Kokoro is a lightweight open-weight text-to-speech model offering local speech synthesis, multiple languages, voices, and speed control.
Read more
Kokoro is a lightweight open-weight text-to-speech model offering local speech synthesis, multiple languages, voices, and speed control.
Read more
Chatterbox provides multilingual text-to-speech, voice cloning, expressive tags and compact models for local speech synthesis.
Read more
MeloTTS generates multilingual speech with English accents, CPU inference, selectable voices and programmatic text-to-speech.
Read more
Parler-TTS generates natural speech from text with descriptive control of voice, delivery, recording quality and speaker identity.
Read more
Orpheus-FastAPI hosts a text-to-speech API with expressive voices, a web interface, audio stitching and external inference.
Read more
Dia is a text to speech model capable of generating ultra-realistic dialogue in a single pass.
Read more
VoiceGen converts text to speech using online and offline engines through a Qt desktop interface with language selection.
Read more
Speakup provides spoken access to Linux text consoles through kernel screen review, cursor tracking and hardware or software speech.
Read more
RHVoice is a multilingual speech synthesizer. The aim is to give visually impaired people access to a synthesis voice with a screen reader.
Read more
Gespeaker is a GTK-based frontend for eSpeak. Like eSpeak, Gespeaker is free and open source software.
Read more
eSpeak NG (Next Generation) is a continuation of the eSpeak with more feedback from native speakers. It supports more than 100 languages and accents.
Read more
Coqui TTS (TTS) is a library for advanced Text-to-Speech generation. It offers pretrained models in more than 1,100 different languages.
Read more
Tortoise TTS is a multi-voice text-to-speech system trained with an emphasis on quality.
Read more
Festival is a speech synthesis framework with configurable voices, linguistic modules, scripting and several waveform generators.
Read more
CMU Flite is a compact speech synthesis engine for embedded devices and servers, with lightweight voices and C library APIs.
Read more
eSpeak is the original compact formant speech synthesizer, with multilingual voices, phoneme conversion and audio output to WAV files.
Read more
Emacspeak adds speech output, voice highlighting and auditory cues to Emacs for accessible editing, browsing and everyday computing.
Read more
ESPnet supports speech recognition, synthesis, translation, enhancement and diarization with reproducible experiments and pretrained models.
Read more