Microsoft Oxford Speech API, Speech to Text, Text to Speech functionality

Speech APIs enable you to recognize speech and convert it to text using advanced machine learning, and also to convert text to speech.

gTTS (Google Text-to-Speech) is a Ruby library and CLI tool to interface with Google Translate text-to-speech API

speech to text using different services

A comprehensive Ruby client for ElevenLabs covering Text-to-Speech, Speech-to-Speech, Text-to-Dialogue, Sound Effects, and Music generation with voice management, streaming, and built-in cost tracking.

There are good text-to-speech engines for English and classical Latin, but none for medieval Latin. MedievalLatina converts Latin text to a kind of phonetic spelling that can be read by English text-to-speech engines.

Ruby API client for connecting to the Watson Text To Speech (TTS) and Automated Speech Recognition (ASR).

espeak-ruby is small Ruby API for utilizing ‘espeak’ and ‘lame’ to create Text-To-Speech mp3 files

espeak-ruby is small Ruby API for utilizing ‘espeak’ and ‘lame’ to create Text-To-Speech mp3 files

Text-to-speech for Ruby using festivaltts. Provides two new methods for String: to_speech and to_mp3. Requires festivaltts and lame.

Text-to-speech gem based using Azure Cognitive Speech Services.

Text to speech translation. Supports next languages: english, turkey, ukrain, russian. Supports speaker, emotion, speech speed selection. Based on Yandex Speech API (about technology: https://tech.yandex.ru/speechkit/).

ruby interface to the flite text to speech simulator.

Standalone Ruby SDK for AI generation across OpenRouter and Replicate, ElevenLabs speech-to-text, with iterative tool loops and SSE streaming.

Fluentd Output plugin to make a phone call with Twilio VoIP API. Twiml supports text-to-speech with many languages ref. https://www.twilio.com/docs/api/twiml/say

A library for text-to-speech functionality designed for AI applications and natural language processing, with the ability to detect and adapt to the operating system (Windows, macOS, Linux)

Using the Mac system text-to-speech Voice Chapters will create an audio file with bookmarked chapters. It takes a regex capture group to define the chapter markers and the gem will create a m4a/acc file.

OpenAIHelper is a Ruby module designed to enhance productivity by integrating OpenAI's capabilities into local scripts. It allows file uploads, structured output extraction, text-to-speech generation, and automatic audio playback.

Provides Text-to-speech functionality in many languages. Results can be stored into MP3 file. Based on technologies from Google.

Provide a Text-to-Speech service on the service bus