Local text-to-speech with an on-device model, multiple voices and languages, voice cloning and WAV, FLAC, MP3 or Opus output.
Setup
This project documents no single launch command; follow its repository instructions.
LoudKit
loudreader
Related
More- MMobvoi MCPMobvoiOfficialChinaMobvoi's server for its text-to-speech, voice cloning, photo-driven avatar, video dubbing and video translation APIs.Media & Content18 Repository stars
- CCartesia MCP ServerCartesiaOfficialUses the Cartesia voice platform for text-to-speech, voice cloning and related audio tasks.Media & Content15 Repository stars
- AAllVoiceLabAllVoiceLabOfficialGives agents AllVoiceLab voice tools: text to speech, voice cloning and video translation.Media & Content
- AAllVoiceLab MCP ServerAllVoiceLabOfficialChinaOfficial AllVoiceLab server for text to speech, video translation and voice changing through the AllVoiceLab API.Media & Content62 Repository stars
- LListenHub MCP ServerMarsWave AIOfficialChinaOfficial ListenHub server for generating single- or dual-speaker AI podcasts and FlowSpeech audio; requires ListenHub Pro or above.Media & Content16 Repository stars
- DDAISYS MCPDAISYSOfficialGenerates speech audio with the DAISYS platform and plays or stores the results.Media & Content14 Repository stars