Log inSign up
Deepgram
2,678 posts
user avatar
Deepgram
@DeepgramAI
Real-time APIs powering the Voice AI economy. Trusted by enterprises & 200k+ developers to build low-latency Voice AI. Get $200 free โ†’ dpgr.am/try-free
San Francisco, CA
deepgram.com
Joined February 2016
744
Following
10.8K
Followers
  • Pinned
    user avatar
    Deepgram
    @DeepgramAI
    May 14
    Nova-3 expands speech-to-text support across Asia-Pacific. ๐ŸŒ New support now available for: ๐Ÿ”น Thai ๐Ÿ”น Cantonese Traditional ๐Ÿ”น Mandarin Simplified ๐Ÿ”น Mandarin Traditional Plus: โœ”๏ธ Accuracy improvements for Bengali, Marathi, Tamil, and Telugu โœ”๏ธ New Gujarati support Built
    00:00
    1.6K
  • user avatar
    Deepgram
    @DeepgramAI
    Sep 19, 2023
    Introducing Nova-2, our next-gen model for superhuman speech-to-text. TL;DR Nova-2 delivers: ๐Ÿ’ฅ Next-level accuracy: +18% accuracy than Nova-1 & over 36% accuracy than OpenAI Whisper large ๐Ÿ’ฅ Up to 40x faster ๐Ÿ’ฅ Same low cost: 3-7x cheaper dpgr.am/044098e ๐Ÿงต๐Ÿ‘‡
    00:00
    2.2M
  • user avatar
    Deepgram
    @DeepgramAI
    Feb 12, 2025
    Nova-3, our most advanced speech-to-text, is here! โšก๏ธ โœ… Leads in accuracy by 54.2% (streaming) and 47.4% (pre-recorded) vs. next-best ASR โœ… New real-time multilingual capabilities โœ… Self-serve customization (vocabulary adaptation without retraining) See the benchmarks (๐Ÿงต)
    00:00
    495K
  • user avatar
    Deepgram
    @DeepgramAI
    Mar 12, 2024
    The wait is finally over! We're thrilled to present Aura text-to-speech to the world. ๐Ÿ‘‹ TL;DR it checks all the boxes: โšก๏ธ Lightning-fast: <250 ms latency ๐Ÿ—ฃ๏ธ High-quality voices: natural tone, rhythm, emotion ๐Ÿš€ Cost-effective for high-throughput use cases
    00:00
    1.1M
  • user avatar
    Deepgram
    @DeepgramAI
    Dec 7, 2023
    Weโ€™re thrilled to introduce Aura, a powerful text-to-speech (#TTS) model built for real-time, conversational voice AI agents. ๐ŸŽ‰ Check it out: dpgr.am/3d07449 Let's dive in... ๐Ÿงต
    592K
  • user avatar
    Deepgram
    @DeepgramAI
    Sep 19, 2024
    Introducing our unified Voice Agent API! โšก๏ธ Quickly and easily build voice agents that listen, think, and respond in real-time, as naturally as a human can. Powered by the industry's fastest, most performant speech recognition and voice synthesis models to deliver:
    00:00
    726K
  • user avatar
    Deepgram
    @DeepgramAI
    Apr 15, 2025
    The worldโ€™s first enterprise text to speech is here. Aura-2 is now available! It delivers: โœ… 40+ natural, expressive voices โœ… Superior pronunciation of industry terms โœ… Sub-200ms latency for real-time apps Put it to the test: dpgr.am/tryaura2 Dive deeper in ๐Ÿงต...
    Introducing Aura-2: The Worldโ€™s First Enterprise-Grade Text-to-Speech
    184K
  • user avatar
    Deepgram
    @DeepgramAI
    Nov 14, 2023
    The wait is over! With 60M+ minutes transcribed, our next-gen speech-to-text model Nova-2 is now available. What's new? โœ… Expanded languages: Spanish, Hindi, German, French, Portuguese โœ… Custom model training โœ… On-prem deployment dpgr.am/9f52615 Let's dive in...๐Ÿงต
    00:00
    1.4M
  • user avatar
    Deepgram
    @DeepgramAI
    Aug 22, 2024
    Learn how to build a voice AI agent from the ground up in our virtual workshop with @GroqInc. -Hands-on coding and expert guidance -Best practices for responsive voice interactions -$1K in Deepgram credits to build with ๐Ÿ“† Sept 20 @ 9AM-12PM Register: dpgr.am/VoiceAILabs
    584K
  • user avatar
    Deepgram
    @DeepgramAI
    Apr 13, 2023
    MAJOR NEWS๐Ÿšจ We're excited to introduce Novaโšก๏ธ our most powerful speech-to-text model. TL;DR it surpasses competitors on: ๐Ÿ’ฅSpeed: 23x faster ๐Ÿ’ฅAccuracy: 22% fewer errors ๐Ÿ’ฅCost: 3-7x cheaper dpgr.am/c6f4cf4 Letโ€™s dig in on how Nova outperforms every ASR modelโ€ฆ ๐Ÿงต
    00:00
    1.5M
  • user avatar
    Deepgram
    @DeepgramAI
    Feb 15, 2024
    Weโ€™re thrilled to announce a major expansion of Deepgramโ€™s Audio Intelligence lineup. ๐Ÿš€ Introducing new models for sentiment analysis, intent recognition, and topic detection for enhanced understanding of conversational interactions. dpgr.am/e78eafa Let's dive in.. ๐Ÿงต
    00:00
    239K
  • user avatar
    Deepgram
    @DeepgramAI
    Oct 4, 2024
    After spending time with #OpenAIโ€™s Voice Mode in #ChatGPT, we were eager to explore the API behind it. A few weeks ago, we launched our Voice Agent API, and weโ€™ve been curious to see how the two compare. Hereโ€™s what we foundโ€”just some early thoughts. ๐Ÿ‘‡
    00:00
    241K
  • user avatar
    Deepgram
    @DeepgramAI
    Feb 27, 2025
    Imagine using your voice to guide an AI as you code, turning ideas into working prototypes fast. Meet Vibe Coder, our experimental, open-source take on voice-driven coding aka #vibecoding (shout out to @karpathy for coining this catchy term). Weโ€™ve been tinkering with how voice
    Introducing Vibe Coder: Our Take on Voice-Driven Coding
    208K
  • user avatar
    Deepgram
    @DeepgramAI
    Sep 5, 2024
    Healthcare's $1 trillion admin problem has a solution: AI. Companies like @chartnote , @Sonia_Health, and @stackai are revolutionizing care, automating note taking, EHR documentation, QA, and more. We're powering health tech apps with our Nova-2 model for real-time medical
    Transforming Healthcare and Delivering ROI with the Nova-2 Medical Transcription API | Deepgram
    606K

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms of Service|Privacy Policy|Cookie Policy|Accessibility|Ads info|ยฉ 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up