Batch speech-to-text via Google Cloud Speech-to-Text API for AgentOS voice pipeline
Accessible On-Demand YouTube Import, Live Streams, Smart Recommendations, Sleep Timer, Touch Gestures, Voice Assistant & A11y Engine for PeerTube
Offline speech-to-text via Vosk for AgentOS voice pipeline
fal.ai adapter for TanStack AI image, video, live, audio, speech, and transcription generation.
Node.js bindings for OpenAI's Whisper. Runs local on CPU.
An easy-to-use speech toolset. Includes tools for synthesis, recognition, alignment, speech translation, language detection, source separation and more.
On-device AI for React Native and Expo: LLMs, speech-to-text, vision, and embeddings. Each capability is opt-in at build time. No API key. Zero runtime JavaScript dependencies.
Generated protocol definitions for Rime text-to-speech and speech-to-text
speech to text with google speech api
React Component For Web Speech API
SocialDataX / 社媒数据助手 skill installer and direct CLI helper for hosted MCP services.
Voice plugin for DeepSeek Harness: local streaming speech recognition into editable drafts, sentence-by-sentence read-aloud with captions, and voice interruption. Edge online or local VITS/Kokoro TTS; host compatibility is bounded by engines.dsh.
Offline voice dictation and read-aloud for OpenCode Desktop and TUI on Windows and Linux
Speech engines for Helix dictation that recognize in the page, on the device: Moonshine, in WebAssembly.
OpenAI provider — DALL-E 3 image generation, GPT-4o Vision description, TTS-1 text-to-speech, Whisper-1 speech-to-text
moved to speechless
Deepgram provider — Nova-2 speech-to-text transcription and speaker diarization
Real-time PCM audio streaming for Expo (New Architecture)
豆包输入法 ASR TypeScript 客户端
Soniox transcription provider for the Vercel AI SDK.
The Lumavox API from your server: end users, ephemeral keys and the rest, typed from the published OpenAPI document. Zero dependencies.
Local cockpit for the Claude Code CLI — multi-tab terminal, full config surface, scheduler, voice dictation, and live observability.
ElevenLabs adapter for TanStack AI realtime voice, text-to-speech, transcription, music, and sound effects.
A web component that a developer can use to enable accurate speech-to-text, either locally or in the cloud, in their web-based application, including a WebView.
Text-to-speech and speech-to-text for Pi: read replies aloud, dictate prompts (Alt+Z), transcribe audio. OpenRouter, xAI, OpenAI-compatible endpoints or local on-device models (Whisper, Parakeet, Kokoro), with playback on a remote machine over SSH
Connect a web app to any LLM provider through the AI SDK: provider registry, model creation, connection test, a settings store, image generation (OpenRouter, AI Gateway, fal.ai, OpenAI, Google, xAI, Replicate), text-to-speech (AI Gateway, fal.ai, OpenAI,
Experimental speech recognition with independently selectable providers
Record and recognize, and stream speech transcripts through the WebSpeech API.
Headless speech-to-text library (microphone capture + Reson8 realtime streaming) for Puls integrations.
React Native real-time Speech Recognition Library powered by Nitro Modules
Authenticated experimental speech transcription for browser clients
Local SenseVoice ONNX transcription with a managed sherpa-onnx process
Self-hosted LLM gateway and SDK for Node — a LiteLLM-style unified API for 16 providers (Anthropic, OpenAI, Gemini, Mistral, Groq, xAI, DeepSeek, OpenRouter, …) with per-call USD cost tracking, streaming, tool calls, vision, speech-to-text, and built-in O
Mock SpeechRecognition for headless unit tests
Provides S2T support to any Textinput in react native.
Wrapper to transform any textinput into Speech-to-text Texinput
Multi-provider AI agent layer: schema-validated asks, thinking extraction, a model catalog with per-model tuning defaults, token cost accounting for 12 LLM providers, voice agents (TTS/STT) for OpenAI and Gemini, per-subject spend budgets, and (via ./imag
Voice I/O layer for AI coding assistants — local TTS, STT, session booking. MCP server.
TypeScript SDK for the Persona Labs Voice API — agents, STT, TTS, RAG, and voice cloning
Browser-native audio transcription powered by WebGPU Whisper — zero server, fully local.
Google Speech-to-Text integration for IVR Tester
AI multimodal CLI — OpenAI, Gemini, MiniMax, OpenRouter, Leonardo, BytePlus, ElevenLabs, fal.ai, Atlas Cloud, Replicate, Runway, HeyGen, ffmpeg, ImageMagick, doc-to-md
MCP server for AI image / video / 3D / audio (TTS, music, speech-to-text) generation & LLM chat. Use Sora 2, Veo 3, Kling 3, Seedance 2, Flux 2, Nano Banana Pro, Hunyuan 3D, Seed Audio, Suno in Claude Code, Cursor, Codex, Gemini CLI.
High-performance speech-to-text inference addon using NVIDIA Parakeet models for Bare runtime
n8n community nodes for Wiro AI: generate video, images, speech and music, chat with LLMs and create 3D models inside your n8n workflows.
ElevenLabs STT and TTS providers for Cloudflare Agents voice pipeline
14 standalone agent skills for software execution, design, review, context, releases, collaboration, skill development, and speech.