Загрузка видео...

Не удалось загрузить видео

На главную

You can now generate real-time speech that sounds conversational. Microsoft just open-sourced VibeVoice, a real-time text-to-speech system with ~300 ms first audio latency and streaming input. It handles long conversations without falling apart. 𝗧𝗵𝗶𝘀 𝗺𝗼𝗱𝗲𝗹 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗲𝘀 𝗹𝗼𝗻𝗴, 𝗺𝘂𝗹𝘁𝗶-𝘀𝗽𝗲𝗮𝗸𝗲𝗿 𝘀𝗽𝗲𝗲𝗰𝗵. It produces up to 90 minutes of audio. It supports...

LiorOnAI's profile picture

Lior Alexander

112,341 subscribers

60,568 просмотров • 5 месяцев назад •via X (Twitter)

ОбразованиеНовости и политикаНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Microsoft did it again! Speech AI models have a major limitation. They slice long recordings into tiny chunks, lose track of who's speaking, and forget all context halfway through. This is exactly what Microsoft's VibeVoice solves. It's an open-source family of frontier voice AI models for both speech recognition and speech generation. Here's what it can do: > VibeVoice-ASR processes up to 60 minutes of audio in a single pass. No chunking. It outputs structured transcriptions with who spoke, when they spoke, and what they said. > You can feed it custom hotwords like names, technical jargon, or domain-specific terms. The model uses them to significantly improve accuracy on specialized content. > VibeVoice-TTS generates up to 90 minutes of multi-speaker speech with up to 4 distinct speakers. Natural turn-taking, emotional expression, all in one pass. > VibeVoice-Realtime is a 0.5B streaming TTS model with ~300ms first-audio latency. Small enough to deploy practically anywhere. All of this is powered by continuous speech tokenizers running at just 7.5 Hz. This ultra-low frame rate preserves audio quality while making long sequences computationally feasible. I have shared the link to the GitHub repo in the replies!
1:10

Microsoft did it again! Speech AI models have a major limitation. They slice long recordings into tiny chunks, lose track of who's speaking, and forget all context halfway through. This is exactly what Microsoft's VibeVoice solves. It's an open-source family of frontier voice AI models for both speech recognition and speech generation. Here's what it can do: > VibeVoice-ASR processes up to 60 minutes of audio in a single pass. No chunking. It outputs structured transcriptions with who spoke, when they spoke, and what they said. > You can feed it custom hotwords like names, technical jargon, or domain-specific terms. The model uses them to significantly improve accuracy on specialized content. > VibeVoice-TTS generates up to 90 minutes of multi-speaker speech with up to 4 distinct speakers. Natural turn-taking, emotional expression, all in one pass. > VibeVoice-Realtime is a 0.5B streaming TTS model with ~300ms first-audio latency. Small enough to deploy practically anywhere. All of this is powered by continuous speech tokenizers running at just 7.5 Hz. This ultra-low frame rate preserves audio quality while making long sequences computationally feasible. I have shared the link to the GitHub repo in the replies!

Akshay 🚀

45,182 просмотров • 3 месяцев назад

🚨 JUST IN: MICROSOFT just open sourced a VOICE AI THAT TRANSCRIBES 60 MINUTES OF AUDIO in a single pass. 100% FREE. It knows who spoke. It knows when they spoke. It knows exactly what they said. All in one shot. No chunking. No context loss. It's called VibeVoice. Not a transcription tool. Not a basic speech to text wrapper. A frontier voice AI family with ASR, TTS, and real time streaming. All open source. All free. Here's what it actually does 👇 VibeVoice ASR - Speech Recognition: → Processes 60 minutes of continuous audio in a single pass → Never slices audio into chunks so global context is never lost → Identifies WHO spoke, WHEN they spoke and WHAT they said simultaneously → Supports customized hotwords for domain specific accuracy → Works in 50+ languages natively → Already adopted by Hugging Face Transformers library → Already being built on by the open source community BY PEOPLE WHO HAD NO IDEA THIS LEVEL OF ACCURACY WAS ALREADY FREE. VibeVoice TTS - Text to Speech: → Generates up to 90 minutes of speech in a single pass → Supports up to 4 distinct speakers in one conversation → Natural turn taking and speaker consistency throughout → Expressive speech that captures emotional nuances → Supports English, Chinese and multiple other languages VibeVoice Realtime - Streaming TTS: → Only 300 millisecond first audible latency → Streams text input in real time → 0.5B parameters so it actually deploys anywhere → Robust long form generation up to 10 minutes → Lightweight enough for production use today The core innovation nobody is talking about: Most voice AI models slice long audio into short chunks. Every time they slice, they lose context. Speaker tracking breaks. Semantic coherence breaks. Accuracy drops. VibeVoice uses continuous speech tokenizers running at an ultra low frame rate of 7.5 Hz. This preserves audio fidelity while dramatically boosting computational efficiency. The entire 60 minutes stays in context. Nothing gets lost. Nobody gets misidentified. The numbers: → VibeVoice ASR 7B - available now on Hugging Face → VibeVoice Realtime 0.5B - try it on Colab right now → 50+ supported languages → 11 distinct English voice styles → 9 multilingual speaker voices → Already integrated into Hugging Face Transformers → Finetuning code now available The wildest part? A voice powered input method called Vibing just built itself on top of VibeVoice ASR. Available on macOS and Windows right now. The open source community is already shipping products on top of this. 100% Open Source. Free to use. Free to fine tune. Free to build on. 🔖 Save this before your competitors find it first. 👇
0:44

🚨 JUST IN: MICROSOFT just open sourced a VOICE AI THAT TRANSCRIBES 60 MINUTES OF AUDIO in a single pass. 100% FREE. It knows who spoke. It knows when they spoke. It knows exactly what they said. All in one shot. No chunking. No context loss. It's called VibeVoice. Not a transcription tool. Not a basic speech to text wrapper. A frontier voice AI family with ASR, TTS, and real time streaming. All open source. All free. Here's what it actually does 👇 VibeVoice ASR - Speech Recognition: → Processes 60 minutes of continuous audio in a single pass → Never slices audio into chunks so global context is never lost → Identifies WHO spoke, WHEN they spoke and WHAT they said simultaneously → Supports customized hotwords for domain specific accuracy → Works in 50+ languages natively → Already adopted by Hugging Face Transformers library → Already being built on by the open source community BY PEOPLE WHO HAD NO IDEA THIS LEVEL OF ACCURACY WAS ALREADY FREE. VibeVoice TTS - Text to Speech: → Generates up to 90 minutes of speech in a single pass → Supports up to 4 distinct speakers in one conversation → Natural turn taking and speaker consistency throughout → Expressive speech that captures emotional nuances → Supports English, Chinese and multiple other languages VibeVoice Realtime - Streaming TTS: → Only 300 millisecond first audible latency → Streams text input in real time → 0.5B parameters so it actually deploys anywhere → Robust long form generation up to 10 minutes → Lightweight enough for production use today The core innovation nobody is talking about: Most voice AI models slice long audio into short chunks. Every time they slice, they lose context. Speaker tracking breaks. Semantic coherence breaks. Accuracy drops. VibeVoice uses continuous speech tokenizers running at an ultra low frame rate of 7.5 Hz. This preserves audio fidelity while dramatically boosting computational efficiency. The entire 60 minutes stays in context. Nothing gets lost. Nobody gets misidentified. The numbers: → VibeVoice ASR 7B - available now on Hugging Face → VibeVoice Realtime 0.5B - try it on Colab right now → 50+ supported languages → 11 distinct English voice styles → 9 multilingual speaker voices → Already integrated into Hugging Face Transformers → Finetuning code now available The wildest part? A voice powered input method called Vibing just built itself on top of VibeVoice ASR. Available on macOS and Windows right now. The open source community is already shipping products on top of this. 100% Open Source. Free to use. Free to fine tune. Free to build on. 🔖 Save this before your competitors find it first. 👇

Kanika

220,591 просмотров • 2 месяцев назад

Mini-Omni 2 understands image, audio and text inputs all via end-to-end voice conversations with users 🔥 > Understands and processes images, speech, and text > Generates real-time speech responses > Supports interruptions during speech Technical Overview: > Concatenates image, audio, and text features for input. > Uses text-guided delayed parallel output for real-time speech > Involves encoder adaptation, modal alignment, and multimodal fine-tuning Best part: MIT licensed ⚡
0:54

Mini-Omni 2 understands image, audio and text inputs all via end-to-end voice conversations with users 🔥 > Understands and processes images, speech, and text > Generates real-time speech responses > Supports interruptions during speech Technical Overview: > Concatenates image, audio, and text features for input. > Uses text-guided delayed parallel output for real-time speech > Involves encoder adaptation, modal alignment, and multimodal fine-tuning Best part: MIT licensed ⚡

Vaibhav (VB) Srivastav

45,409 просмотров • 1 год назад

This is a big day. Meta is open-sourcing AudioCraft. You can now generate incredible music and sounds with a single prompt. It includes the most performant Generative AI Model (audio) on the market, the "Llama" of Audio. The research framework contains the weights and code of these models: ▸ MusicGen: controllable text-to-music model. ▸ AudioGen: text-to-sound model. ▸ EnCodec: high fidelity neural audio codec. ▸ Multi Band Diffusion: An EnCodec compatible decoder using diffusion. This is going to tremendously speed up audio research 👏
0:28

This is a big day. Meta is open-sourcing AudioCraft. You can now generate incredible music and sounds with a single prompt. It includes the most performant Generative AI Model (audio) on the market, the "Llama" of Audio. The research framework contains the weights and code of these models: ▸ MusicGen: controllable text-to-music model. ▸ AudioGen: text-to-sound model. ▸ EnCodec: high fidelity neural audio codec. ▸ Multi Band Diffusion: An EnCodec compatible decoder using diffusion. This is going to tremendously speed up audio research 👏

Lior Alexander

231,604 просмотров • 2 лет назад

Generate lifelike audio in real-time without a GPU! 🚀 Check out orpheus-cpp: a llama.cpp port of orpheus 3b text-to-speech model with built-in support for sync and async streaming. 𝚙𝚒𝚙 𝚒𝚗𝚜𝚝𝚊𝚕𝚕 𝚘𝚛𝚙𝚑𝚎𝚞𝚜-𝚌𝚙𝚙 𝚙𝚢𝚝𝚑𝚘𝚗 -𝚖 𝚘𝚛𝚙𝚑𝚎𝚞𝚜_𝚌𝚙𝚙
0:31

Generate lifelike audio in real-time without a GPU! 🚀 Check out orpheus-cpp: a llama.cpp port of orpheus 3b text-to-speech model with built-in support for sync and async streaming. 𝚙𝚒𝚙 𝚒𝚗𝚜𝚝𝚊𝚕𝚕 𝚘𝚛𝚙𝚑𝚎𝚞𝚜-𝚌𝚙𝚙 𝚙𝚢𝚝𝚑𝚘𝚗 -𝚖 𝚘𝚛𝚙𝚑𝚎𝚞𝚜_𝚌𝚙𝚙

Freddy A Boulton

17,465 просмотров • 1 год назад

Real-time AI conversations are here! PlayHT, one of the best text-to-speech models I’ve used, now has a latency of less than 300ms. Checkout how fast it outputs audio 🤯 Also, my experience cloning my own voice and links to try it for free are below.
0:30

Real-time AI conversations are here! PlayHT, one of the best text-to-speech models I’ve used, now has a latency of less than 300ms. Checkout how fast it outputs audio 🤯 Also, my experience cloning my own voice and links to try it for free are below.

Alvaro Cintas

335,344 просмотров • 2 лет назад

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 просмотров • 5 месяцев назад

Introducing Marvis-TTS 🔥🚀 A new local-first TTS model Lucas Newman and I built for efficiency, accessibility, and real-time performance right on consumer devices like Apple Silicon, iPhones, iPads, and more. Traditional TTS models often demand full text inputs or sacrifice real-time capabilities, Marvis flips the script. It streams audio chunks as text is processed, creating a truly conversational experience. No more awkward pauses or unnatural breaks—Marvis handles the entire text context intelligently to deliver coherent, expressive speech. Get started today: > pip install -U mlx-audio
3:57

Introducing Marvis-TTS 🔥🚀 A new local-first TTS model Lucas Newman and I built for efficiency, accessibility, and real-time performance right on consumer devices like Apple Silicon, iPhones, iPads, and more. Traditional TTS models often demand full text inputs or sacrifice real-time capabilities, Marvis flips the script. It streams audio chunks as text is processed, creating a truly conversational experience. No more awkward pauses or unnatural breaks—Marvis handles the entire text context intelligently to deliver coherent, expressive speech. Get started today: > pip install -U mlx-audio

Prince Canuma

81,299 просмотров • 10 месяцев назад

MICROSOFT OPEN SOURCED A 7B PARAMETER MODEL THAT TRANSCRIBES 60 MINUTES OF AUDIO IN A SINGLE PASS and it's completely free VIBEVOICE ASR no chunking, no context loss, full speaker diarization baked in not just speech to text..not a basic wrapper who spoke, when they spoke, exactly what they said..all in one shot and it handles the hard stuff too..50+ languages, custom hotwords, long form audio that breaks every other tool the model doesn't know what "context window" means apparently Available on macOS and Windows right now. Free to use. Free to fine tune. Free to build on.
5:45

MICROSOFT OPEN SOURCED A 7B PARAMETER MODEL THAT TRANSCRIBES 60 MINUTES OF AUDIO IN A SINGLE PASS and it's completely free VIBEVOICE ASR no chunking, no context loss, full speaker diarization baked in not just speech to text..not a basic wrapper who spoke, when they spoke, exactly what they said..all in one shot and it handles the hard stuff too..50+ languages, custom hotwords, long form audio that breaks every other tool the model doesn't know what "context window" means apparently Available on macOS and Windows right now. Free to use. Free to fine tune. Free to build on.

Rahul

1,371,397 просмотров • 2 месяцев назад

There's a lot of interesting stuff in Seaweed-7B. No word on if they will open source: - generate video and audio together - make videos that are conditioned with audio from Omnihuman (ie a character that matches the voice and the speech is synced) - videos up to 20 seconds, or 1 minute with "extension technique" - 720p, upsample to 2k - can do real-time 720p generation at 24fps - multi-shot, long-form storytelling with scene continuity - t2v and i2v (first or last frame) - human or object reference images to insert into videos
0:25

There's a lot of interesting stuff in Seaweed-7B. No word on if they will open source: - generate video and audio together - make videos that are conditioned with audio from Omnihuman (ie a character that matches the voice and the speech is synced) - videos up to 20 seconds, or 1 minute with "extension technique" - 720p, upsample to 2k - can do real-time 720p generation at 24fps - multi-shot, long-form storytelling with scene continuity - t2v and i2v (first or last frame) - human or object reference images to insert into videos

fofr

30,718 просмотров • 1 год назад

HOLY FUCK! Zyphra just dropped Zonos - Apache 2.0 licensed, Multilingual, Text to Speech model with INSTANT voice cloning! 🔥 > Zero-shot TTS with Voice Cloning: Input text and a 10-30 second speaker sample to generate high-quality text-to-speech output > Audio Prefix Inputs: Enhance speaker matching by adding an audio prefix to the text, enabling behaviors like whispering that are hard to achieve with voice cloning alone > Multilingual Support: Supports English, Japanese, Chinese, French, and German > Audio Quality & Emotion Control: Fine-tune speaking rate, pitch, frequency, audio quality, and emotions (e.g., happiness, anger, sadness, fear) > Fast Performance: Runs at ~2x real-time speed on an RTX 4090 > Available on the Hugging Face Hub 🤗
1:21

HOLY FUCK! Zyphra just dropped Zonos - Apache 2.0 licensed, Multilingual, Text to Speech model with INSTANT voice cloning! 🔥 > Zero-shot TTS with Voice Cloning: Input text and a 10-30 second speaker sample to generate high-quality text-to-speech output > Audio Prefix Inputs: Enhance speaker matching by adding an audio prefix to the text, enabling behaviors like whispering that are hard to achieve with voice cloning alone > Multilingual Support: Supports English, Japanese, Chinese, French, and German > Audio Quality & Emotion Control: Fine-tune speaking rate, pitch, frequency, audio quality, and emotions (e.g., happiness, anger, sadness, fear) > Fast Performance: Runs at ~2x real-time speed on an RTX 4090 > Available on the Hugging Face Hub 🤗

Vaibhav (VB) Srivastav

298,858 просмотров • 1 год назад

Listen up 🔊 We’ve made some updates to our Gemini Audio models and capabilities: — Gemini’s live speech-to-speech translation capability is rolling out in a beta experience to the Google Translate app, bringing you real-time audio translation that captures the nuance of human speech — Gemini 2.5 Flash and 2.5 Pro Text-to-Speech preview models bring improved adherence to style prompts, precision pacing with context-aware speed adjustments, and character voice consistency for multi-speaker scenarios — Gemini 2.5 Flash Native Audio is now updated, with improvements to handle complex workflows, navigate user instructions, and hold natural conversations
2:50

Listen up 🔊 We’ve made some updates to our Gemini Audio models and capabilities: — Gemini’s live speech-to-speech translation capability is rolling out in a beta experience to the Google Translate app, bringing you real-time audio translation that captures the nuance of human speech — Gemini 2.5 Flash and 2.5 Pro Text-to-Speech preview models bring improved adherence to style prompts, precision pacing with context-aware speed adjustments, and character voice consistency for multi-speaker scenarios — Gemini 2.5 Flash Native Audio is now updated, with improvements to handle complex workflows, navigate user instructions, and hold natural conversations

Google AI

1,092,032 просмотров • 6 месяцев назад

Oh my…FlashLabs releases Chroma 1.0, first open-source real-time speech-to-speech model with personalized voice cloning. Native speech-to-speech with <150ms latency & voice cloning from seconds of audio. Finally, an open alternative to OpenAI Realtime.
1:57

Oh my…FlashLabs releases Chroma 1.0, first open-source real-time speech-to-speech model with personalized voice cloning. Native speech-to-speech with <150ms latency & voice cloning from seconds of audio. Finally, an open alternative to OpenAI Realtime.

Alvaro Cintas

46,151 просмотров • 5 месяцев назад

Universal-Streaming is our real-time speech-to-text model — built for voice agents with ~300ms latency, high accuracy, unlimited concurrency, and just $0.15/hour. 👉 Test it live in the playground →
1:03

Universal-Streaming is our real-time speech-to-text model — built for voice agents with ~300ms latency, high accuracy, unlimited concurrency, and just $0.15/hour. 👉 Test it live in the playground →

AssemblyAI

1,017,880 просмотров • 1 год назад

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

290,517 просмотров • 3 лет назад

🚨 ElevenLabs just killed every transcription tool on the market. They dropped Scribe v2 Realtime and it's not just another speech-to-text model. This thing processes audio in real-time with zero lag, handles multiple speakers, and actually understands context not just words. Here's how with real examples: Full thread 🧵
0:50

🚨 ElevenLabs just killed every transcription tool on the market. They dropped Scribe v2 Realtime and it's not just another speech-to-text model. This thing processes audio in real-time with zero lag, handles multiple speakers, and actually understands context not just words. Here's how with real examples: Full thread 🧵

Hasan Toor

220,459 просмотров • 7 месяцев назад

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

185,560 просмотров • 2 лет назад

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 просмотров • 3 месяцев назад

Today we're releasing our first open source TTS model, TADA! TADA (Text Audio Dual Alignment) is a speech-language model that generates text and audio in one synchronized stream to reduce token-level hallucinations and improve latency. This means: → Zero content hallucinations across 1,000+ test samples → 5x faster than similar-grade LLM-based TTS → Fits much longer audio: 2,048 tokens cover ~700 seconds with TADA vs. ~70 seconds in conventional systems → Free transcript alongside audio with no added latency
0:55

Today we're releasing our first open source TTS model, TADA! TADA (Text Audio Dual Alignment) is a speech-language model that generates text and audio in one synchronized stream to reduce token-level hallucinations and improve latency. This means: → Zero content hallucinations across 1,000+ test samples → 5x faster than similar-grade LLM-based TTS → Fits much longer audio: 2,048 tokens cover ~700 seconds with TADA vs. ~70 seconds in conventional systems → Free transcript alongside audio with no added latency

Hume AI

269,190 просмотров • 3 месяцев назад