Speech-to-Text

Speech to Text command using IBM Watson API

Evaluate your speech-to-text system with similarity measures such as word error rate (WER)

The official Python SDK for the Soniox API (STT, REST)

Agent Framework plugin for services using Soniox's API.

Speechmatics Real-Time API Client

A lightweight Python package for Automatic Speech Recognition using ONNX models

Speechmatics Agent STT Python client for agent transcription

ElevenLabs MCP Server

Agent Framework plugin for voice synthesis and speech-to-text with Inworld's API.

Generated protocol definitions for Rime text-to-speech and speech-to-text

Speechmatics Batch API Client

Agent Framework plugin for services using Gladia's API.

A light-weight, production-ready, unified interface for various AI model providers

A streamlined Speech-to-Text pipeline for Whisper using CTranslate2

A small tool that uses Selenium to drive a local speech-to-text demo page.

Agent Framework plugin for speech synthesis and recognition with Smallest AI.

this is stt file

Run local opensource AI models (Stable Diffusion, LLMs, TTS, STT, chatbots) in a lightweight Python GUI

Meta Muse Voice Transcribe plugin for LiveKit Agents

Real-time speech-to-text with web interface and WebSocket sync

Agent-operated transcription, translation, and live browser captions

Run transformer models inside your Python program: embeddings, classification, reranking, search, chat, speech-to-text, summarization and translation. Same output as PyTorch, no PyTorch needed.

Local, offline-by-default voice dictation for Linux, macOS, and Windows — hold a key, speak, release

Local, streaming speech-to-text that types wherever your cursor is (macOS)

Prebuilt native library for transcribe-cpp (speech-to-text, ggml)

openai/whisper speech to text model + extra features

Audio Quality Estimation Client

Omnilingual ASR Modeling Library

A powerful yet lightweight Python package to calculate and analyze the Word Error Rate (WER).

Microsoft AI speech-to-text, text-to-speech, and decision plugin for LiveKit Agents

Lightweight on-device speech recognition via ggml — Python bindings for CrispASR (Whisper, Qwen3-ASR, FastConformer, Canary, Parakeet, Cohere, Granite, Voxtral, wav2vec2, and more).

High-performance Whisper transcription with Turbo v3 for Apple Silicon

Real-time speech-to-text models

Speech-to-text, speaker diarization, speaker identification, multilingual caption translation, and narration. Local-first: Whisper, NeMo Sortformer, TitaNet, Kokoro, local LLM.

LiveKit Agents plugin for Munsit voice AI: Arabic speech-to-text (batch + live streaming) and text-to-speech. Consolidates livekit-plugins-faseeh.

Python bindings for transcribe.cpp

Phonon speech recognition engine and Neutrino language models from Fermion Research, on CPU, Apple silicon and NVIDIA GPUs

Haystack integration for whisper

Pre-alpha, open, local speech-to-text and text-to-speech: licence-checked manifest, hash-verified downloads, transcribe() and synthesize() with a Whisper engine (optional extra) and an Indic Parler-TTS engine (own environment). Every model is unverified.

Official Python library for generating WebVTT and SRT captions from Deepgram and other speech-to-text API responses

NPU-accelerated local live captioning for Linux, via OpenVINO GenAI Whisper

Coro: OpenAI-compatible ASR + speaker-diarization server with pluggable backends.

Agent Framework plugin for Reson8 speech-to-text with server-side turn detection.

Text-to-speech and speech-to-text interfaces with swappable engine adapters (Kokoro, Wyoming Whisper).

Cartesia STT and TTS integration for Vision Agents

A fast Voice Activity Detection and Transcription System

Deepgram STT and TTS integration for Vision Agents

Voice dictation for Linux. Speak → text, locally, instantly.

Official Addis AI SDK for Python — voice (TTS), realtime voice streaming, chat, speech-to-text, and translation.