A unified interface for browser speech synthesis and Eleven Labs voices
Google Cloud Text-to-Speech provider for server-side TTS with speech marks support
OpenClaw MiniMax speech provider plugin
ElevenLabs speech-to-text and text-to-speech provider for @effect-uai/core.
OpenAI speech-to-text and text-to-speech provider for @effect-uai/core.
Inworld speech-to-text and text-to-speech provider for @effect-uai/core.
Fish Audio speech provider for OpenClaw with high-quality TTS, voice cloning, configurable voices, and voice-note friendly output for Telegram and WhatsApp.
OpenClaw speech provider plugin for Cartesia Sonic-2 — high-quality TTS with voice cloning, drop-in for messages.tts and talk surfaces (Telegram voice notes, etc.).
VoxFlow TTS speech provider for OpenClaw — 94+ Chinese voices, multilingual, voice cloning
Volcengine (Doubao) TTS speech provider plugin for OpenClaw — high-quality Chinese voice synthesis
Fish Audio low-latency speech provider for OpenClaw, using WebSocket TTS Live for real-time Discord voice channel conversation.
A standalone speech rule engine for XML structures, based on the original engine from ChromeVox.
The **[Deepgram provider](https://ai-sdk.dev/providers/ai-sdk-providers/deepgram)** for the [AI SDK](https://ai-sdk.dev/docs) contains transcription model support for the Deepgram transcription API and speech model support for the Deepgram text-to-speech
TypeScript definitions for dom-speech-recognition
Local CLI TTS plugin for OpenClaw — use any command-line TTS tool as a speech provider
Microsoft Cognitive Services Speech SDK for JavaScript
Cartesia speech provider integration for the usevoiceai server pipeline.
Speech recognition for your React app
Speech Recognition for React Native Expo projects
Cloud Speech Client Library for Node.js
<div align="center"> <a href="README.md">🇺🇸 English</a> | <a href="README.zh.md">🇨🇳 中文</a> | <a href="README.ja.md">🇯🇵 日本語</a> </div>
n8n node for integrating Palatine Speech API into workflow
Hume text-to-speech provider for the usevoiceai server pipeline.
node-edge-tts is a module that using Microsoft Edge's online TTS (Text-to-Speech) service on the Node.js
Provides Ruby FFI bindings for Pocketsphinx, a lightweight speech recognition engine.
Provides Text-to-speech functionality in many languages. Results can be stored into MP3 file. Based on technologies from Google.
Text-to-speech for Ruby using festivaltts. Provides two new methods for String: to_speech and to_mp3. Requires festivaltts and lame.
Provide a Text-to-Speech service on the service bus
A Ruby gem that provides bindings to the whisper.cpp library for speech transcription.
This is the simple REST client for Cloud Text-to-Speech API V1. Simple REST clients are Ruby client libraries that provide access to Google services via their HTTP REST API endpoints. These libraries are generated and updated automatically based on the discovery documents published by the service, and they handle most concerns such as authentication, pagination, retry, timeouts, and logging. You can use this client to access the Cloud Text-to-Speech API, but note that some services may provide a separate modern client that is easier to use.
This is the simple REST client for Cloud Speech-to-Text API V1. Simple REST clients are Ruby client libraries that provide access to Google services via their HTTP REST API endpoints. These libraries are generated and updated automatically based on the discovery documents published by the service, and they handle most concerns such as authentication, pagination, retry, timeouts, and logging. You can use this client to access the Cloud Speech-to-Text API, but note that some services may provide a separate modern client that is easier to use.
This is the simple REST client for Cloud Text-to-Speech API V1beta1. Simple REST clients are Ruby client libraries that provide access to Google services via their HTTP REST API endpoints. These libraries are generated and updated automatically based on the discovery documents published by the service, and they handle most concerns such as authentication, pagination, retry, timeouts, and logging. You can use this client to access the Cloud Text-to-Speech API, but note that some services may provide a separate modern client that is easier to use.
This is the simple REST client for Cloud Speech-to-Text API V1p1beta1. Simple REST clients are Ruby client libraries that provide access to Google services via their HTTP REST API endpoints. These libraries are generated and updated automatically based on the discovery documents published by the service, and they handle most concerns such as authentication, pagination, retry, timeouts, and logging. You can use this client to access the Cloud Speech-to-Text API, but note that some services may provide a separate modern client that is easier to use.
High-level Ruby bindings to the Stanford CoreNLP package, a set natural language processing tools that provides tokenization, part-of-speech tagging and parsing for several languages, as well as named entity recognition and coreference resolution for English, German, French and other languages.
This is the simple REST client for Cloud Speech-to-Text API V2beta1. Simple REST clients are Ruby client libraries that provide access to Google services via their HTTP REST API endpoints. These libraries are generated and updated automatically based on the discovery documents published by the service, and they handle most concerns such as authentication, pagination, retry, timeouts, and logging. You can use this client to access the Cloud Speech-to-Text API, but note that some services may provide a separate modern client that is easier to use.
High-level Ruby bindings to the Stanford CoreNLP package, a set natural language processing tools that provides tokenization, part-of-speech tagging and parsing for several languages, as well as named entity recognition and coreference resolution for English.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.