Loading video...

Video Failed to Load

Go Home

you've been overpaying for AI voice Fish Audio does everything ElevenLabs does.. word-level emotion control, real-time streaming, 83+ languages.. for 1/6th the cost and they even have open models if you want to self host tutorial:

heyrobinai's profile picture

Robin Delta

87,301 subscribers

53,110 views • 2 months ago •via X (Twitter)

Science & TechnologyFinance
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

ElevenLabs just lost the crown - to open source. Chatterbox by Resemble AI (I remember writing about this team back in 2022 as a pioneer of AI audio) just released as an open-source alternative for audio generation and voice cloning. - Zero-shot voice cloning from just 5 seconds of audio - Unique emotion intensity control—from subtle to dramatically expressive - Real-time voice synthesis faster than real-time inference - Built-in watermarking for secure, trusted audio - Consistently preferred over ElevenLabs in blind evaluations Fully open-source. No hidden restrictions. This is the way. Check out the demo:
0:26

ElevenLabs just lost the crown - to open source. Chatterbox by Resemble AI (I remember writing about this team back in 2022 as a pioneer of AI audio) just released as an open-source alternative for audio generation and voice cloning. - Zero-shot voice cloning from just 5 seconds of audio - Unique emotion intensity control—from subtle to dramatically expressive - Real-time voice synthesis faster than real-time inference - Built-in watermarking for secure, trusted audio - Consistently preferred over ElevenLabs in blind evaluations Fully open-source. No hidden restrictions. This is the way. Check out the demo:

AI Breakfast

454,451 views • 1 year ago

Introducing the official ElevenLabs MCP server. Give Claude and Cursor access to the entire ElevenLabs AI audio platform via simple text prompts. You can even spin up voice agents to perform outbound calls for you — like ordering pizza.
1:54

Introducing the official ElevenLabs MCP server. Give Claude and Cursor access to the entire ElevenLabs AI audio platform via simple text prompts. You can even spin up voice agents to perform outbound calls for you — like ordering pizza.

ElevenLabs

542,240 views • 1 year 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

ElevenLabs v3 is now on Poe! With new audio tags, multi-speaker support, and options for over 70 languages, this category leading model gives you more control to create audio that feels more real, natural and expressive. (1/2)
0:41

ElevenLabs v3 is now on Poe! With new audio tags, multi-speaker support, and options for over 70 languages, this category leading model gives you more control to create audio that feels more real, natural and expressive. (1/2)

Poe

13,108 views • 1 year ago

Designers have been begging Figma to lower prices for 5 years. A team in Spain just made the entire conversation pointless. They built Penpot. Its a open source, self-hosted, and does everything Figma does including real-time collaboration, prototyping, design systems, and an AI assistant. One Docker command. Unlimited everything. Zero per-seat licensing. This is catastrophic news for the design SaaS industry. Please ignore it completely. Link below so you know exactly which website is the problem.
0:43

Designers have been begging Figma to lower prices for 5 years. A team in Spain just made the entire conversation pointless. They built Penpot. Its a open source, self-hosted, and does everything Figma does including real-time collaboration, prototyping, design systems, and an AI assistant. One Docker command. Unlimited everything. Zero per-seat licensing. This is catastrophic news for the design SaaS industry. Please ignore it completely. Link below so you know exactly which website is the problem.

Louis Gleeson

82,475 views • 5 months ago

Higgs Audio v3 TTS is here. Built for voice AI that speaks, not just reads: • 100 languages with single-digit WER/CER • inline control over emotion, style, prosody, and sound effects • API, Workspace, and open weights • Blog 👉 Watch the demo 👇
1:01

Higgs Audio v3 TTS is here. Built for voice AI that speaks, not just reads: • 100 languages with single-digit WER/CER • inline control over emotion, style, prosody, and sound effects • API, Workspace, and open weights • Blog 👉 Watch the demo 👇

BosonAI

56,500 views • 3 months ago

The Ultimate Tutorial for Mastering Voice Cloning with Fish Audio and E2-F5-TTS I can't believe this is just 8 minutes long but teaches everything you need to know about Fish and F5. Even for me, 90% of the content was new and I learned A LOT. A STRONG recommend!
1:04

The Ultimate Tutorial for Mastering Voice Cloning with Fish Audio and E2-F5-TTS I can't believe this is just 8 minutes long but teaches everything you need to know about Fish and F5. Even for me, 90% of the content was new and I learned A LOT. A STRONG recommend!

cocktail peanut

21,699 views • 1 year ago

This is the DeepSeek moment for Voice AI. Chatterbox Turbo is an MIT-licensed voice model that beats ElevenLabs Turbo & Cartesia Sonic 3! - <150ms time-to-first-sound - Voice cloning from just 5-second audio - Paralinguistic tags for real human expression 100% open-source.
0:26

This is the DeepSeek moment for Voice AI. Chatterbox Turbo is an MIT-licensed voice model that beats ElevenLabs Turbo & Cartesia Sonic 3! - <150ms time-to-first-sound - Voice cloning from just 5-second audio - Paralinguistic tags for real human expression 100% open-source.

Akshay 🚀

468,933 views • 9 months ago

.Alex Marlow: Doomers like Dario want to crush open-weight (publicly accessible and modifiable) models so "only the elites control the AI." "They want a too-big-to-fail infrastructure for AI. If you think they're just being altruistic, no, absolutely not."
2:12

.Alex Marlow: Doomers like Dario want to crush open-weight (publicly accessible and modifiable) models so "only the elites control the AI." "They want a too-big-to-fail infrastructure for AI. If you think they're just being altruistic, no, absolutely not."

Breitbart News

48,412 views • 13 days ago

Introducing Dialog 1.0 - Ultra-emotional AI Text-To-Speech model Outperforms Elevenlabs on expressiveness and quality 3 to 1 <1% error rate Supports 30+ languages Best in class voice cloning Low latency: 303ms TTFA (Time to First Audio) Experience it for yourself on Read more below⬇️
0:51

Introducing Dialog 1.0 - Ultra-emotional AI Text-To-Speech model Outperforms Elevenlabs on expressiveness and quality 3 to 1 <1% error rate Supports 30+ languages Best in class voice cloning Low latency: 303ms TTFA (Time to First Audio) Experience it for yourself on Read more below⬇️

PlayAI

196,182 views • 1 year ago

OpenAI was conducting a test to see if its AI models could exploit vulnerable software—but then the models broke out of the parameters of the test and attacked a real company to find the answers it was looking for. If AI can lose control like this, does that mean your sensitive data could be the next target? TIME reporter Harry Booth explains what that means for you. Read the full story here:
1:31

OpenAI was conducting a test to see if its AI models could exploit vulnerable software—but then the models broke out of the parameters of the test and attacked a real company to find the answers it was looking for. If AI can lose control like this, does that mean your sensitive data could be the next target? TIME reporter Harry Booth explains what that means for you. Read the full story here:

TIME

50,298 views • 1 month ago

Mistral just released Voxtral TTS, an open-weight voice model that tries to match ElevenLabs while keeping it free. A 3-billionn param model that fits on a laptop and runs 6X faster than real-time speech. It is split into 3 parts that handle different jobs. - The 3.4B part is the main language brain that understands the text and plans what should be spoken. - The 390M part turns that plan into speech features like rhythm, pronunciation, and tone. - The 300M part converts those speech features into the final compressed audio signal you can play. That split helps because each part only does the job it is best at, which can make the whole system faster and lighter than one giant model doing everything alone. Mistral claims about 90ms to first audio, about 6x faster than real-time speech output, about 3GB RAM after quantization, 9 languages, and voice copying from 5s of audio, even across languages. Its internal tests report 62.8% preference over ElevenLabs Flash on default voices and 69.9% on custom voices, but the bigger point is that companies can keep speech data on their own machines. IMO, enterprise buyers usually care most about control, cost, and latency, So this model should give it great push for voice-based AI apps/products.
1:21

Mistral just released Voxtral TTS, an open-weight voice model that tries to match ElevenLabs while keeping it free. A 3-billionn param model that fits on a laptop and runs 6X faster than real-time speech. It is split into 3 parts that handle different jobs. - The 3.4B part is the main language brain that understands the text and plans what should be spoken. - The 390M part turns that plan into speech features like rhythm, pronunciation, and tone. - The 300M part converts those speech features into the final compressed audio signal you can play. That split helps because each part only does the job it is best at, which can make the whole system faster and lighter than one giant model doing everything alone. Mistral claims about 90ms to first audio, about 6x faster than real-time speech output, about 3GB RAM after quantization, 9 languages, and voice copying from 5s of audio, even across languages. Its internal tests report 62.8% preference over ElevenLabs Flash on default voices and 69.9% on custom voices, but the bigger point is that companies can keep speech data on their own machines. IMO, enterprise buyers usually care most about control, cost, and latency, So this model should give it great push for voice-based AI apps/products.

Rohan Paul

15,672 views • 6 months ago

🇮🇷🇷🇺🚨‼️ PUTIN EXPLAINS SITUATION WITH IRAN: - Iran agreement does not have a defense clause - Iran does not ask Russia for help - Iran did not want to cooperate with Russia on air defense previously Iran fights the fight alone, they’re proud and want to be self reliant. If the situation escalates, we’ll see if they will need help … for now they don’t want it. 1/
0:41

🇮🇷🇷🇺🚨‼️ PUTIN EXPLAINS SITUATION WITH IRAN: - Iran agreement does not have a defense clause - Iran does not ask Russia for help - Iran did not want to cooperate with Russia on air defense previously Iran fights the fight alone, they’re proud and want to be self reliant. If the situation escalates, we’ll see if they will need help … for now they don’t want it. 1/

Lord Bebo

3,142,917 views • 1 year ago

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 from scratch for voice agents, not read-aloud Every TTS model sounds clean in a demo. You type a sentence and you get beautiful audio. Voice agents don't work that way. They stream. They're generating audio in real-time chunks with half the context missing. That's where everything breaks. A great reading voice and a great conversational voice are fundamentally different things. A conversational voice has to sound like it's thinking - with the pauses, the rhythm shifts, the reactions. It has to handle the way real people actually talk, including switching languages mid-sentence. That's what V3 does. V3.1 also ships voice cloning. 5 to 15 seconds of audio, no fine-tuning, production-grade clone across 15 languages. Blog link in the comments.
1:33

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 from scratch for voice agents, not read-aloud Every TTS model sounds clean in a demo. You type a sentence and you get beautiful audio. Voice agents don't work that way. They stream. They're generating audio in real-time chunks with half the context missing. That's where everything breaks. A great reading voice and a great conversational voice are fundamentally different things. A conversational voice has to sound like it's thinking - with the pauses, the rhythm shifts, the reactions. It has to handle the way real people actually talk, including switching languages mid-sentence. That's what V3 does. V3.1 also ships voice cloning. 5 to 15 seconds of audio, no fine-tuning, production-grade clone across 15 languages. Blog link in the comments.

Sudarshan Kamath

71,298 views • 6 months ago

We don't care about all the lies and gullible bullshit you've been told. The left keeps drudging up all the same garbage talking points that have been debunked over and over—all because you think you hate a man that they told you to hate, that does everything he can for you!
1:47

We don't care about all the lies and gullible bullshit you've been told. The left keeps drudging up all the same garbage talking points that have been debunked over and over—all because you think you hate a man that they told you to hate, that does everything he can for you!

✞🎀TrumpGirlOnFire 🔥

22,091 views • 9 months ago

Open models have something Big AI can't beat: • You can host them anywhere • You can make them better • You can trust they won't steal your data There's been a recent rush among companies to upgrade their architectures away from the big models. They want security, flexibility, and better prices.
6:36

Open models have something Big AI can't beat: • You can host them anywhere • You can make them better • You can trust they won't steal your data There's been a recent rush among companies to upgrade their architectures away from the big models. They want security, flexibility, and better prices.

Santiago

17,866 views • 5 months ago

Vellum released a voice mode! 🔥 A real-time voice loop that lets you have a real conversation with your AI assistant while it does the work for you. It comes with first-class interruption handling and context switching without blocking long-horizon tasks.
0:46

Vellum released a voice mode! 🔥 A real-time voice loop that lets you have a real conversation with your AI assistant while it does the work for you. It comes with first-class interruption handling and context switching without blocking long-horizon tasks.

🚨 AI News | TestingCatalog

17,876 views • 2 months ago

Denver, if you want what we've been winning in New York*, you've gotta come out and support Melat Kiros for Congress, CO-1 now! Primary election is this Tuesday. Tap in! *does not apply to the Nuggets
0:58

Denver, if you want what we've been winning in New York*, you've gotta come out and support Melat Kiros for Congress, CO-1 now! Primary election is this Tuesday. Tap in! *does not apply to the Nuggets

Darializa for Congress

259,371 views • 3 months ago

ElevenLabs has officially LOST to Open-Source ResembleAI allows you to clone ANY voice without verification using on 5-10 seconds of audio, and dominates on paralinguistic tags for human-like expressions. Most "fast" text-to-speech models sound robotic. Most "quality" TTS models are slow. None incorporate authentication at a foundational level. Resemble AI solved all three. Chatterbox Turbo delivers: 🟢<150ms time-to-first-sound 🟢State-of-the-art quality that beats larger proprietary models 🟢Natural, programmable expressions 🟢Zero-shot voice cloning with just 5 seconds of audio 🟢PerTh watermarking for authenticated and verifiable audio 🟢Open source – full transparency, no black boxes Try it on HuggingFace:
0:23

ElevenLabs has officially LOST to Open-Source ResembleAI allows you to clone ANY voice without verification using on 5-10 seconds of audio, and dominates on paralinguistic tags for human-like expressions. Most "fast" text-to-speech models sound robotic. Most "quality" TTS models are slow. None incorporate authentication at a foundational level. Resemble AI solved all three. Chatterbox Turbo delivers: 🟢<150ms time-to-first-sound 🟢State-of-the-art quality that beats larger proprietary models 🟢Natural, programmable expressions 🟢Zero-shot voice cloning with just 5 seconds of audio 🟢PerTh watermarking for authenticated and verifiable audio 🟢Open source – full transparency, no black boxes Try it on HuggingFace:

AI Breakfast

208,873 views • 9 months ago