Moonshine Open-Weights STT models
higher accuracy than WhisperLargev3. Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces. I wanted to share our new speech to text model, and the library to use them effectively.
Open source
Reactions (1)
Similar products
by description similarity
Babytalk
github.comOffline speech to text and text to speech on ESP32
Nari Qwen3-TTS and Qwen3-ASR
narilabs.comHigh accuracy, low latency and cost
High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model
Three new Kitten TTS models
github.comsmallest less than 25MB
Voice bots with 500ms response times
fastvoiceagent.cerebrium.aiA demo showcasing the potential capabilities of voice-driven AI chatbots when optimized and deployed to minimize network and model latency.