Skip to content

支持实时流式输出和声音克隆功能。我们只需提供一段简短的音频样本,即可快速复刻出目标音色。A TTS that fits in your CPU (and pocket)

Python · active 2026-01-132026-08-08 (UTC)

Partial coverage11,342 / 12,163 hourly files (93%) · 2 absent upstream · 818 failed, retryable2025-03-222026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
1.8K
Pushes
62
Pull requests
38
Issues
39
Stars
1.3K
Forks
145

Activity over time

Daily event counts in the loaded window

Line chart, 208 days from 2026-01-13 to 2026-08-08. Pushes: 62 total, peak 8 in a day. Pull requests: 38 total, peak 7 in a day. Issues: 39 total, peak 4 in a day. Comments: 146 total, peak 11 in a day. Stars: 1,322 total, peak 176 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

Recent activity

Latest issues, pull requests and releases

  • Issue comment#127handpickencounter2026-05-27 02:14
    [Feature Request] Kokoro-style Voice Mixing
  • Issue#196Daveydrz2026-05-24 22:07
    Polish language
  • Pull request#193slaughters85j2026-05-20 23:12
  • Issue#192slaughters85j2026-05-18 23:44
    Native macOS app now available - Python-free, on-device TTS via Core ML & MLX
  • Issue comment#115marafx2026-05-11 00:06
    Prosody and audio quality worse than Kokoro
  • Issue comment#185Abhishek81082026-05-10 10:21
    Feature request: support saving/loading quantized language model
  • Issue comment#174shadowofsoul2026-05-08 22:22
    Generating text in Spanish gives truncated or mangled output.
  • Issue comment#178gabrieldemarmiesse2026-05-04 07:33
    Cannot clone voice from wav file when generating output
  • Pull request#176gabrieldemarmiesse2026-05-02 16:05
  • Pull request#172memchr2026-04-27 11:12
  • Issue comment#118Shackless2026-04-25 10:27
    Official announcement: More languages for Pocket-TTS
  • Issue comment#162gabrieldemarmiesse2026-04-19 08:55
    Pocket tokenizer incorrectly splits decimals
  • Issue comment#161gabrieldemarmiesse2026-04-19 08:51
    The project actually doesn't support multi-language
  • Issue comment#155benterris2026-04-09 07:38
    Super secret feature not really secret
  • Issue#156markd892026-04-05 20:05
    New Project using Pocket TTS: FrontPocket
  • Issue comment#7thataboy2026-04-01 21:07
    Add quantization to run the computation in int8
  • Pull request#154jspaulsen2026-03-31 20:47
  • Issue comment#118escomputers2026-03-30 21:47
    Official announcement: More languages for Pocket-TTS
  • Issue comment#143gabrieldemarmiesse2026-03-24 10:50
    Split long sentences on commas to prevent skipped words
  • Issue comment#147gabrieldemarmiesse2026-03-24 10:28
    Add int8 dynamic quantization support
  • Issue comment#147nabil-tazi2026-03-24 00:17
    Add int8 dynamic quantization support
  • Issue comment#121RunjiaChen2026-03-22 10:58
    Add the possibility to read the input text from stdin as it comes out
  • Issue comment#146teddybear0822026-03-19 01:44
    Pocket-TTS add-on for NVDA screenreader
  • Issue comment#66damageboy2026-03-16 00:18
    Word-level timestamps
  • Issue comment#118Zig-VS-TypeScript-VS2026-03-15 19:13
    Official announcement: More languages for Pocket-TTS

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1,322 stars here means stars gained during the window, not the repo's star count.