Skip to content
TechIndexSubmit
Back to directory

Earlybird

A 29M-parameter speech-to-text model capable of outputting words before they are fully spoken. It is designed for real-time transcription and low-latency applications.

Similar tools

  • tiny-voca is a fully open, 4.5M-parameter English text-to-speech AI model with two voices, designed for efficient, real-time operation on CPUs and in browsers.

    Models
  • A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

    AI Apps
  • SOV-Transcribe-1 is Salesforce's open-weight speech-augmented language model for non-streaming automatic speech recognition, offering high English transcription accuracy and multilingual support.

    Models
  • An open-source, multilingual Text-to-Speech (TTS) model with approximately 131M parameters, capable of both speaking and singing. It supports 14 voices across multiple languages and is designed for efficient local execution.

    Models
  • Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

    AI Apps
  • Baidu's latest foundation model in the ERNIE family, offering comprehensive improvements in coding, agentic capabilities, knowledge work, and deep research. It is a large model with 280 billion parameters and a 1M context window.

    Models