Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Say It — private, local text-to-speech for macOS Open models 100% on-device, speak text from any app with a hotkey, and even clone your own voice. Infinite voices. Free & open-source. Listen to the video 🔊

callebtc's profile picture

calle

63,393 subscribers

71,229 Aufrufe • vor 1 Monat •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

42 Kommentare

Profilbild von dr. calle 🟥
dr. calle 🟥vor 1 Monat

Download for macOS:

Profilbild von dr. calle 🟥
dr. calle 🟥vor 1 Monat

This is my contribution to the war against paid apps that should be free. I hope you enjoy it! Leave a star on GitHub ⭐️ PRs are welcome!

Profilbild von Alex 🧙‍♂️
Alex 🧙‍♂️vor 1 Monat

Kimi, improve this app so you can take a pdf and generate an audiobook for me 🚀

Profilbild von dr. calle 🟥
dr. calle 🟥vor 1 Monat

easy

Profilbild von Occo
Occovor 1 Monat

this slaps hard no cap

Profilbild von dr. calle 🟥
dr. calle 🟥vor 1 Monat

thank you, I use it to read articles online

Profilbild von Jim Hoffman
Jim Hoffmanvor 1 Monat

Very nice! May finally get through some of the long form posts here on X! Thank you.

Profilbild von dr. calle 🟥
dr. calle 🟥vor 1 Monat

That's how I do it!

Profilbild von Daniele
Danielevor 1 Monat

MACOS?? What should anyone do with something like that? 😭

Profilbild von Self Wealth 01123🎲
Self Wealth 01123🎲vor 1 Monat

Fakkkk I need this for Linux!

Profilbild von edi21
edi21vor 1 Monat

installed, amazed » thanks - finally I can hear all content on 2x while working.

Profilbild von dr. calle 🟥
dr. calle 🟥vor 1 Monat

beautiful!

Profilbild von Tristan
Tristanvor 1 Monat

thank your mr calle

Profilbild von GreenLeapForward.wtf
GreenLeapForward.wtfvor 1 Monat

Sweet!

Profilbild von 🟠 Goose
🟠 Goosevor 1 Monat

crushing it as always

Profilbild von Marius Off🔗Chain
Marius Off🔗Chainvor 1 Monat

I'd need it to be able to read in 2 or 3 different languages without having that unlistenable accent 😢

Profilbild von :EggTank.
:EggTank.vor 1 Monat

💪💪

Profilbild von Noza ₿
Noza ₿vor 1 Monat

No Linux?

Profilbild von dr. calle 🟥
dr. calle 🟥vor 1 Monat

someone port it!

Profilbild von Rodrigo Martínez
Rodrigo Martínezvor 1 Monat

Nice, thanks!

Profilbild von Breno Brito
Breno Britovor 1 Monat

What are you using? Kokoro? Is the best light one I found but still too heavy for what I wanted, so I'm using mostly Piper.

Profilbild von dr. calle 🟥
dr. calle 🟥vor 1 Monat

qwen

Profilbild von jiminica
jiminicavor 1 Monat

So any forbandroid or grapheneos? I dislike apple, even tho im forced to use it as a work phone.

Profilbild von Endo Rivers
Endo Riversvor 1 Monat

Any plans for the Intel version @callebtc ?

Profilbild von Bitcoin Meetup Ostschweiz 🇨🇭
Bitcoin Meetup Ostschweiz 🇨🇭vor 22 Tagen

Any plans for a Linux (preferred Debian based) version?

Profilbild von dr. calle 🟥
dr. calle 🟥vor 22 Tagen

say no more

Profilbild von Geronimo
Geronimovor 1 Monat

When will German be available?

Profilbild von jc
jcvor 1 Monat

and what you recommend for speech to text?

Profilbild von dr. calle 🟥
dr. calle 🟥vor 1 Monat

@belair6909

Profilbild von Rick Apollo
Rick Apollovor 1 Monat

I can’t figure out how to open a sayit window on mac to make changes to the settings. Clicking on the Dock icon doesn’t open a window.

Profilbild von Borchooga
Borchoogavor 1 Monat

Thanks! Def gonna try it out to see how it compares. I’ve been using Grok’s and have gotten used to how much better it is compared to baked-in MacOS/iOS.

Profilbild von lukeswissman
lukeswissmanvor 1 Monat

You are a Mac user?

Profilbild von Moultrie Ball
Moultrie Ballvor 1 Monat

Looks like

Profilbild von Yuri Yerofeyev
Yuri Yerofeyevvor 1 Monat

Wow, I just installed Handy for voice to text. Now it's time to go text to voice as well. Great job!

Profilbild von Matt Kulis ⚡️
Matt Kulis ⚡️vor 1 Monat

Any thoughts on making one for windows?

Profilbild von dr. calle 🟥
dr. calle 🟥vor 1 Monat

I don't use windows

Profilbild von ስብሐት ታደሰ ፨ Sebhat Tadesse
ስብሐት ታደሰ ፨ Sebhat Tadessevor 1 Monat

Thankyou @callebtc what us about Android users ?

Profilbild von dr. calle 🟥
dr. calle 🟥vor 1 Monat

check out T2S for android

Profilbild von Kate 🥰
Kate 🥰vor 1 Monat

This is a fantastic resource for visualizing entropy. Thanks for sharing!

Profilbild von Wayne
Waynevor 1 Monat

Time to put BT7274 voice to dictate data...

Profilbild von Adrián Treviño
Adrián Treviñovor 1 Monat

@gladstein Sick!

Profilbild von dr. calle 🟥
dr. calle 🟥vor 1 Monat

@gladstein and free!

Ähnliche Videos

So you can clone any voice 100% locally using this new open source model?! Alibaba has released Qwen3-TTS on Hugging Face. You can easily: - Create custom voices - Clone any voice from a VERY short audio - Generate speech with style instructions Only 0.6B & 1.8B! Sound on🔊
0:29

So you can clone any voice 100% locally using this new open source model?! Alibaba has released Qwen3-TTS on Hugging Face. You can easily: - Create custom voices - Clone any voice from a VERY short audio - Generate speech with style instructions Only 0.6B & 1.8B! Sound on🔊

Paul Couvert

149,398 Aufrufe • vor 8 Monaten

SPEECH-TO-TEXT STARTUPS ARE OFFICIALLY SWEATING RIGHT NOW. Google just dropped its own AI voice dictation app for macOS and iOS. You get all the premium feats of a paid speech-to-text app without any subscription. 100% FREE. Runs offline. Powered by Gemma 4. Download link in 🧵↓
0:26

SPEECH-TO-TEXT STARTUPS ARE OFFICIALLY SWEATING RIGHT NOW. Google just dropped its own AI voice dictation app for macOS and iOS. You get all the premium feats of a paid speech-to-text app without any subscription. 100% FREE. Runs offline. Powered by Gemma 4. Download link in 🧵↓

Chaz Wargnier ♨️

68,780 Aufrufe • vor 3 Monaten

Meet Moshiko and Moshika, the open source Moshi models 📖🟢. Moshi is a 7B text-audio model, capable of doing full-duplex conversations: it can listen and speak at any time. Plus, its inner text monologue improves the generation 💬 All on device🧑‍💻 🔎
0:30

Meet Moshiko and Moshika, the open source Moshi models 📖🟢. Moshi is a 7B text-audio model, capable of doing full-duplex conversations: it can listen and speak at any time. Plus, its inner text monologue improves the generation 💬 All on device🧑‍💻 🔎

Alexandre Défossez

131,467 Aufrufe • vor 2 Jahren

This is the best open source text-to-speech I’ve ever heard. It’s free and you can run it locally. It’s also unrestricted as you can give it any voice sample. In this video I have it speak as Peter Griffin, Trump, Jarvis, & Scarjo’s voice from HER. More in thread 👇
1:31

This is the best open source text-to-speech I’ve ever heard. It’s free and you can run it locally. It’s also unrestricted as you can give it any voice sample. In this video I have it speak as Peter Griffin, Trump, Jarvis, & Scarjo’s voice from HER. More in thread 👇

Blaine Brown

343,292 Aufrufe • vor 1 Jahr

Your app talks back. Lovable now supports text-to-speech and-speech-to-text, so you can seamlessly add AI voice features to your projects. Make a voice assistant, a hands-free tool, or an app you can literally speak to. Sound on:
0:31

Your app talks back. Lovable now supports text-to-speech and-speech-to-text, so you can seamlessly add AI voice features to your projects. Make a voice assistant, a hands-free tool, or an app you can literally speak to. Sound on:

Lovable

22,473 Aufrufe • vor 3 Monaten

Private AI browser with the OpenClaw agent on free local models Run your agent on Qwen, Gemma, or Nemotron directly in the browser Open source. Private. Runs on your local device
0:36

Private AI browser with the OpenClaw agent on free local models Run your agent on Qwen, Gemma, or Nemotron directly in the browser Open source. Private. Runs on your local device

Sigma Browser

115,689 Aufrufe • vor 5 Monaten

Clone any voice. Keep it local. Voice Clone Lab turns 5–15 minutes of audio into a voice model on your own GPU, cleanup, transcription, fine-tuning, and generation included. Open source: github/tetsuo-ai/voice_clone_lab
0:48

Clone any voice. Keep it local. Voice Clone Lab turns 5–15 minutes of audio into a voice model on your own GPU, cleanup, transcription, fine-tuning, and generation included. Open source: github/tetsuo-ai/voice_clone_lab

tetsuo

66,025 Aufrufe • vor 2 Monaten

Speak with ChatGPT: You can now use voice to engage in a back-and-forth conversation with your assistant. The hyper-realistic text-to-speech model allows you to choose from five different voices. On mobile, opt-in to voice in Settings → New Features on the mobile app.
1:41

Speak with ChatGPT: You can now use voice to engage in a back-and-forth conversation with your assistant. The hyper-realistic text-to-speech model allows you to choose from five different voices. On mobile, opt-in to voice in Settings → New Features on the mobile app.

Rowan Cheung

55,915 Aufrufe • vor 3 Jahren

Local speech-to-text with system wide dictation, file transcription, translations, subtitle export, and fully local no telemetry processing. And yes, it’s free and open-source 😉
0:37

Local speech-to-text with system wide dictation, file transcription, translations, subtitle export, and fully local no telemetry processing. And yes, it’s free and open-source 😉

AlternativeTo

11,694 Aufrufe • vor 5 Monaten

You can run local AI models up to 120B without a $10,000 Mac Studio This phone-sized device is your own server for open-source models. 100% local and private. And you can use it to: - Power an agent like OpenClaw 24/7 - Completely replace a chatbot - Literally anything that requires an API It’s called Tiiny, and, once again, you can run the latest open-source models on it. Link below
16:10

You can run local AI models up to 120B without a $10,000 Mac Studio This phone-sized device is your own server for open-source models. 100% local and private. And you can use it to: - Power an agent like OpenClaw 24/7 - Completely replace a chatbot - Literally anything that requires an API It’s called Tiiny, and, once again, you can run the latest open-source models on it. Link below

Paul Couvert

41,245 Aufrufe • vor 6 Monaten

Introduce OpenVoice V2 - a Text-to-Speech model that can clone any voice and speak in any language. Developed by MyShell and MIT CSAIL researchers. 🌐 Imagine your voice going global in multiple languages. 🔊 OpenVoice V2 breaks the language barrier and redefines voice interaction.
1:26

Introduce OpenVoice V2 - a Text-to-Speech model that can clone any voice and speak in any language. Developed by MyShell and MIT CSAIL researchers. 🌐 Imagine your voice going global in multiple languages. 🔊 OpenVoice V2 breaks the language barrier and redefines voice interaction.

MyShell.AI

292,600 Aufrufe • vor 2 Jahren

To generate 3D models in Codex with text-to-cad: Start a new project, write your prompt for a 3D model, and include a link to clone the text-to-cad repo. Codex handles the rest. The repo is open source and all scripts / ui run locally. Link below.
0:21

To generate 3D models in Codex with text-to-cad: Start a new project, write your prompt for a 3D model, and include a link to clone the text-to-cad repo. Codex handles the rest. The repo is open source and all scripts / ui run locally. Link below.

Jake Fitzgerald

22,113 Aufrufe • vor 5 Monaten

Meet June: your private AI agent now with local models on your Mac. Turn the wifi off: Agent, dictation, meeting notes, and your files all in one workspace. 100% free to use with local inference. Open Source. MIT. Local first. Try it:
0:49

Meet June: your private AI agent now with local models on your Mac. Turn the wifi off: Agent, dictation, meeting notes, and your files all in one workspace. 100% free to use with local inference. Open Source. MIT. Local first. Try it:

OpenSoftware

17,471 Aufrufe • vor 2 Monaten

We are excited to introduce the Text to Sound Effects API. To showcase it - we've built the first Video to Sounds Effects app. This app is available for free online and fully open-source.
0:57

We are excited to introduce the Text to Sound Effects API. To showcase it - we've built the first Video to Sounds Effects app. This app is available for free online and fully open-source.

ElevenLabs

120,703 Aufrufe • vor 2 Jahren

SwiftUI: You can chain free and open-source STT, TTS, and LLMs to build voice/vision apps with Core AI. Here is a demo I was experimenting with: - Whisper: Speech-to-text - Kokoro-82M: Text-to-speech - Qwen3-VL 2B: Vision I converted Pocket TTS and VibeVoice to Core AI models and tried with Gemma 4. All is working great.
0:36

SwiftUI: You can chain free and open-source STT, TTS, and LLMs to build voice/vision apps with Core AI. Here is a demo I was experimenting with: - Whisper: Speech-to-text - Kokoro-82M: Text-to-speech - Qwen3-VL 2B: Vision I converted Pocket TTS and VibeVoice to Core AI models and tried with Gemma 4. All is working great.

Amos Gyamfi

80,976 Aufrufe • vor 2 Monaten

Hermes Agent by Nous Research (100k+ ⭐) now inside Atomic Bot: – Free Local models: Qwen, Gemma or – Use your API keys for any provider – Dashboard, terminal, logs and files explorer – Private and Open Source Download MacOS app or run in Cloud👇
0:57

Hermes Agent by Nous Research (100k+ ⭐) now inside Atomic Bot: – Free Local models: Qwen, Gemma or – Use your API keys for any provider – Dashboard, terminal, logs and files explorer – Private and Open Source Download MacOS app or run in Cloud👇

atomicbot.ai

344,454 Aufrufe • vor 5 Monaten

Run KiloCode on open models powered by Atomic Chat Kilo is trusted by 3M+ developers. Code, debug, and build entirely on your device — no cloud, fully private, free and open-source with atomic.chat local AI provider
0:44

Run KiloCode on open models powered by Atomic Chat Kilo is trusted by 3M+ developers. Code, debug, and build entirely on your device — no cloud, fully private, free and open-source with atomic.chat local AI provider

atomic.chat

11,990 Aufrufe • vor 3 Monaten

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 Aufrufe • vor 8 Monaten

From 2D to 3D to video with speech using the tools I have developed. So 100% local and open-source. LTX.io #b3d
0:45

From 2D to 3D to video with speech using the tools I have developed. So 100% local and open-source. LTX.io #b3d

tintwotin

11,163 Aufrufe • vor 2 Monaten