniox TTS v2 delivers frontier TTS at just $0.70 per generated hour. Available globally today as tts-rt-v2. Try it out: Turn the sound on and hear what’s possible. 🔊

Soniox

665,001 views • 1 month ago

Meet the new Soniox voice library. Soniox Text-to-Speech now includes more than 200 built-in voices, carefully curated for different applications, styles, accents, ages, and voice characteristics. Every voice works across 60+ languages, so you can choose the voice that fits your product and use that same voice globally while preserving its identity and character. You can now browse and filter voices by: • Gender • Age • Accent • Use case, such as conversational, narration, or social media • Style, such as warm, confident, friendly, calm, energetic, or deep This makes it much easier to find a voice for a specific application, for example: • Conversational + warm + middle-aged • Narration + deep + confident • Social media + young + energetic • Educational + calm + friendly We manually selected, reviewed, and tagged the voices so the metadata reflects how the voices actually sound and where they work well. We also redesigned the TTS Playground to make it easier to browse, filter, compare, and test voices with your own text and languages. Learn more:
0:42

Meet the new Soniox voice library. Soniox Text-to-Speech now includes more than 200 built-in voices, carefully curated for different applications, styles, accents, ages, and voice characteristics. Every voice works across 60+ languages, so you can choose the voice that fits your product and use that same voice globally while preserving its identity and character. You can now browse and filter voices by: • Gender • Age • Accent • Use case, such as conversational, narration, or social media • Style, such as warm, confident, friendly, calm, energetic, or deep This makes it much easier to find a voice for a specific application, for example: • Conversational + warm + middle-aged • Narration + deep + confident • Social media + young + energetic • Educational + calm + friendly We manually selected, reviewed, and tagged the voices so the metadata reflects how the voices actually sound and where they work well. We also redesigned the TTS Playground to make it easier to browse, filter, compare, and test voices with your own text and languages. Learn more:

Soniox

126,206 views • 15 days ago

meet silk mulberry 1.5, a voice model built to outperform expectations. - 162ms end-to-end latency - replies before you finish reading the message. - matches elevenlabs v3 on the MOS benchmark while being 95% cheaper. (₹0.40/min vs ₹9.40/min) ⁃ you don't pick a voice, you design one - describe the age, accent, pitch, emotion, whatever you want, only limit is your imagination. - mid-sentence language switching across 20+ languages with native accents, plus expressive range (whispers, singing and much more)
0:52

meet silk mulberry 1.5, a voice model built to outperform expectations. - 162ms end-to-end latency - replies before you finish reading the message. - matches elevenlabs v3 on the MOS benchmark while being 95% cheaper. (₹0.40/min vs ₹9.40/min) ⁃ you don't pick a voice, you design one - describe the age, accent, pitch, emotion, whatever you want, only limit is your imagination. - mid-sentence language switching across 20+ languages with native accents, plus expressive range (whispers, singing and much more)

rumik

32,464 views • 2 months ago

🚨 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 👇
0:22

🚨 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 views • 1 month ago

Text-to-speech is moving way too fast. Just a few days ago, I tweeted about PersonaPlex-7B, NVIDIA's new open source TTS ( And today, Qwen just open-sourced Qwen3-TTS 🤯 It’s a revolutionary text-to-speech model built for control. Not just about generating speech, but about shaping how it sounds directly from language. You can guide the pace, the tone, and the expressiveness straight from text, without touching audio graphs or hand-tuning parameters. That’s the real shift! What makes Qwen3-TTS stand out is how practical it already is: → voice cloning from just a few seconds of audio → voice creation without any reference sample → support for 10 languages out of the box → end-to-end latency down to ~97ms → works in both streaming and non-streaming setups The models come in two sizes (0.6B and 1.7B), so you can trade off quality and hardware cost depending on your setup. You can work with curated voices, designed voices, or cloned ones, and it integrates cleanly with vLLM for production use. It also ships as a simple Python package you can pip install. If you’re building real-time voice systems, this removes a lot of friction! 100% free and open source. I put the repo in the 🧵↓
0:41

Text-to-speech is moving way too fast. Just a few days ago, I tweeted about PersonaPlex-7B, NVIDIA's new open source TTS ( And today, Qwen just open-sourced Qwen3-TTS 🤯 It’s a revolutionary text-to-speech model built for control. Not just about generating speech, but about shaping how it sounds directly from language. You can guide the pace, the tone, and the expressiveness straight from text, without touching audio graphs or hand-tuning parameters. That’s the real shift! What makes Qwen3-TTS stand out is how practical it already is: → voice cloning from just a few seconds of audio → voice creation without any reference sample → support for 10 languages out of the box → end-to-end latency down to ~97ms → works in both streaming and non-streaming setups The models come in two sizes (0.6B and 1.7B), so you can trade off quality and hardware cost depending on your setup. You can work with curated voices, designed voices, or cloned ones, and it integrates cleanly with vLLM for production use. It also ships as a simple Python package you can pip install. If you’re building real-time voice systems, this removes a lot of friction! 100% free and open source. I put the repo in the 🧵↓

Charly Wargnier

59,144 views • 8 months ago

Did xAI just mass-murder the entire voice AI industry? 🤯 Grok just launched two voice APIs. Speech-to-Text and Text-to-Speech. Built on the same stack powering Tesla cars and Starlink support. And priced at 10x cheaper than ElevenLabs. Speech-to-Text: $0.10/hr batch. $0.20/hr streaming. Text-to-Speech: $4.20 per million characters. 25+ languages. Real-time streaming. Speaker diarization. Already outperforming ElevenLabs, Deepgram, and AssemblyAI on word error rate. TTS ships with expressive tags like [laugh], [sigh], , . Voices that don't sound like robots reading a script. ElevenLabs spent years building a voice AI company. xAI built voice AI for cars and satellites.
0:27

Did xAI just mass-murder the entire voice AI industry? 🤯 Grok just launched two voice APIs. Speech-to-Text and Text-to-Speech. Built on the same stack powering Tesla cars and Starlink support. And priced at 10x cheaper than ElevenLabs. Speech-to-Text: $0.10/hr batch. $0.20/hr streaming. Text-to-Speech: $4.20 per million characters. 25+ languages. Real-time streaming. Speaker diarization. Already outperforming ElevenLabs, Deepgram, and AssemblyAI on word error rate. TTS ships with expressive tags like [laugh], [sigh], , . Voices that don't sound like robots reading a script. ElevenLabs spent years building a voice AI company. xAI built voice AI for cars and satellites.

Vaibhav Sisinty

24,537,509 views • 5 months ago

Learn to build conversational AI voice agents in "Building AI Voice Agents for Production", created in collaboration with LiveKit and RealAvatar, and taught by dsa (Co-founder & CEO of LiveKit), Shayne (Developer Advocate, LiveKit), and Nedelina Teneva (Head of AI at RealAvatar, an AI Fund portfolio company). Voice agents combine speech and reasoning capabilities to enable real-time conversations. They're already being used to support customer service, to improve accessibility in healthcare, for entertainment applications, and for talk therapy. In this course, you’ll learn to build voice agents that listen, reason, and respond naturally. You’ll follow the architecture used to create the "AI Andrew" Avatar, a collaborative project between and RealAvatar that responds to users in what sounds like my voice. You’ll build a voice agent from scratch and deploy it to the cloud, enabling support for many simultaneous users. What you’ll learn: - Understand the fundamentals of voice agents, including key components like speech-to-text (STT), text-to-speech (TTS), and LLMs, and how latency is introduced at each layer. - Explore voice agent architectures and the trade-offs between modular pipelines and speech-to-speech APIs. - Explore how platforms like LiveKit mitigate latency issues with optimized networking infrastructure and low-latency communication protocols. - Learn how to connect client devices to voice agents using WebRTC—and why it outperforms HTTP and WebSocket for low-latency audio streaming. - Incorporate voice activity detection (VAD), end-of-turn detection, and context management to detect turns, handle interruptions, and manage conversational flow. - Understand the trade-offs between latency, quality, and cost in an example in which you build a voice agent and change its voice. - Equip your agent with metrics to measure latency at each stage of the voice pipeline and learn the key levers you can pull to make your agent faster and more responsive. The voice agents built in this course also incorporate voice technology from , a supporting contributor to the project. By the end of this course, you'll have learned the components of an AI voice agent pipeline, combined them into a system with low-latency communication, and deployed them on cloud infrastructure so it scales to many users. I’m looking forward to seeing what voice agents you build from this course! Please sign up here:
2:41

Learn to build conversational AI voice agents in "Building AI Voice Agents for Production", created in collaboration with LiveKit and RealAvatar, and taught by dsa (Co-founder & CEO of LiveKit), Shayne (Developer Advocate, LiveKit), and Nedelina Teneva (Head of AI at RealAvatar, an AI Fund portfolio company). Voice agents combine speech and reasoning capabilities to enable real-time conversations. They're already being used to support customer service, to improve accessibility in healthcare, for entertainment applications, and for talk therapy. In this course, you’ll learn to build voice agents that listen, reason, and respond naturally. You’ll follow the architecture used to create the "AI Andrew" Avatar, a collaborative project between and RealAvatar that responds to users in what sounds like my voice. You’ll build a voice agent from scratch and deploy it to the cloud, enabling support for many simultaneous users. What you’ll learn: - Understand the fundamentals of voice agents, including key components like speech-to-text (STT), text-to-speech (TTS), and LLMs, and how latency is introduced at each layer. - Explore voice agent architectures and the trade-offs between modular pipelines and speech-to-speech APIs. - Explore how platforms like LiveKit mitigate latency issues with optimized networking infrastructure and low-latency communication protocols. - Learn how to connect client devices to voice agents using WebRTC—and why it outperforms HTTP and WebSocket for low-latency audio streaming. - Incorporate voice activity detection (VAD), end-of-turn detection, and context management to detect turns, handle interruptions, and manage conversational flow. - Understand the trade-offs between latency, quality, and cost in an example in which you build a voice agent and change its voice. - Equip your agent with metrics to measure latency at each stage of the voice pipeline and learn the key levers you can pull to make your agent faster and more responsive. The voice agents built in this course also incorporate voice technology from , a supporting contributor to the project. By the end of this course, you'll have learned the components of an AI voice agent pipeline, combined them into a system with low-latency communication, and deployed them on cloud infrastructure so it scales to many users. I’m looking forward to seeing what voice agents you build from this course! Please sign up here:

Andrew Ng

87,868 views • 1 year ago

I joined OpenAI at the beginning of the year -- partly because I was excited about the possibility of better voice interaction with computers. So it was *especially* amazing to work with the team here on the gpt-4o model launch. It's hard to grok until you try it how big of a step forward this is for human/computer voice communication. It feels different -- it's obvious that the model understands you better than anything you've used before. This is my favorite demo of gpt-4o, it demonstrates not just good stt/tts, but actual conversational ability over full, realistic phone call. It's so obvious how useful this will be!
2:13

I joined OpenAI at the beginning of the year -- partly because I was excited about the possibility of better voice interaction with computers. So it was *especially* amazing to work with the team here on the gpt-4o model launch. It's hard to grok until you try it how big of a step forward this is for human/computer voice communication. It feels different -- it's obvious that the model understands you better than anything you've used before. This is my favorite demo of gpt-4o, it demonstrates not just good stt/tts, but actual conversational ability over full, realistic phone call. It's so obvious how useful this will be!

Peter Bakkum

144,441 views • 2 years ago

This is the fastest text-to-speech and speech-to-text API out there. It's under 250 ms to first-byte latency. That's what we need to deploy conversational AI applications everywhere! (I can't wait for the death of automated voice machines.) Look at the attached video. For the first time, I could have a conversation with an AI agent in real time without awkward pauses. This technology is Aura from Deepgram. It's the fastest text-to-speech option I've seen. Here is a GitHub repository with the demo in the video: You can use it to build a conversational AI application using natural voice. You'll need a Deepgram API Key and an OpenAI API Key. Thanks to Deepgram for giving me access to Aura and collaborating with me on this post. If you want to learn more about Aura, here is the announcement post:
3:38

This is the fastest text-to-speech and speech-to-text API out there. It's under 250 ms to first-byte latency. That's what we need to deploy conversational AI applications everywhere! (I can't wait for the death of automated voice machines.) Look at the attached video. For the first time, I could have a conversation with an AI agent in real time without awkward pauses. This technology is Aura from Deepgram. It's the fastest text-to-speech option I've seen. Here is a GitHub repository with the demo in the video: You can use it to build a conversational AI application using natural voice. You'll need a Deepgram API Key and an OpenAI API Key. Thanks to Deepgram for giving me access to Aura and collaborating with me on this post. If you want to learn more about Aura, here is the announcement post:

Santiago

185,640 views • 2 years ago

NVIDIA just removed one of the biggest friction points in Voice AI. PersonaPlex-7B is an open-source, full-duplex conversational model. Free, open source (MIT), with open model weights on Hugging Face 🤗 Links to repo and weights in 🧵↓ The traditional ASR → LLM → TTS pipeline forces rigid turn-taking. It’s efficient, but it never feels natural. PersonaPlex-7B changes that. This NVIDIA model can listen and speak at the same time. It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components. That unlocks: → instant back-channel responses → interruptions that feel human → real conversational rhythm Persona control is fully zero-shot! If you’re building low-latency assistants or support agents, this is a big step forward 🔥
0:42

NVIDIA just removed one of the biggest friction points in Voice AI. PersonaPlex-7B is an open-source, full-duplex conversational model. Free, open source (MIT), with open model weights on Hugging Face 🤗 Links to repo and weights in 🧵↓ The traditional ASR → LLM → TTS pipeline forces rigid turn-taking. It’s efficient, but it never feels natural. PersonaPlex-7B changes that. This NVIDIA model can listen and speak at the same time. It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components. That unlocks: → instant back-channel responses → interruptions that feel human → real conversational rhythm Persona control is fully zero-shot! If you’re building low-latency assistants or support agents, this is a big step forward 🔥

Charly Wargnier ♨️

566,171 views • 8 months ago

🚀 VoxCPM 2 is live! 🎉 Another open-source AI #TTS model from China — and one that stands shoulder to shoulder with Qwen3-TTS, while bringing everything into a single unified model. After rapid iterations from V1 (zero-shot cloning) to V1.5 (long-form + fine-tuning), #VoxCPM has consistently pushed quality and usability forward. Now, VoxCPM 2 takes it further: 🔹30+ languages — truly global, truly local. 🔹Infinite voice design — type it, hear it, control it. From a whisper to a booming cinematic voice. 🔹Studio-grade audio — 48kHz ultra-high fidelity with emotional depth 🔹Diffusion-Autoregressive cloning — preserves more acoustic and emotional detail than token-based models like Qwen3-TTS 💡 Big shoutout to Grok — used your multi-image video magic for our launch demo. It’s scarily good at keeping visuals consistent across shots. Elon Elon Musk, this one’s for you. 😉 Check the demo & start cloning your dream voice: 🌐 Hugging Face Space: 🤗 Hugging Face Model: 🤖 ModelScope Model: 💻 GitHub： #TTS #AI #VoiceCloning #GrokImagine #ElonMusk #OpenBMB #VoxCPM
1:26

🚀 VoxCPM 2 is live! 🎉 Another open-source AI #TTS model from China — and one that stands shoulder to shoulder with Qwen3-TTS, while bringing everything into a single unified model. After rapid iterations from V1 (zero-shot cloning) to V1.5 (long-form + fine-tuning), #VoxCPM has consistently pushed quality and usability forward. Now, VoxCPM 2 takes it further: 🔹30+ languages — truly global, truly local. 🔹Infinite voice design — type it, hear it, control it. From a whisper to a booming cinematic voice. 🔹Studio-grade audio — 48kHz ultra-high fidelity with emotional depth 🔹Diffusion-Autoregressive cloning — preserves more acoustic and emotional detail than token-based models like Qwen3-TTS 💡 Big shoutout to Grok — used your multi-image video magic for our launch demo. It’s scarily good at keeping visuals consistent across shots. Elon Elon Musk, this one’s for you. 😉 Check the demo & start cloning your dream voice: 🌐 Hugging Face Space: 🤗 Hugging Face Model: 🤖 ModelScope Model: 💻 GitHub： #TTS #AI #VoiceCloning #GrokImagine #ElonMusk #OpenBMB #VoxCPM

OpenBMB

560,058 views • 5 months ago

What if you could talk to your Telegram bot and it actually talked back? Learn how built a voice-enabled Telegram bot with the Gemini Interactions API in ~400 lines of Python. Send a voice note in any language, Gemini understands the audio and replies with text and a spoken voice message. Uses: - Gemini 3.1 Flash Lite for reasoning, 3.1 Flash TTS for speech - Interactions API handles multi-turn memory server-side - Native audio input, no transcription step needed - Deploys to Cloud Run with scale-to-zero Awesome work by Thor 雷神 ⚡️. 🤗
9:11

What if you could talk to your Telegram bot and it actually talked back? Learn how built a voice-enabled Telegram bot with the Gemini Interactions API in ~400 lines of Python. Send a voice note in any language, Gemini understands the audio and replies with text and a spoken voice message. Uses: - Gemini 3.1 Flash Lite for reasoning, 3.1 Flash TTS for speech - Interactions API handles multi-turn memory server-side - Native audio input, no transcription step needed - Deploys to Cloud Run with scale-to-zero Awesome work by Thor 雷神 ⚡️. 🤗

Philipp Schmid

11,204 views • 5 months ago

I've just tested the EVI 3 speech-to-speech model by Hume Hume AI, and this is the most realistic voice cloning I’ve heard. It doesn’t just clone the sound of your voice — it captures your tone, your speech patterns, your personality. Feels like your voice is thinking in real time. What’s wild is: — It’s not text-to-speech. It’s speech-to-speech. — You speak → it clones your voice + vibe — And it’s compatible with LLMs like Groq, Anthropic, Deepseek - Try talking to a voice clone: - Want more control? Customize it here: This changes how we’ll interact with AI voices. No more robotic replies — these sound human.
1:09

I've just tested the EVI 3 speech-to-speech model by Hume Hume AI, and this is the most realistic voice cloning I’ve heard. It doesn’t just clone the sound of your voice — it captures your tone, your speech patterns, your personality. Feels like your voice is thinking in real time. What’s wild is: — It’s not text-to-speech. It’s speech-to-speech. — You speak → it clones your voice + vibe — And it’s compatible with LLMs like Groq, Anthropic, Deepseek - Try talking to a voice clone: - Want more control? Customize it here: This changes how we’ll interact with AI voices. No more robotic replies — these sound human.

Aaliya

28,046 views • 1 year ago

Today, we’re launching Bland Speech v3 - The world's first Human Speech Engine. In Design Arena’s Audio Realism benchmark, Speech v3 is the top model, outranking Elevenlabs, Grok, Cartesia, and OpenAI. Trained on over 100 million real, human conversations: businesses, developers, and creators can now create any audio they can imagine. To showcase this, we used 5 seconds of old footage to help James, a 49 year old father who recently suffered a stroke, get his voice back. Try it for free at Full length documentary below🧵
2:03

Today, we’re launching Bland Speech v3 - The world's first Human Speech Engine. In Design Arena’s Audio Realism benchmark, Speech v3 is the top model, outranking Elevenlabs, Grok, Cartesia, and OpenAI. Trained on over 100 million real, human conversations: businesses, developers, and creators can now create any audio they can imagine. To showcase this, we used 5 seconds of old footage to help James, a 49 year old father who recently suffered a stroke, get his voice back. Try it for free at Full length documentary below🧵

Bland

2,130,589 views • 1 month ago

Remember when AI couldn't draw a hand? Seven fingers, knuckles pointing backwards. And the AI spaghetti videos. That was three years ago. Images are done now. Video is close enough that you scrolled past AI ads this week and clocked exactly zero of them. Code writes itself and there are like 40 coding agents. AI voice spent that entire stretch sounding like the lady voice in a 2014 GPS. Flat, evenly spaced and every sentence landing with the same weight, like it's reading from a phone book. Here's why it stayed broken. Bad images are funny. You screenshot the seven fingers, it goes viral for being bad, someone fixes it. Bad audio is just boring. It doesn't fail spectacularly, so it never got that pressure. The bigger problem was the scoring. The whole industry graded AI voices on whether you could make out the words. So the models learned to over pronounce everything, hitting every syllable like a newsreader. Perfectly clear but robotic. Everyone was chasing a score that had nothing to do with sounding human. Meanwhile a small open-source team was doing something harder. Their lead researcher, an ex-NVIDIA engineer, went all in on an approach the rest of the field had written off. Two years early. No funding announcements or launch tour. He just put the whole thing on GitHub for free. It's sitting at 50,000+ stars now. Then they ran the test everyone else avoided. For 10 days they piped real users through their model and every big competitor with the listener never told which was which. Thousands of real people, real scripts. Whichever voice you actually preferred, they logged it. Theirs came out on top. It beat ElevenLabs about 6 times out of 10, head to head. It beat OpenAI's voice model 8 times out of 10. The gap was widest on the breathing, the pauses, the little hesitations, which is exactly the stuff that makes a voice sound like a person instead of a machine reading. They ran on real users rather than a lab, which is more than most of these claims can say. That's Fish Audio. This week they shipped S2.1 Pro: - Clone anyone's voice from 15 seconds of audio - Fast enough to hold a live conversation - 83 languages, one model - Type [whisper] or [sigh] mid-sentence and it does it - Around 70% cheaper than ElevenLabs - Free to download and run yourself Voice was the last thing on the list. Around 20 people with a free repo got there before other billion dollar companies did.
0:34

Remember when AI couldn't draw a hand? Seven fingers, knuckles pointing backwards. And the AI spaghetti videos. That was three years ago. Images are done now. Video is close enough that you scrolled past AI ads this week and clocked exactly zero of them. Code writes itself and there are like 40 coding agents. AI voice spent that entire stretch sounding like the lady voice in a 2014 GPS. Flat, evenly spaced and every sentence landing with the same weight, like it's reading from a phone book. Here's why it stayed broken. Bad images are funny. You screenshot the seven fingers, it goes viral for being bad, someone fixes it. Bad audio is just boring. It doesn't fail spectacularly, so it never got that pressure. The bigger problem was the scoring. The whole industry graded AI voices on whether you could make out the words. So the models learned to over pronounce everything, hitting every syllable like a newsreader. Perfectly clear but robotic. Everyone was chasing a score that had nothing to do with sounding human. Meanwhile a small open-source team was doing something harder. Their lead researcher, an ex-NVIDIA engineer, went all in on an approach the rest of the field had written off. Two years early. No funding announcements or launch tour. He just put the whole thing on GitHub for free. It's sitting at 50,000+ stars now. Then they ran the test everyone else avoided. For 10 days they piped real users through their model and every big competitor with the listener never told which was which. Thousands of real people, real scripts. Whichever voice you actually preferred, they logged it. Theirs came out on top. It beat ElevenLabs about 6 times out of 10, head to head. It beat OpenAI's voice model 8 times out of 10. The gap was widest on the breathing, the pauses, the little hesitations, which is exactly the stuff that makes a voice sound like a person instead of a machine reading. They ran on real users rather than a lab, which is more than most of these claims can say. That's Fish Audio. This week they shipped S2.1 Pro: - Clone anyone's voice from 15 seconds of audio - Fast enough to hold a live conversation - 83 languages, one model - Type [whisper] or [sigh] mid-sentence and it does it - Around 70% cheaper than ElevenLabs - Free to download and run yourself Voice was the last thing on the list. Around 20 people with a free repo got there before other billion dollar companies did.

Rez Karim

18,446 views • 1 month ago

VoiceBox just did what everyone thought was impossible. It might have killed ElevenLabs overnight. No subscription. No cloud. No credits. Runs locally on your machine. Clones a voice from 3 seconds of audio. Powered by Qwen 3 TTS. Apache 2.0 license. Commercial use allowed. And your voice data never leaves your computer. For years, if you wanted high quality voice cloning, ElevenLabs was the default. Now there’s a free open-source alternative that sounds shockingly close. Plus it has a built-in multi-track editor, recording, transcription with Whisper, and a local API. This isn’t just another TTS tool. It’s a full voice production studio on your desktop. Open source AI is catching up fast. And this changes the game for creators and businesses. Would you trust the cloud with your voice… or keep it local? 👇
8:20

VoiceBox just did what everyone thought was impossible. It might have killed ElevenLabs overnight. No subscription. No cloud. No credits. Runs locally on your machine. Clones a voice from 3 seconds of audio. Powered by Qwen 3 TTS. Apache 2.0 license. Commercial use allowed. And your voice data never leaves your computer. For years, if you wanted high quality voice cloning, ElevenLabs was the default. Now there’s a free open-source alternative that sounds shockingly close. Plus it has a built-in multi-track editor, recording, transcription with Whisper, and a local API. This isn’t just another TTS tool. It’s a full voice production studio on your desktop. Open source AI is catching up fast. And this changes the game for creators and businesses. Would you trust the cloud with your voice… or keep it local? 👇

Julian Goldie SEO

59,167 views • 7 months ago

A voice agent powered by gpt-oss. Running locally on my macBook. Demo recorded in a Waymo with WiFi turned off. I'm still on my space game voice AI kick, obviously. Code link below. For conversational voice AI, you want to set the gpt-oss reasoning behavior to "low". (The default is "medium".) Notes on how to do that and a jinja template you can use are in the repo. The LLM in the demo video is the big, 120B version of gpt-oss. You can use the smaller, 20B model for this, of course. But OpenAI really did a cool thing here designing the 120B model to run in "just" 80GB of VRAM. And the llama.cpp mlx inference is fast: ~250ms TTFT. Running a big model on-device feels like a time warp into the future of AI.
4:35

A voice agent powered by gpt-oss. Running locally on my macBook. Demo recorded in a Waymo with WiFi turned off. I'm still on my space game voice AI kick, obviously. Code link below. For conversational voice AI, you want to set the gpt-oss reasoning behavior to "low". (The default is "medium".) Notes on how to do that and a jinja template you can use are in the repo. The LLM in the demo video is the big, 120B version of gpt-oss. You can use the smaller, 20B model for this, of course. But OpenAI really did a cool thing here designing the 120B model to run in "just" 80GB of VRAM. And the llama.cpp mlx inference is fast: ~250ms TTFT. Running a big model on-device feels like a time warp into the future of AI.

kwindla

202,211 views • 1 year ago