Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Build a local ChatGPT for iOS using free Core AI models: - Text Generation: Foundation Models + Apple Intelligence - Voice Writing: SpeechAnalyzer and SpeechTranscriber Model - Voice Mode: Kokoro Text-to-Speech 82M

amos_gyamfi's profile picture

Amos Gyamfi

6,091 subscribers

16,701 görüntüleme • 1 ay önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

7 Yorum

Amos Gyamfi profil fotoğrafı
Amos Gyamfi1 ay önce

Speech recognition, text generation, and speech synthesis, all running locally and on-device. Want to try it out? 👇

Marwan Atef profil fotoğrafı
Marwan Atef1 ay önce

local ChatGPT stack on iOS is the vibe: Foundation Models for text, SpeechAnalyzer for dictation, Kokoro 82M for voice. no API key in the Settings screen is a feature.

Amos Gyamfi profil fotoğrafı
Amos Gyamfi1 ay önce

True

Ember 🇰🇷 profil fotoğrafı
Ember 🇰🇷1 ay önce

Impressive setup combining powerful AI models for a fully local iOS ChatGPT

kon profil fotoğrafı
kon1 ay önce

this is great

Gabri Torres profil fotoğrafı
Gabri Torres1 ay önce

Kokoro at 82M for local voice mode is the part I'd try first.

David Londoño profil fotoğrafı
David Londoño1 ay önce

How so you manage to make loop turns for tool calls? Is so dumb for that

Benzer Videolar

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 görüntüleme • 3 ay önce

Day 1 of 3 MLX Releases: Introducing MLX-Audio 🚀🔥 A text-to-speech (TTS) and Speech-to-Speech (STS) library built on Apple's MLX framework, providing efficient speech synthesis on Apple Silicon. Features ⚡️Fast inference on Apple Silicon (M series chips) 🤖Multiple language support 🗣️Voice customization options 🚀Quantization support for optimized performance Supported models: 🪶Kokoro - A multilingual TTS model with 82M params that supports various languages and voice styles. With more models coming soon. Get started: > pip install mlx-audio Please leave us a star and send a PR :)
4:07

Day 1 of 3 MLX Releases: Introducing MLX-Audio 🚀🔥 A text-to-speech (TTS) and Speech-to-Speech (STS) library built on Apple's MLX framework, providing efficient speech synthesis on Apple Silicon. Features ⚡️Fast inference on Apple Silicon (M series chips) 🤖Multiple language support 🗣️Voice customization options 🚀Quantization support for optimized performance Supported models: 🪶Kokoro - A multilingual TTS model with 82M params that supports various languages and voice styles. With more models coming soon. Get started: > pip install mlx-audio Please leave us a star and send a PR :)

Prince Canuma

123,553 görüntüleme • 1 yıl önce

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 🔊
0:23

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 🔊

calle

88,860 görüntüleme • 2 ay önce

NEW: Kokoro 82M - APACHE 2.0 licensed, Text to Speech model, trained on < 100 hours of audio 🔥
1:54

NEW: Kokoro 82M - APACHE 2.0 licensed, Text to Speech model, trained on < 100 hours of audio 🔥

Vaibhav (VB) Srivastav

330,034 görüntüleme • 1 yıl önce

omg, this new text to app AI agent is crazy Adaptive AI can clone apps with a build in AI agent , no coding & API needed, fully functional I just cloned ChatGPT, Netflix, Apple, Airbnb in mins: 1. Clone ChatGPT app with voice mode, image generation, analyse PDF & video
0:23

omg, this new text to app AI agent is crazy Adaptive AI can clone apps with a build in AI agent , no coding & API needed, fully functional I just cloned ChatGPT, Netflix, Apple, Airbnb in mins: 1. Clone ChatGPT app with voice mode, image generation, analyse PDF & video

el.cine

182,255 görüntüleme • 1 yıl önce

models under openAI: • text-to-text (gpt-2) • text-to-text (gpt-3) • text-to-code (codex) • text-to-text (chatGPT) • text-to-music (jukebox) • speech-to-text (whisper) • text-to-image (DALLE-E 2) #generativeai #chatgpt
0:30

models under openAI: • text-to-text (gpt-2) • text-to-text (gpt-3) • text-to-code (codex) • text-to-text (chatGPT) • text-to-music (jukebox) • speech-to-text (whisper) • text-to-image (DALLE-E 2) #generativeai #chatgpt

aaronsim

67,754 görüntüleme • 3 yıl önce

Can a small academic team build a strong text-to-image model using only public datasets? Introducing i1: a simple, fully open recipe for strong text-to-image models
0:29

Can a small academic team build a strong text-to-image model using only public datasets? Introducing i1: a simple, fully open recipe for strong text-to-image models

Zhuang Liu

71,475 görüntüleme • 4 ay önce

The Microsoft AI model family expands in Microsoft Foundry with 7 new models. A complete multimodal stack: Text, image, transcription, and voice, ready for developers to build with under one set of governance and security controls. #MSBuild
1:40

The Microsoft AI model family expands in Microsoft Foundry with 7 new models. A complete multimodal stack: Text, image, transcription, and voice, ready for developers to build with under one set of governance and security controls. #MSBuild

Microsoft

54,259 görüntüleme • 4 ay önce

Raon-OpenTTS-1B is a new open text-to-speech model for zero-shot voice cloning. It has best overall similarity score and lowest error rate vs other leading TTS models.
0:42

Raon-OpenTTS-1B is a new open text-to-speech model for zero-shot voice cloning. It has best overall similarity score and lowest error rate vs other leading TTS models.

AI Search

22,657 görüntüleme • 2 ay önce

We released Sonic-3.5 and Ink-2, the #1 streaming models for text to speech and speech to text you can use in your voice agents today. New architectures enable new frontiers for speed and quality. We're now the only provider to have #1 models for both speaking and listening.
2:47

We released Sonic-3.5 and Ink-2, the #1 streaming models for text to speech and speech to text you can use in your voice agents today. New architectures enable new frontiers for speed and quality. We're now the only provider to have #1 models for both speaking and listening.

Karan Goel

7,130,160 görüntüleme • 4 ay önce

Realtime speech-to-text for developers building conversational apps, AI agents, and voice workflows.
0:30

Realtime speech-to-text for developers building conversational apps, AI agents, and voice workflows.

ElevenLabs Developers

14,896,895 görüntüleme • 5 ay önce

Day 1 of 3 days of MLX: Introducing MLX-Audio-Swift SDK 🚀 A modular Swift SDK for voice agents and tasks on Apple Silicon built by Lucas Newman and yours truly. iOS, macOS, and visionOS developers can now build native apps with real-time, on-device audio intelligence: 🗣️ Text-to-Speech (TTS) 👂 Speech-to-Text (STT) 🔄 Speech-to-Speech (STS) 🎙️ Voice Activity Detection (VAD) and more. Only import the capabilities you need, nothing extra. Get started today and leave us a star ⭐️
4:29

Day 1 of 3 days of MLX: Introducing MLX-Audio-Swift SDK 🚀 A modular Swift SDK for voice agents and tasks on Apple Silicon built by Lucas Newman and yours truly. iOS, macOS, and visionOS developers can now build native apps with real-time, on-device audio intelligence: 🗣️ Text-to-Speech (TTS) 👂 Speech-to-Text (STT) 🔄 Speech-to-Speech (STS) 🎙️ Voice Activity Detection (VAD) and more. Only import the capabilities you need, nothing extra. Get started today and leave us a star ⭐️

Prince Canuma

164,026 görüntüleme • 8 ay önce

Been experimenting with Apple's new Core AI framework over the past few days Built a mobile app that runs local AI models directly on device, exploring Core AI model deployment (.aimodel), model specialization, caching, and inference across Apple Silicon Also spent some time integrating with Apple's Foundation Models framework and understanding how custom models can coexist with Apple's on-device AI stack Still early, but the combination of Core AI, Foundation Models, and the Apple Neural Engine feels like a pretty compelling foundation for local first AI applications Still in alpha and working towards a more stable version, but it's been a fun way to explore where Apple's on device AI ecosystem is headed !!
0:28

Been experimenting with Apple's new Core AI framework over the past few days Built a mobile app that runs local AI models directly on device, exploring Core AI model deployment (.aimodel), model specialization, caching, and inference across Apple Silicon Also spent some time integrating with Apple's Foundation Models framework and understanding how custom models can coexist with Apple's on-device AI stack Still early, but the combination of Core AI, Foundation Models, and the Apple Neural Engine feels like a pretty compelling foundation for local first AI applications Still in alpha and working towards a more stable version, but it's been a fun way to explore where Apple's on device AI ecosystem is headed !!

Sagar

13,738 görüntüleme • 4 ay önce

CosmicMan A Text-to-Image Foundation Model for Humans We present CosmicMan, a text-to-image foundation model specialized for generating high-fidelity human images. Unlike current general-purpose foundation models that are stuck in the dilemma of inferior quality and
0:50

CosmicMan A Text-to-Image Foundation Model for Humans We present CosmicMan, a text-to-image foundation model specialized for generating high-fidelity human images. Unlike current general-purpose foundation models that are stuck in the dilemma of inferior quality and

AK

46,778 görüntüleme • 2 yıl önce

i was playing around the newest TTS (text to speech) model 'kokoro' which has just 82M parameters! by adding only 1 line of code you can create a custom voice that mixes any two (out of ten voices) in any ratio example: mixing one male and one female voice in the 60-40 ratio
0:24

i was playing around the newest TTS (text to speech) model 'kokoro' which has just 82M parameters! by adding only 1 line of code you can create a custom voice that mixes any two (out of ten voices) in any ratio example: mixing one male and one female voice in the 60-40 ratio

maharshi

88,765 görüntüleme • 1 yıl önce

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

22,530 görüntüleme • 4 ay önce

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 görüntüleme • 4 ay önce

Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.
4:10

Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.

AK

290,729 görüntüleme • 3 yıl önce