Search Results for "streaming"

x
Sort By:

Showing 1 open source project for "streaming"

View related business solutions
Speech Python Clear Filters & Widen Search
  • Vibes don’t ship, Retool does Icon
    Vibes don’t ship, Retool does

    Start from a prompt and build production-ready apps on your data—with security, permissions, and compliance built in.

    Vibe coding tools create cool demos, but Retool helps you build software your company can actually use. Generate internal apps that connect directly to your data—deployed in your cloud with enterprise security from day one. Build dashboards, admin panels, and workflows with granular permissions already in place. Stop prototyping and ship on a platform that actually passes security review.
    Build apps that ship
  • Outgrown Windows Task Scheduler? Icon
    Outgrown Windows Task Scheduler?

    Free diagnostic identifies where your workflow is breaking down—with instant analysis of your scheduling environment.

    Windows Task Scheduler wasn't built for complex, cross-platform automation. Get a free diagnostic that shows exactly where things are failing and provides remediation recommendations. Interactive HTML report delivered in minutes.
    Download Free Tool
  • 1
    Moshi

    Moshi

    A speech-text foundation model for real time dialogue

    Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec. Mimi processes 24 kHz audio, down to a 12.5 Hz representation with a bandwidth of 1.1 kbps, in a fully streaming manner (latency of 80ms, the frame size), yet performs better than existing, non-streaming, codecs like SpeechTokenizer (50 Hz, 4kbps), or SemantiCodec (50 Hz, 1.3kbps). Moshi models two streams of audio: one corresponds to Moshi, and the other one to the user. ...
    Downloads: 5 This Week
    Last Update:
    See Project
  • Previous
  • You're on page 1
  • Next

Related Categories