stt-api

Examples and guides for using the Smallest AI

RaDUO turns live radio broadcasts into multilingual STT datasets for ASR research. It records stations in parallel, splits streams into clips, transcribes audio, extracts quality features, and stores searchable metadata. Includes 16 kHz mono WAVs, transcripts, station info, languages, and optional word timings.

Web-based control panel for self-hosted LLM inference on NVIDIA GPUs — vLLM, MIG, LiteLLM gateway, HTTPS, monitoring.

Realtime STT/TTS library allowing provider agnostic implementation

Speech-To-Text (STT) project

an extremely fast qwen3-asr-0.6B model on CPU for hermes agents and others.

Meet VoiceFlow 🎙️🔊, your production-ready microservices platform for all things AI speech! It's designed to make high-performance voice processing a breeze, letting you effortlessly transcribe audio to text and convert text into natural-sounding speech. 🚀

Add to my main repository

AI-powered real-time interview companion. Listens to conversations, provides instant speech-to-text transcription and translation, and generates context-aware answers based on your CV, interview history, and preferred language.

speech to text on CUDA

Bhava-Voice-Agent is a real-time, modular, multi-agent voice pipeline built on FastAPI, WebSockets, Silero VAD, Groq STT (Whisper), Multi-Agent Dialogue orchestrations, and Edge TTS. It features interactive streaming, real-time voice activity detection, multi-agent dialogue routing, and web UI streaming dashboard capabilities.

Vectra-Orbit is a real-time, cascaded AI voice calling platform built with FastAPI, WebSockets, and SQLAlchemy (PostgreSQL / SQLite). It is designed to execute voice campaigns (marketing, surveys, customer support) with automatic call forwarding / transfer to real human customer care representatives.

api for speach recognithion with gigaam model

Linux-first local voice input runtime for OpenClaw

홀로그램 대화형 AI