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。

🎙️Transcribe meetings, interviews, and more - with built-in speaker diarization and segmentation.

Mistral AI for Developers

9,998 subscribers

11,986 次观看 • 2 个月前 •via X (Twitter)

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

Start experimenting with Voxtral Mini Transcribe 2 in the new audio playground on Mistral Studio. Upload files, toggle diarization, add context bias, and get instant transcriptions.

Start experimenting with Voxtral Mini Transcribe 2 in the new audio playground on Mistral Studio. Upload files, toggle diarization, add context bias, and get instant transcriptions.

Mistral AI

44,999 次观看 • 5 个月前

🎙️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

🎙️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

Mistral AI for Developers

18,182 次观看 • 3 个月前

Automate or simplify your workflow for subtitle creation with Voxtral Transcribe 2.0! From word-level timestamps to diarization and context biasing, take it further by leveraging our other general-purpose models to translate subtitles.

Automate or simplify your workflow for subtitle creation with Voxtral Transcribe 2.0! From word-level timestamps to diarization and context biasing, take it further by leveraging our other general-purpose models to translate subtitles.

Mistral AI for Developers

14,886 次观看 • 5 个月前

Checking in with our new Brazilians. 🇧🇷 Watch Jesus and Jair's first interviews! 🎙️

Checking in with our new Brazilians. 🇧🇷 Watch Jesus and Jair's first interviews! 🎙️

Nottingham Forest

34,245 次观看 • 11 个月前

Introducing Prompter. Pro teleprompting built for chat, scripts, meetings, and more. Available now:

Introducing Prompter. Pro teleprompting built for chat, scripts, meetings, and more. Available now:

Elgato

2,458,337 次观看 • 2 年前

🚀 Introducing +AI Meeting Notes! Now, within Spark, you can easily transcribe and summarize your meetings! Available now on Desktop, with read-only mode on mobile ✨

🚀 Introducing +AI Meeting Notes! Now, within Spark, you can easily transcribe and summarize your meetings! Available now on Desktop, with read-only mode on mobile ✨

Spark Email

104,578 次观看 • 1 年前

fenix 8 is here, and it’s evolved. - AMOLED or Solar - Built-in speaker and microphone - Dive rated with leakproof buttons and new sensor guard - Dynamic round-trip routing - Sport-specific strength training - And much, much, more. ♾️

fenix 8 is here, and it’s evolved. - AMOLED or Solar - Built-in speaker and microphone - Dive rated with leakproof buttons and new sensor guard - Dynamic round-trip routing - Sport-specific strength training - And much, much, more. ♾️

Garmin

10,694 次观看 • 1 年前

$100K ₿ and more in this week's 'Kraken in 60' with @Pete_Rizzo_ 🇧🇷 BRL deposits now live via PIX ⚙️ Makina is coming to @Inkonchain 📊 Derivatives rolling out in the UK 🎙️ Interviews with Thomas Perfumo, CFA | thomasp.eth 🐒 and Co-CEO Dave Ripley

$100K ₿ and more in this week's 'Kraken in 60' with @Pete_Rizzo_ 🇧🇷 BRL deposits now live via PIX ⚙️ Makina is coming to @Inkonchain 📊 Derivatives rolling out in the UK 🎙️ Interviews with Thomas Perfumo, CFA | thomasp.eth 🐒 and Co-CEO Dave Ripley

Kraken Exchange

27,383 次观看 • 1 年前

I’m falling in love with Ashley more and more! Her interviews are soo refreshing 🥹🥰 #BBMzansi #AshleyOlge

I’m falling in love with Ashley more and more! Her interviews are soo refreshing 🥹🥰 #BBMzansi #AshleyOlge

THABELO🇿🇦

14,652 次观看 • 1 年前

Ever wish you could be in two places at once? 🤔 With HeyGen’s Interactive Avatar, now you can! Let your AI twin take over meetings, interviews, sales calls, and more. Check out our launch on Product Hunt!👇

HeyGen

22,611 次观看 • 1 年前

Introducing Wan 2.6 🎥 Cinematic multishot AI videos with scene-based segmentation and built-in multilingual audio. Create up to 15-second videos in 1080p, with precise control over the timing of every shot Available now on Freepik

Introducing Wan 2.6 🎥 Cinematic multishot AI videos with scene-based segmentation and built-in multilingual audio. Create up to 15-second videos in 1080p, with precise control over the timing of every shot Available now on Freepik

Magnific (formerly Freepik)

15,552 次观看 • 6 个月前

Make your own NYC street interviews in any style in MINUTES. Generate your image with Imagen4, stylize it with Flux Kontext, and choose the speaker with Face Selection (only in Hedra Studio). One platform. One workflow.

Make your own NYC street interviews in any style in MINUTES. Generate your image with Imagen4, stylize it with Flux Kontext, and choose the speaker with Face Selection (only in Hedra Studio). One platform. One workflow.

Hedra

33,994 次观看 • 1 年前

🎙️ Maggie Wolfendale interviews Kendrick Carmouche and Todd Pletcher Racing Stables after their win in the Grade 3 With Anticipation Stakes with Final Score. ⤵️

🎙️ Maggie Wolfendale interviews Kendrick Carmouche and Todd Pletcher Racing Stables after their win in the Grade 3 With Anticipation Stakes with Final Score. ⤵️

NYRA (🌳)

26,494 次观看 • 10 个月前

Microsoft just killed voice subscriptions. 🤯 They quietly open-sourced VibeVoice, and it’s a total industry disruptor. Transcribe hour-long meetings or generate 90 minutes of natural, multi-speaker speech, all locally on your hardware for free. It handles 50+ languages and complex speaker tracking without the monthly fees. The era of expensive voice apps is officially over. I share updates like these in my free AI community on WhatsApp. Join here

Microsoft just killed voice subscriptions. 🤯 They quietly open-sourced VibeVoice, and it’s a total industry disruptor. Transcribe hour-long meetings or generate 90 minutes of natural, multi-speaker speech, all locally on your hardware for free. It handles 50+ languages and complex speaker tracking without the monthly fees. The era of expensive voice apps is officially over. I share updates like these in my free AI community on WhatsApp. Join here

Vaibhav Sisinty

22,056 次观看 • 2 个月前

With the first presidential debate only two days away, Pres. Biden held a mock debate with his personal lawyer. Former Pres. Trump has been holding campaign events, policy meetings with advisors, and doing media interviews. Rachel Scott has more.

With the first presidential debate only two days away, Pres. Biden held a mock debate with his personal lawyer. Former Pres. Trump has been holding campaign events, policy meetings with advisors, and doing media interviews. Rachel Scott has more.

World News Tonight

11,096 次观看 • 2 年前

Track Anything: Segment Anything Meets Videos Track-Anything is a flexible and interactive tool for video object tracking and segmentation suitable for: - Video object tracking and segmentation with shot changes. - Visualized development and data annnotation for video object tracking and segmentation. - Object-centric downstream video tasks, such as video inpainting and editing. abs: github:

Track Anything: Segment Anything Meets Videos Track-Anything is a flexible and interactive tool for video object tracking and segmentation suitable for: - Video object tracking and segmentation with shot changes. - Visualized development and data annnotation for video object tracking and segmentation. - Object-centric downstream video tasks, such as video inpainting and editing. abs: github:

AK

578,619 次观看 • 3 年前

Sarvam Beats GPT-4o: India’s New AI Model Claims Top Spot in Indic Speech Sarvam AI, an Indian startup, recently launched Sarvam Audio, a speech recognition model that claims superior performance over GPT-4o Transcribe on Indic language benchmarks. This development highlights India's push for AI sovereignty in handling local linguistic nuances. Sarvam Audio supports 22 Indian languages from the Eighth Schedule, plus Indian English, with strong handling of code-mixing like Hindi-English blends. It features built-in speaker diarization for up to eight speakers and processes long-form audio such as podcasts or meetings. Trained on the IndicVoices dataset 12,000 hours from over 16,000 speakers across 208 districts it captures real-world noise and spontaneous speech. The model reportedly outperforms GPT-4o Transcribe and Gemini 3 Flash in transcription accuracy (lower Word Error Rate) on IndicVoices benchmarks for unnormalized, normalized, and code-mixed speech. Sarvam attributes this to specialization on Indian accents and patterns, unlike global models trained on Western data. Detailed public benchmarks are pending independent verification. Key Applications 🔴 Call centers and logistics for multilingual transcription. 🔴 Banking, fintech, and e-commerce for customer interactions. 🔴 Podcasts, meetings, and lectures via API for real-time or batch processing. 🔴 This B2B-focused tool aligns with India's IndiaAI Mission, backed by government GPU access for sovereign LLMs. Credit : AIM Networks.

Sarvam Beats GPT-4o: India’s New AI Model Claims Top Spot in Indic Speech Sarvam AI, an Indian startup, recently launched Sarvam Audio, a speech recognition model that claims superior performance over GPT-4o Transcribe on Indic language benchmarks. This development highlights India's push for AI sovereignty in handling local linguistic nuances. Sarvam Audio supports 22 Indian languages from the Eighth Schedule, plus Indian English, with strong handling of code-mixing like Hindi-English blends. It features built-in speaker diarization for up to eight speakers and processes long-form audio such as podcasts or meetings. Trained on the IndicVoices dataset 12,000 hours from over 16,000 speakers across 208 districts it captures real-world noise and spontaneous speech. The model reportedly outperforms GPT-4o Transcribe and Gemini 3 Flash in transcription accuracy (lower Word Error Rate) on IndicVoices benchmarks for unnormalized, normalized, and code-mixed speech. Sarvam attributes this to specialization on Indian accents and patterns, unlike global models trained on Western data. Detailed public benchmarks are pending independent verification. Key Applications 🔴 Call centers and logistics for multilingual transcription. 🔴 Banking, fintech, and e-commerce for customer interactions. 🔴 Podcasts, meetings, and lectures via API for real-time or batch processing. 🔴 This B2B-focused tool aligns with India's IndiaAI Mission, backed by government GPU access for sovereign LLMs. Credit : AIM Networks.

Augadh

43,429 次观看 • 5 个月前

It's time for a musical journey that bridges generations and genres, travelling across continents and timelines, with in-depth interviews and features with Nicky B. 🎙️ Mandisi Dyantyis Sunday 8 February #TheWorldShowWithNickyB #MandisiDyantyisOnKaya959 📻

It's time for a musical journey that bridges generations and genres, travelling across continents and timelines, with in-depth interviews and features with Nicky B. 🎙️ Mandisi Dyantyis Sunday 8 February #TheWorldShowWithNickyB #MandisiDyantyisOnKaya959 📻

Kaya ON 959

47,764 次观看 • 5 个月前