p-groarke / Wsay
Licence: bsd-3-clause
Windows "say"
Stars: ✭ 36
Projects that are alternatives of or similar to Wsay
Voice Builder
An opensource text-to-speech (TTS) voice building tool
Stars: ✭ 362 (+905.56%)
Mutual labels: speech, speech-synthesis, text-to-speech, tts
editts
Official implementation of EdiTTS: Score-based Editing for Controllable Text-to-Speech
Stars: ✭ 74 (+105.56%)
Mutual labels: text-to-speech, speech, tts, speech-synthesis
Fre-GAN-pytorch
Fre-GAN: Adversarial Frequency-consistent Audio Synthesis
Stars: ✭ 73 (+102.78%)
Mutual labels: text-to-speech, speech, tts, speech-synthesis
spokestack-android
Extensible Android mobile voice framework: wakeword, ASR, NLU, and TTS. Easily add voice to any Android app!
Stars: ✭ 52 (+44.44%)
Mutual labels: text-to-speech, speech, tts, speech-synthesis
Lightspeech
LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search
Stars: ✭ 31 (-13.89%)
Mutual labels: speech, speech-synthesis, text-to-speech, tts
Durian
Implementation of "Duration Informed Attention Network for Multimodal Synthesis" (https://arxiv.org/pdf/1909.01700.pdf) paper.
Stars: ✭ 111 (+208.33%)
Mutual labels: speech, speech-synthesis, text-to-speech, tts
ttslearn
ttslearn: Library for Pythonで学ぶ音声合成 (Text-to-speech with Python)
Stars: ✭ 158 (+338.89%)
Mutual labels: text-to-speech, speech, tts, speech-synthesis
Zero-Shot-TTS
Unofficial Implementation of Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration
Stars: ✭ 33 (-8.33%)
Mutual labels: text-to-speech, speech, tts, speech-synthesis
IMS-Toucan
Text-to-Speech Toolkit of the Speech and Language Technologies Group at the University of Stuttgart. Objectives of the development are simplicity, modularity, controllability and multilinguality.
Stars: ✭ 295 (+719.44%)
Mutual labels: text-to-speech, speech, tts, speech-synthesis
Wavegrad
Implementation of Google Brain's WaveGrad high-fidelity vocoder (paper: https://arxiv.org/pdf/2009.00713.pdf). First implementation on GitHub.
Stars: ✭ 245 (+580.56%)
Mutual labels: speech, speech-synthesis, text-to-speech, tts
StyleSpeech
Official implementation of Meta-StyleSpeech and StyleSpeech
Stars: ✭ 161 (+347.22%)
Mutual labels: text-to-speech, speech, tts, speech-synthesis
AdaSpeech
AdaSpeech: Adaptive Text to Speech for Custom Voice
Stars: ✭ 108 (+200%)
Mutual labels: text-to-speech, speech, tts, speech-synthesis
Tts
🤖 💬 Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)
Stars: ✭ 5,427 (+14975%)
Mutual labels: speech, text-to-speech, tts
talkie
Text-to-speech browser extension button. Select text on any web page, and have the computer read it out loud for you by simply clicking the Talkie button.
Stars: ✭ 43 (+19.44%)
Mutual labels: text-to-speech, tts, speech-synthesis
Multilingual text to speech
An implementation of Tacotron 2 that supports multilingual experiments with parameter-sharing, code-switching, and voice cloning.
Stars: ✭ 324 (+800%)
Mutual labels: speech-synthesis, text-to-speech, tts
Tts
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Stars: ✭ 305 (+747.22%)
Mutual labels: speech, text-to-speech, tts
esp32-flite
Speech synthesis running on ESP32 based on Flite engine.
Stars: ✭ 28 (-22.22%)
Mutual labels: text-to-speech, tts, speech-synthesis
Hifi Gan
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
Stars: ✭ 325 (+802.78%)
Mutual labels: speech-synthesis, text-to-speech, tts
Cboard
AAC communication system with text-to-speech for the browser
Stars: ✭ 437 (+1113.89%)
Mutual labels: speech, text-to-speech, tts
Parakeet
PAddle PARAllel text-to-speech toolKIT (supporting WaveFlow, WaveNet, Transformer TTS and Tacotron2)
Stars: ✭ 279 (+675%)
Mutual labels: speech-synthesis, text-to-speech, tts
wsay
Windows equivalent of macOS say
.
Simple command line text-to-speech with easy file output, voice selection and more.
Features
- Output to wav file.
- Select different voices (including new Windows 10 voices).
- Supports speech xml.
- Play text file.
- Interactive mode.
- Supports selecting playback device.
- Supports multiple simultaneous playback devices and file output.
- Full unicode (utf8) support (supports asian languages, Slovak, etc).
- Note : Window's legacy command prompt has some of it's own issues with utf8.
- If you need full unicode support, best to use the new Windows Terminal.
- Supports utf8, utf16le and utf16be text files.
Install Instructions
- Copy
wsay.exe
to a folder you like. - Add that folder to your
Path
environment variable. - Type
wsay
in your command prompt.
Examples
# Say something.
wsay "Hello there."
# Ouput to a wav file. If no filename is entered, outputs to 'out.wav'.
wsay "I can output to a wav file." -o
# List supported voices. Install new Windows voices for more choices.
wsay --list_voices
1 : Microsoft David Desktop - English (United States)
2 : Microsoft Hazel Desktop - English (Great Britain)
3 : Microsoft Zira Desktop - English (United States)
4 : Microsoft David - English (United States)
5 : Microsoft James - English (Australia)
6 : Microsoft Linda - English (Canada)
# etc.
# Use the number provided by '--list_voices' to select a different voice.
wsay "I can use different voices." --voice 6
# Provide an output filename.
wsay "You can name the ouput file." -o my_output_file.wav
# Read text from a text file instead.
wsay -i i_can_read_a_text_file.txt
# In interactive mode, type sentences and press enter for them to be read.
# Use !exit to quit.
# Use !stop to stop speaking.
wsay --interactive
[Info] Type sentences, press enter to speak them.
[Command] '!exit' : Exit interactive mode.
[Command] '!stop' : Interrupt speaking.
# List supported playback devices.
wsay --list_devices
1 : BenQ GW2765 (NVIDIA High Definition Audio)
2 : Speakers (AudioQuest DragonFly Black v1.5)
3 : Digital Audio (S/PDIF) (High Definition Audio Device)
# etc.
# Speak using a non-default playback device.
wsay "I am speaking on another playback device." --playback_device 2
# You can play on multiple devices and save to a file simultaneously.
# Seperate the device numbers with spaces.
# WARNING : The "sentence" must come before the --playback_device (-p) option if it is used!
wsay "Output EVERYWHERE \o/" -p 1 2 -o
# Here, we are using voice 6, reading text from a file and outputting to 'output.wav'.
wsay -v 6 -i mix_and_match_options.txt -o output.wav
# Ouput to multiple devices using interactive mode with voice 5.
wsay -v 5 -I -p 1 2
Help
Usage: wsay "sentence" [options]
Arguments:
"sentence" Sentence to say. You can use speech xml.
Options:
-l, --list_voices Lists available voices.
-v, --voice <value> Choose a different voice. Use the voice number printed using --list_voices.
-i, --input_text <value> Play text from '.txt' file. Supports speech xml.
-o, --output_file <optional> Outputs to wav file. Uses 'out.wav' if no filename is provided.
-I, --interactive Enter interactive mode. Type sentences, they will be spoken when you press enter.
Use 'ctrl+c' or type '!exit' to quit.
-d, --list_devices List detected playback devices.
-p, --playback_device <multiple> Specify a playback device. Use the number provided by --list_devices.
You can provide more than 1 playback device, seperate the numbers with spaces.
You can also mix output to file + playback.
-h, --help Print this help
Build
Install recent conan, cmake and compiler.
Windows
mkdir build && cd build
cmake .. && cmake --build .
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].