From 467b28c797777dab983c847e054ddd3c106c7e40 Mon Sep 17 00:00:00 2001 From: tiyn Date: Sat, 28 Feb 2026 10:10:16 +0100 Subject: [PATCH] added speech recognition and synthesis --- wiki/audio.md | 5 +++++ wiki/speech_recognition_and_synthesis.md | 14 ++++++++++++++ 2 files changed, 19 insertions(+) create mode 100644 wiki/speech_recognition_and_synthesis.md diff --git a/wiki/audio.md b/wiki/audio.md index 8da81e6..0013221 100644 --- a/wiki/audio.md +++ b/wiki/audio.md @@ -15,6 +15,11 @@ For voice based communication, social platforms or messengers navigate to the [section](/wiki/communication.md#social-platforms-messengers-and-voip-services). For headphones navigate to the [headphones article](/wiki/headphones.md): +## Speech Recognition and Synthesis + +[Speech recognition and synthesis](/wiki/speech_recognition_and_synthesis.md) describe processes to +understand and convert spoken language to text aswell as the reverse process. + ## Technical Specifications This section aswell as its subsections address all technical things about audio, like connections, diff --git a/wiki/speech_recognition_and_synthesis.md b/wiki/speech_recognition_and_synthesis.md new file mode 100644 index 0000000..d1ddb32 --- /dev/null +++ b/wiki/speech_recognition_and_synthesis.md @@ -0,0 +1,14 @@ +# Speech Recognition and Synthesis + +Speech recognition describes the process of understanding and interpreting spoken language. +The most common form of this is speech-to-text (STT) programs, that convert spoken language into +text. +On the other hand speech synthesis describes the artificial production of human speech. +A Text-to-speech (TTS) program is one, that converts an input text to speech. + +## Speech-to-Text Programs + +The following is a list of STT programs. + +- [Nerd Dictation](https://github.com/ideasman42/nerd-dictation/) is an offline speech recognition + software for [Linux](/wiki/linux.md)-based operating systems.