Loading video...

Video Failed to Load

Go Home

🎙️Designing a speech-to-speech assistant Build a speech-to-speech assistant with web search access in 150 lines of code. - Voxtral Transcribe 2 for STT + diarization - Mistral Small 4 for agentic reasoning & efficiency - Voxtral TTS for realistic speech synthesis

MistralDevs's profile picture

Mistral AI for Developers

11,606 subscribers

18,266 views • 4 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

🎙️Do you know you now have all the building blocks for full speech-to-speech? - Voxtral Realtime: High-quality, real-time speech-to-text. - Mistral Small 4: Fast, efficient, general-purpose agentic model. - Voxtral TTS: Realistic customizable text-to-speech with streaming output.
0:50

🎙️Do you know you now have all the building blocks for full speech-to-speech? - Voxtral Realtime: High-quality, real-time speech-to-text. - Mistral Small 4: Fast, efficient, general-purpose agentic model. - Voxtral TTS: Realistic customizable text-to-speech with streaming output.

Mistral AI for Developers

27,858 views • 4 months ago

This is what happens when you plug LLMs into voice assistants, instead of a decade of handwritten rules. This video dissects Voxtral (a family of OSS speech models) and the foundational work behind it (audio tokenization, semantic/acoustic disaggregation, etc). Thank you Mistral AI for your collaboration and for your detailed technical reports in an increasingly opaque industry! 00:00 Intro 01:03 Modular vs end-to-end speech models 03:30 Speech-to-Text 06:07 Delayed Streams Modeling (DSM) 09:41 Whisper Streaming 10:33 Voxtral Realtime 13:07 Voxtral Text-to-Speech 14:28 Throwback: WaveNet 15:24 Audio tokenization 20:39 The Voxtral Codec 21:49 Back to Voxtral TTS 25:30 Outro
26:36

This is what happens when you plug LLMs into voice assistants, instead of a decade of handwritten rules. This video dissects Voxtral (a family of OSS speech models) and the foundational work behind it (audio tokenization, semantic/acoustic disaggregation, etc). Thank you Mistral AI for your collaboration and for your detailed technical reports in an increasingly opaque industry! 00:00 Intro 01:03 Modular vs end-to-end speech models 03:30 Speech-to-Text 06:07 Delayed Streams Modeling (DSM) 09:41 Whisper Streaming 10:33 Voxtral Realtime 13:07 Voxtral Text-to-Speech 14:28 Throwback: WaveNet 15:24 Audio tokenization 20:39 The Voxtral Codec 21:49 Back to Voxtral TTS 25:30 Outro

Julia Turc

297,055 views • 1 month ago

🔊Introducing Voxtral TTS: our new frontier open-weight model for natural, expressive, and ultra-fast text-to-speech 🎭Realistic, emotionally expressive speech. 🌍Supports 9 languages and accurately captures diverse dialects. ⚡Very low latency for time-to-first-audio. 🔄Easily adaptable to new voices
1:21

🔊Introducing Voxtral TTS: our new frontier open-weight model for natural, expressive, and ultra-fast text-to-speech 🎭Realistic, emotionally expressive speech. 🌍Supports 9 languages and accurately captures diverse dialects. ⚡Very low latency for time-to-first-audio. 🔄Easily adaptable to new voices

Mistral AI

942,293 views • 4 months ago

Presenting MetaVoice-1B, a 1.2B parameter base model for TTS (text-to-speech). * Emotional speech in English * Voice cloning with fine-tuning * Zero-shot cloning for American & British voices * Support for long-form synthesis
1:54

Presenting MetaVoice-1B, a 1.2B parameter base model for TTS (text-to-speech). * Emotional speech in English * Voice cloning with fine-tuning * Zero-shot cloning for American & British voices * Support for long-form synthesis

MetaVoice

111,805 views • 2 years ago

for those who hate reading, demo video of the final speech to speech pipeline, featuring Armin Ronacher ⇌. pretty solid for < 9gb of unified RAM use for STT, TTS, and LLM combined.
1:45

for those who hate reading, demo video of the final speech to speech pipeline, featuring Armin Ronacher ⇌. pretty solid for < 9gb of unified RAM use for STT, TTS, and LLM combined.

Mario Zechner

12,852 views • 2 months ago

Our latest speech-to-speech model is faster, more accurate, and excels at function calling. Watch @promptshant and Brian Fioca build a realtime voice agent that can search the web and hand off tasks to reasoning models with full context.
1:58

Our latest speech-to-speech model is faster, more accurate, and excels at function calling. Watch @promptshant and Brian Fioca build a realtime voice agent that can search the web and hand off tasks to reasoning models with full context.

OpenAI Developers

81,822 views • 1 year ago

Introducing Voxtral WebGPU: Real-time speech transcription entirely in your browser. This demo runs Voxtral-Mini-4B, a powerful streaming ASR model from Mistral AI, locally on WebGPU. The model supports 13 languages and is capable of <500 ms latency. Fully private. Zero cost.
0:39

Introducing Voxtral WebGPU: Real-time speech transcription entirely in your browser. This demo runs Voxtral-Mini-4B, a powerful streaming ASR model from Mistral AI, locally on WebGPU. The model supports 13 languages and is capable of <500 ms latency. Fully private. Zero cost.

Xenova

94,356 views • 4 months ago

What if voice AI could understand context, intent, and emotion — not just words? 🎙️ Meet Seed Speech 2.0. A new speech AI stack designed for natural, expressive conversations — with major upgrades in both text-to-speech (TTS) and speech recognition (ASR). Built for developers and creators who want natural conversational speech. What’s inside: - Natural and expressive speech generation - Prompt-controlled emotion and tone - High-accuracy multilingual recognition - Strong contextual reasoning Built for: 🎧 Voice content creation 🤖 AI assistants ☎️ Customer service 🎬 Dubbing & subtitling 📊 Audio-video analysis Voice AI built for expression, accuracy, and understanding. Try it now → Read more about Seed Speech here → #SeedSpeech #VoiceAI #SpeechAI #AI
0:30

What if voice AI could understand context, intent, and emotion — not just words? 🎙️ Meet Seed Speech 2.0. A new speech AI stack designed for natural, expressive conversations — with major upgrades in both text-to-speech (TTS) and speech recognition (ASR). Built for developers and creators who want natural conversational speech. What’s inside: - Natural and expressive speech generation - Prompt-controlled emotion and tone - High-accuracy multilingual recognition - Strong contextual reasoning Built for: 🎧 Voice content creation 🤖 AI assistants ☎️ Customer service 🎬 Dubbing & subtitling 📊 Audio-video analysis Voice AI built for expression, accuracy, and understanding. Try it now → Read more about Seed Speech here → #SeedSpeech #VoiceAI #SpeechAI #AI

BytePlus

19,740 views • 4 months ago

Build a real-time AI Voice Agent that can actually sell. In less than 30 minutes, you'll learn how to build a sophisticated real-time voice sales agent that can have natural conversations with potential customers. Includes a full code notebook, recorded tutorial, and docs The stack: ⚡ fast inference 🎙 LiveKit for real-time audio/video infrastructure 🗣 realistic speech synthesis (STT/TTS)
0:30

Build a real-time AI Voice Agent that can actually sell. In less than 30 minutes, you'll learn how to build a sophisticated real-time voice sales agent that can have natural conversations with potential customers. Includes a full code notebook, recorded tutorial, and docs The stack: ⚡ fast inference 🎙 LiveKit for real-time audio/video infrastructure 🗣 realistic speech synthesis (STT/TTS)

Sarah Chieng

452,438 views • 10 months ago

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

163,744 views • 5 months ago

What a week for open audio models! 🕺 💃 I demo: 🗣️ Voxtral 4B TTS from Mistral AI 🎙️ Transcribe 2B from Cohere 🏭 and how to run a batch transcribe job in 1 line of CLI using Daniel van Strien uv script links below
4:39

What a week for open audio models! 🕺 💃 I demo: 🗣️ Voxtral 4B TTS from Mistral AI 🎙️ Transcribe 2B from Cohere 🏭 and how to run a batch transcribe job in 1 line of CLI using Daniel van Strien uv script links below

Jeff Boudier 🤗

32,918 views • 4 months ago

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

79,756 views • 1 month ago

An ‘interactive speech’ from Parliament. A first ? 👉🏻5 of 10 people in rural India lack internet access so they can’t watch speech 👉🏻Yet MGNREGA workers are forced to go online for wages CLIP from my speech on Budget 2026. Parliament 👇🏻 Full speech:
1:06

An ‘interactive speech’ from Parliament. A first ? 👉🏻5 of 10 people in rural India lack internet access so they can’t watch speech 👉🏻Yet MGNREGA workers are forced to go online for wages CLIP from my speech on Budget 2026. Parliament 👇🏻 Full speech:

Derek O'Brien | ডেরেক ও'ব্রায়েন

30,151 views • 5 months ago

You can use Cerebras' gpt-oss-120b to build realistic speech-to-speech voice interfaces with emotion via Hume AI's new EVI 3. Perfect for your next voice ai project! Link to try below 👇
1:20

You can use Cerebras' gpt-oss-120b to build realistic speech-to-speech voice interfaces with emotion via Hume AI's new EVI 3. Perfect for your next voice ai project! Link to try below 👇

Cerebras

22,034 views • 1 year ago

What will you build with Vision Agents? Out-of-the-box support for: - Turn detection - Speech-to-text + text-to-speech - Voice activity detection - MCP &amp; function-calling support Open-source. Video-first. Ready to build.
0:30

What will you build with Vision Agents? Out-of-the-box support for: - Turn detection - Speech-to-text + text-to-speech - Voice activity detection - MCP &amp; function-calling support Open-source. Video-first. Ready to build.

Stream

226,723 views • 6 months ago

xAI just dropped 2 absolute monsters: Grok Speech-to-Text + Grok Text-to-Speech APIs Same battle-tested stack that runs Grok Voice, millions of Tesla cars, and Starlink support. - STT: Real-time WebSocket, speaker diarization, 25+ languages, word-level timestamps. - TTS: Super natural, expressive voices with tags for laugh, sigh, whisper, emphasis, pause; batch + streaming. Put voice AI on the list of things Grok already 100%'d xAI, Grok
0:27

xAI just dropped 2 absolute monsters: Grok Speech-to-Text + Grok Text-to-Speech APIs Same battle-tested stack that runs Grok Voice, millions of Tesla cars, and Starlink support. - STT: Real-time WebSocket, speaker diarization, 25+ languages, word-level timestamps. - TTS: Super natural, expressive voices with tags for laugh, sigh, whisper, emphasis, pause; batch + streaming. Put voice AI on the list of things Grok already 100%'d xAI, Grok

Mario Nawfal

164,850 views • 3 months ago

Introducing SeamlessM4T, the first all-in-one, multilingual multimodal translation model. This single model can perform tasks across speech-to-text, speech-to-speech, text-to-text translation &amp; speech recognition for up to 100 languages depending on the task. Details ⬇️
0:56

Introducing SeamlessM4T, the first all-in-one, multilingual multimodal translation model. This single model can perform tasks across speech-to-text, speech-to-speech, text-to-text translation &amp; speech recognition for up to 100 languages depending on the task. Details ⬇️

AI at Meta

592,766 views • 2 years ago

You can now use Groq’s Kimi K2 to build super realistic speech-to-speech voice interfaces with emotion via Hume AI 's new EVI 3. Perfect for AI companions, phone calls, or anything you’re working on. Link in comments.
0:56

You can now use Groq’s Kimi K2 to build super realistic speech-to-speech voice interfaces with emotion via Hume AI 's new EVI 3. Perfect for AI companions, phone calls, or anything you’re working on. Link in comments.

Groq Inc

46,576 views • 1 year ago

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

123,544 views • 1 year ago

The best use of technology is to improve quality of life. AI powered glasses transcribe speech in real-time for people with hearing loss
2:00

The best use of technology is to improve quality of life. AI powered glasses transcribe speech in real-time for people with hearing loss

Vala Afshar

52,967 views • 3 years ago