正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

We released Qwen3-Omni-Flash (2025-12-01 version) API Service. Smarter interaction, more human expression: · A/V Interaction: Significant boost in instruction following. Solves "dumbing down" in casual chats with rock-solid stability. · Precise Control: Enhanced System Prompt adherence for specific personas, styles, and lengths. · Multilingual Mastery: Solved language switching instability.... show more

Tongyi Lab

16,828 subscribers

1,636,707 次观看 • 6 个月前 •via X (Twitter)

教育新闻政治科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Flux Multilingual is live. Real-time conversational speech-to-text for voice agents in 10 languages, with monolingual-grade accuracy, turn detection, and code-switching. Deploy once and launch globally. Learn more →

Flux Multilingual is live. Real-time conversational speech-to-text for voice agents in 10 languages, with monolingual-grade accuracy, turn detection, and code-switching. Deploy once and launch globally. Learn more →

Deepgram

14,779 次观看 • 1 个月前

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

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 次观看 • 3 个月前

Meet the new Qwen3-TTS (2025-11-27): a major step forward in lifelike voice generation! > 49+ distinctive voices ranging from playful to authoritative, giving creators precise control over personality and style. > Global language coverage with 10 languages and multiple authentic dialects, including Minnan, Wu, Cantonese, Sichuan, Beijing, Nanjing, Tianjin, and Shaanxi. > Human-level delivery with adaptive rhythm, pacing, and intonation that makes speech sound genuinely performed.

Meet the new Qwen3-TTS (2025-11-27): a major step forward in lifelike voice generation! > 49+ distinctive voices ranging from playful to authoritative, giving creators precise control over personality and style. > Global language coverage with 10 languages and multiple authentic dialects, including Minnan, Wu, Cantonese, Sichuan, Beijing, Nanjing, Tianjin, and Shaanxi. > Human-level delivery with adaptive rhythm, pacing, and intonation that makes speech sound genuinely performed.

steven

45,722 次观看 • 6 个月前

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.

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 次观看 • 3 年前

Speech to Speech is now available in 29 languages. In November, we launched Speech to Speech, enabling you to transform your voice into another character with full control over emotions, timing, and delivery. Today we're making Speech to Speech multilingual. Use Speech to Speech to get more control than with prompting alone. Simply say it how you want it, choose a target voice, and generate.

Speech to Speech is now available in 29 languages. In November, we launched Speech to Speech, enabling you to transform your voice into another character with full control over emotions, timing, and delivery. Today we're making Speech to Speech multilingual. Use Speech to Speech to get more control than with prompting alone. Simply say it how you want it, choose a target voice, and generate.

ElevenLabs

113,317 次观看 • 2 年前

Today, we’re excited to introduce Miso One, the most emotive voice model in the world. Miso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a human and responds faster than a human, with just 110 milliseconds of latency. We’ve open-sourced the model weights, with API access coming soon. Hear how Miso One sounds in the thread below.

Today, we’re excited to introduce Miso One, the most emotive voice model in the world. Miso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a human and responds faster than a human, with just 110 milliseconds of latency. We’ve open-sourced the model weights, with API access coming soon. Hear how Miso One sounds in the thread below.

Aoden Teo

5,094,876 次观看 • 22 天前

Meet the new Qwen3‑TTS lineup: VoiceDesign and VoiceClone • VoiceDesign: controllable speech via text; no presets; strong role‑play performance • VoiceClone: clone from 3s audio; supports 10 languages; lower WER; more natural cadence Follow us for more updates!

Meet the new Qwen3‑TTS lineup: VoiceDesign and VoiceClone • VoiceDesign: controllable speech via text; no presets; strong role‑play performance • VoiceClone: clone from 3s audio; supports 10 languages; lower WER; more natural cadence Follow us for more updates!

Alibaba Cloud

204,745 次观看 • 5 个月前

We have officially launched Fun-ASR1.5, a major update to our end-to-end speech recognition model. This release focuses on three core pillars: broader language coverage, language switching, and production-ready text output. Key Features: • Multilingual Support: Supports high-accuracy recognition for 30 languages across Asia, Europe, and the Middle East within a single model. • Language Switching: Handles mixed-language speech (Code-Switching) natively, automatically detecting and transcribing language shifts without the need for manual tagging. • Professional Text Output: Delivers "ready-to-use" text with smart punctuation and automatic formatting for dates, numbers, and currencies. Fun-ASR1.5 bridges the gap between raw audio and professional documentation, providing a reliable engine for global communication.

We have officially launched Fun-ASR1.5, a major update to our end-to-end speech recognition model. This release focuses on three core pillars: broader language coverage, language switching, and production-ready text output. Key Features: • Multilingual Support: Supports high-accuracy recognition for 30 languages across Asia, Europe, and the Middle East within a single model. • Language Switching: Handles mixed-language speech (Code-Switching) natively, automatically detecting and transcribing language shifts without the need for manual tagging. • Professional Text Output: Delivers "ready-to-use" text with smart punctuation and automatic formatting for dates, numbers, and currencies. Fun-ASR1.5 bridges the gap between raw audio and professional documentation, providing a reliable engine for global communication.

Tongyi Lab

3,917,307 次观看 • 2 个月前

Meet MiniMax Speech 2.6 — Ultra-Fast, Ultra-Human, Ultra-Smart ⚡Ultra-Fast: <250 ms latency for real-time conversational interactions 💬Smart Text Normalization for URLs, emails, dates, numbers & more 🎙️Full Voice Clone + Fluent LoRA: natural, expressive, effortless 🌍40+ languages with inline code switching Fluent anytime. In every language. 👉 API available:

Meet MiniMax Speech 2.6 — Ultra-Fast, Ultra-Human, Ultra-Smart ⚡Ultra-Fast: <250 ms latency for real-time conversational interactions 💬Smart Text Normalization for URLs, emails, dates, numbers & more 🎙️Full Voice Clone + Fluent LoRA: natural, expressive, effortless 🌍40+ languages with inline code switching Fluent anytime. In every language. 👉 API available:

Hailuo AI (MiniMax)

553,217 次观看 • 7 个月前

Introducing — a new conversational Voice AI platform and API for creating human-like voice agents and voice interfaces. Powered by our new Large Dialogue Model (LDM), Play LDM 1.0 makes the speech generation contextual; handles turn-taking, interruption, voice energy and emotion modulation for a natural, fluid, human conversations in real-time.

Introducing — a new conversational Voice AI platform and API for creating human-like voice agents and voice interfaces. Powered by our new Large Dialogue Model (LDM), Play LDM 1.0 makes the speech generation contextual; handles turn-taking, interruption, voice energy and emotion modulation for a natural, fluid, human conversations in real-time.

PlayAI

105,616 次观看 • 2 年前

Play AI by vibx (YC W23) is a new platform for creating human-like voice agents. It makes speech generation contextual and handles turn-taking, interruption, voice energy, and emotion modulation for natural, fluid, human conversations in real-time.

Play AI by vibx (YC W23) is a new platform for creating human-like voice agents. It makes speech generation contextual and handles turn-taking, interruption, voice energy, and emotion modulation for natural, fluid, human conversations in real-time.

Y Combinator

21,285 次观看 • 2 年前

New tiny VLM: LFM2.5-VL-450M > Supports bounding box prediction, object detection, and function calling > Improved multilingual capabilities across 9 languages > Enhanced instruction following for vision and text tasks

New tiny VLM: LFM2.5-VL-450M > Supports bounding box prediction, object detection, and function calling > Improved multilingual capabilities across 9 languages > Enhanced instruction following for vision and text tasks

Maxime Labonne

32,092 次观看 • 2 个月前

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 ⚡

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 次观看 • 1 年前

Grok's Text to Speech API is now available in LiveKit Inference. Natural, expressive voices with low-latency streaming. Multilingual in 20+ languages. Telephony and production-ready out of the box. One API key. No extra setup. →

Grok's Text to Speech API is now available in LiveKit Inference. Natural, expressive voices with low-latency streaming. Multilingual in 20+ languages. Telephony and production-ready out of the box. One API key. No extra setup. →

LiveKit

158,923 次观看 • 3 个月前

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

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

1,091,941 次观看 • 6 个月前

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 :)

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

123,480 次观看 • 1 年前

In this demo, we show real-time voice translation between Indian languages. The user can speak in their preferred language, and the system translates and responds in another, preserving both meaning and natural delivery. Speech recognition, translation, and expressive text-to-speech work together seamlessly.

In this demo, we show real-time voice translation between Indian languages. The user can speak in their preferred language, and the system translates and responds in another, preserving both meaning and natural delivery. Speech recognition, translation, and expressive text-to-speech work together seamlessly.

Pratyush Kumar

15,206 次观看 • 4 个月前

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.

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

6,989,575 次观看 • 10 天前

gpt-realtime was trained with customers to excel at real-world tasks like support, personal assistance, and education. It’s better at: • Following instructions • Calling tools • Natural, expressive speech • Understanding cues (like laughs) • Switching languages

gpt-realtime was trained with customers to excel at real-world tasks like support, personal assistance, and education. It’s better at: • Following instructions • Calling tools • Natural, expressive speech • Understanding cues (like laughs) • Switching languages

OpenAI Developers

38,395 次观看 • 10 个月前

Shanghai’s Moya humanoid robot walks with human-like motion, shows realistic facial expressions, and is designed for natural interaction in healthcare and service roles.

Shanghai’s Moya humanoid robot walks with human-like motion, shows realistic facial expressions, and is designed for natural interaction in healthcare and service roles.

Interesting Engineering

15,127 次观看 • 4 个月前