CLUSTER DESKTOP-SPEECH-VOICES · 37 ENTRIES · EARLIEST ENTRY 2025-11-06

Local voice cloning studios

This cluster consists of desktop applications that run locally to clone voices, convert text to speech, transcribe audio, dub videos, and create audiobooks, often supporting multiple languages and custom voice design. The dated history is too thin to read a shape from, as only one entry predates the index start. Traction leaders include sesly, X-Whisper, and yovoice, based on activity signals.

Entry timeline

ENTRY TIMELINE

NOV 2025: 1AUG 2026: 9SEP 2026: 22OCT 2026: 5
NOV 2025OCT 2026

Members by activity

Activity signals, not revenue.

Build origin · 2 hand-coded · 18 unlabelled

Operator · 11 hobby · 2 indie · 3 open source · 4 unlabelled

Two labels per entry, never collapsed into one: how it was built, and who stands behind it. Counted over the 20 listed below. Unlabelled means nothing has decided yet — not that the answer is small.

  1. 01yovoice830★today—Desktop app that converts text to natural expressive speech locally, with voice cloning, emotion control, and audio project management for narration and voiceovers.
  2. 02persian_tts143★21 days—hobbyOffline Persian text-to-speech web app that reads typed Persian text aloud and clones a voice from a short audio sample.
  3. 03Clonar-voz49★1 mo—hobbyLocal web app that clones a voice from a sample and converts text to speech offline in ten languages.
  4. 04sesly5★14 days—hobbyLocal voice studio app that clones and designs voices, dubs videos, narrates audiobooks, and transcribes speech entirely on the user's own machine.
  5. 05Tixi-Voice2★7 days—hand-codedOffline speech studio for Persian and English that converts text to speech, transcribes speech to text, and clones personal voices.
  6. 06VoxCPM-Studio0★21 daysliveindieDesktop application that converts text to speech, clones voices, and creates custom voices from short audio samples.
  7. 07Lyrebird1★11 days—hobbyDesktop app that clones a voice from a short recording and renders speech audio from text scripts, supporting multiple speakers and sound tags.
  8. 08mynah1★10 days—hobbyLocal voice cloning and text-to-speech tool that generates audio from a script with per-line regeneration.
  9. 09SPP-Audio-Studio1★18 days—hobbyNative macOS app that converts local audio formats, separates vocals from accompaniment, and clones voices using on-device models.
  10. 10Breezetts21★15 days—hobbyDesktop app that turns text into speech with preset voices, voice cloning, and tone control, running locally on a Mac.
  11. 11RVC-Client-Phamu-Edition0★22 daysliveindieStandalone Windows desktop application that changes a user's voice in real time using voice conversion models, with a Japanese UI and drag-and-drop model loading.
  12. 12voicestudio-bin0★18 daysliveopen sourceDesktop application that clones and designs voices, dubs videos, transcribes speech, and creates audiobooks using local AI models.
  13. 13AI-Voice-Cloning1★7 days—hobbyWeb app that clones a voice from a short audio sample and generates speech in that voice from any text, with a personal voice library.
  14. 14sayx1★9 days—hobbymacOS command-line text-to-speech app that converts text into natural neural speech and clones voices on-device.
  15. 15Unlock-TTS-Easy18★2 mo—hobbyWeb application for Thai voice cloning that bundles model and tools for one-command installation and text-to-speech generation.
  16. 16voice-studtio0★8 days—open sourceOpen-source application for voice cloning, voice design, video dubbing, transcription, and audiobook creation in many languages.
  17. 17VoiceLab0★10 days—hand-codedopen sourceDesktop application that clones voices, transcribes audio, dubs videos, and creates audiobooks across many languages.
  18. 18VoiceStudio0★11 days—Desktop app that clones and designs voices, dubs videos, transcribes speech, and creates audiobooks in 646 languages.
  19. 19VoiceStudio0★11 days—AI app that clones voices, creates synthetic speech, and dubs videos across many languages.
  20. 20AISpeech0★3 dayslivehobbyReal-time speech-to-speech app that translates Chinese to English with simultaneous interpretation and cloned voices.