Open Source Speech Software

Text to Speech engine for English and many other languages. Compact size with clear but artificial pronunciation. Available as a command-line program with many options, a shared library for Linux, and a Windows SAPI5 version.

Open JTalk is a Japanese text-to-speech synthesis system. This software is released under the Modified BSD license.

hts_engine is software to synthesize speech waveform from HMMs trained by the HMM-based speech synthesis system (HTS). This software is released under the Modified BSD license.

RHVoice is a free and open-source multilingual speech synthesizer. Its developers hope to give more visually impaired people the ability to use a good free synthesis voice reading in their native language with their screen reader. We are especially interested in supporting those languages for which there are currently no good voices that could be used with a screen reader. The creator of RHVoice, Olga Yakovleva, is blind herself. Many of the contributors to the RHVoice project, both programmers and non-programmers, are blind or partially sighted.

WaveSurfer is an open source tool for sound visualization and manipulation. Typical applications are speech/sound analysis and sound annotation/transcription. WaveSurfer may be extended by plug-ins as well as embedded in other applications.

Ever wanted to cut out background noise when talking with others on Skype? Now it's possible! NoiseGator is a light-weight noise gate application that routes audio through an audio input to an audio output. In real-time the audio level is analysed and if the average level is higher than the threshold the audio bypasses as normal. However, if the average level goes below the threshold, the gate closes and the audio is cut. When used with a virtual audio cable it can act as a noise gate for a either a sound input(microphone) or sound output(speakers). Can also be used to gate noise from your own mic or play your microphone through your speakers. REQUIREMENTS: - Java 7 or higher for Windows. - Java 6 or higher for Mac. Java 7 recommended. - A virtual audio cable is required for use with VOIPs: For Windows users I recommend the VB-Cable driver (http://vb-audio.pagesperso-orange.fr/Cable/index.htm). Mac users can use SoundFlower.

eGuideDog project develops free software for the blind. Currently, we focus on WebSpeech, Ekho TTS and WebAnywhere.

Mumble is an open source, low-latency, high quality voice chat software primarily intended for use while gaming. It includes game linking, so voice from other players comes from the direction of their characters, and has echo cancellation so the sound from your loudspeakers won't be audible to other players.

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers. DeepSpeech is an open-source Speech-To-Text engine, using a model trained by machine learning techniques based on Baidu's Deep Speech research paper. Project DeepSpeech uses Google's TensorFlow to make the implementation easier. A pre-trained English model is available for use and can be downloaded following the instructions in the usage docs. If you want to use the pre-trained English model for performing speech-to-text, you can download it (along with other important inference material) from the DeepSpeech releases page.

FreeTTS is a speech synthesis engine written entirely in the Java(tm) programming language. FreeTTS was written by the Sun Microsystems Laboratories Speech Team and is based on CMU's Flite engine. FreeTTS also includes a partial JSAPI 1.0

MMDAgent is the toolkit for building voice interaction systems. Users can design users own dialog scenario, 3D agents, and voices. This software is released under the Modified BSD license.

Coqui STT is a fast, open-source, multi-platform, deep-learning toolkit for training and deploying speech-to-text models. Coqui STT is battle-tested in both production and research. Multiple possible transcripts, each with an associated confidence score. Experience the immediacy of script-to-performance. With Coqui text-to-speech, production times go from months to minutes. With Coqui, the post is a pleasure. Effortlessly clone the voices of your talent and have the clone handle the problems in post. With Coqui, dubbing is a delight. Effortlessly clone the voice of your talent into another language and let the clone do the dub. With text-to-speech, experience the immediacy of script-to-performance. Cast from a wide selection of high-quality, directable, emotive voices or clone a voice to suit your needs. With Coqui text-to-speech, production times go from months to minutes.

Library for performing speech recognition, with support for several engines and APIs, online and offline. Recognize speech input from the microphone, transcribe an audio file, save audio data to an audio file. Show extended recognition results, calibrate the recognizer energy threshold for ambient noise levels (see recognizer_instance.energy_threshold for details). Listening to a microphone in the background, various other useful recognizer features. The easiest way to install this is using pip install SpeechRecognition. The first software requirement is Python 2.6, 2.7, or Python 3.3+. This is required to use the library. PyAudio is required if and only if you want to use microphone input (Microphone). PyAudio version 0.2.11+ is required, as earlier versions have known memory management bugs when recording from microphones in certain situations. To hack on this library, first make sure you have all the requirements listed in the "Requirements" section.

Simple TTS Reader is a small clipboard reader. Simply copy any text, and it will be read aloud. You can choose any installed speech engine, e.g. Microsoft Anna. This text-to-speech utility can also be minimized to tray. Requires .NET Framework 2.0.

TTS is a library for advanced Text-to-Speech generation. It's built on the latest research, was designed to achieve the best trade-off among ease-of-training, speed, and quality. TTS comes with pre-trained models, tools for measuring dataset quality, and is already used in 20+ languages for products and research projects. Released models in PyTorch, Tensorflow and TFLite. Tools to curate Text2Speech datasets underdataset_analysis. Demo server for model testing. Notebooks for extensive model benchmarking. Modular (but not too much) code base enabling easy testing for new ideas. Text2Spec models (Tacotron, Tacotron2, Glow-TTS, SpeedySpeech). Speaker Encoder to compute speaker embeddings efficiently. Vocoder models (MelGAN, Multiband-MelGAN, GAN-TTS, ParallelWaveGAN, WaveGrad, WaveRNN). If you are only interested in synthesizing speech with the released TTS models, installing from PyPI is the easiest option.

SPTK is a suite of speech signal processing tools for UNIX environments, e.g., LPC analysis, PARCOR analysis, LSP analysis, PARCOR synthesis filter, LSP synthesis filter, vector quantization techniques, and other extended versions of them.

Text-to-speech software developed by Electron + vue + ElementUI + js. The high-fidelity and flexible configuration of speech synthesis products opens up the closed loop of human-computer interaction and enables applications to sound realistically. A variety of timbres are available, and functions such as adjusting speech rate, intonation, and volume are provided. Technically, multi-level rhythmic pauses are taken into account to achieve the purpose of natural synthesizing rhythm, and comprehensively use acoustic parameters and linguistic parameters to establish multiple automatic prediction models based on deep learning. Using massive audio data to train the pronunciation model, the synthetic sound is real, full, cadenced, and expressive, and the MOS score has reached the professional level in the industry.

a tool for segmenting, labeling and transcribing speech

Sinsy is an HMM-based singing voice synthesis system. This software is released under the Modified BSD license.

Clavier virtuel et synthétiseur vocal pour les personnes ne pouvant plus parler et ayant du mal à utiliser leurs mains. Virtual keyboard and speech synthetiser for people with reduced mobility and unability to speak. In French and english.

Wrapper for vendors to simplify usage of the Java Speech API (JSR 113). Note that the spec is an untested early access and that there may be changes in the API.

Virtual Hypnotist is a software application that aims to provide a virtual interactive hypnosis session framework, for many uses. It is a rewrite of the Hypnotizer 2000 software. See the readme.txt file for legal info.

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec. Mimi processes 24 kHz audio, down to a 12.5 Hz representation with a bandwidth of 1.1 kbps, in a fully streaming manner (latency of 80ms, the frame size), yet performs better than existing, non-streaming, codecs like SpeechTokenizer (50 Hz, 4kbps), or SemantiCodec (50 Hz, 1.3kbps). Moshi models two streams of audio: one corresponds to Moshi, and the other one to the user. At inference, the stream from the user is taken from the audio input, and the one for Moshi is sampled from the model's output. Along these two audio streams, Moshi predicts text tokens corresponding to its own speech, its inner monologue, which greatly improves the quality of its generation. A small Depth Transformer models inter codebook dependencies for a given time step, while a large, 7B parameter Temporal Transformer models the temporal dependencies.

Open source speech models for Julius speech decoder. Its aim is to give access a wider community of speech recognition enthusiasts to quality models, which they can use in their own projects on different OS platforms (Unix, Windows, etc...) All of the models are based on HTK modelling software and data sets available freely on the Internet.

The Open VXI VoiceXML interpreter is a portable open source library that interprets the VoiceXML dialog markup language. It is designed to serve as a reference for parties interested in understanding how VoiceXML markup might be executed.