kokoro skills

19 tagged kokoro, measured the same way as everything else here.

Browse within: audio 6local-first 6text-to-speech 6asr 5claudecode 5livekit 5

api-contrib

01

remsky/Kokoro-FastAPI

Skill Claude CodeCodex

Contributing to the Kokoro-FastAPI Python API: module layout, endpoint gating pattern, test expectations. Use when adding or changing endpoints, services, or inference code.

5.4k today A 39 tokens original Apache-2.0

readme-benchmarks

02

remsky/Kokoro-FastAPI

Skill Claude CodeCodex

Running the Kokoro-FastAPI benchmark + transcription-roundtrip suites and regenerating the README plots. Use when asked to run/refresh benchmarks, RTF/first-token plots, transcription sanity checks, or the long-form baseline.

5.4k today A 52 tokens original Apache-2.0

web-contrib

03

remsky/Kokoro-FastAPI

Skill Claude CodeCodex

Contributing to the Kokoro-FastAPI web player: vanilla JS constraints, MSE/audio gotchas, unit and e2e test setup. Use when changing anything under web/.

5.4k today A 41 tokens original Apache-2.0

converse

04

mbailey/voicemode

Skill Claude CodeCodex

Start an ongoing voice conversation.

1.3k +1 yesterday A 8 tokens original MIT

impressions

05

mbailey/voicemode

Skill Claude CodeCodex

Add and use custom voices for VoiceMode TTS via local mlx-audio. Use when the user wants to clone a voice, do an impression, add a reference clip, or use voice=" " in converse.

1.3k +1 yesterday A 47 tokens original MIT

voicemode

06

mbailey/voicemode

Skill Claude CodeCodex

Voice interaction for Claude Code. Use when users mention voice mode, speak, talk, converse, voice status, or voice troubleshooting.

1.3k +1 yesterday A 30 tokens original MIT

yoav0gal/agent-voice

Skill Claude CodeCodex

Turn text into speech with Agent Voice and clickable playback controls. Use when the user explicitly requests controlled playback on a compatible desktop renderer.

11 13d ago A 33 tokens original MIT

yoav0gal/agent-voice

Skill Claude CodeCodex

Read an assistant response aloud with clickable Agent Voice playback controls. Use when the user explicitly requests controlled playback on a compatible desktop renderer.

11 13d ago A 30 tokens original MIT

yoav0gal/agent-voice

Skill Claude CodeCodex

Read and embed an assistant response aloud in Codex Desktop, Antigravity App, or OpenCode Desktop.

11 13d ago A 27 tokens original MIT

gen

10

ssrajadh/paperview

Skill Claude CodeCodex

Generate a narrated, animated explainer video from a research paper (PDF) or a codebase/repo. Usage: /ppv:gen .

9 2mo ago A 57 tokens original Apache-2.0

setup

11

ssrajadh/paperview

Skill Claude CodeCodex

One-time toolchain bootstrap for PaperView (Python venv, Remotion deps, local models). Run once before /ppv:gen.

9 2mo ago A 29 tokens original Apache-2.0

vox-voice-alerts

12

kohlhofer/vox

Skill Claude CodeCodex

Speak a short spoken alert to the user via the vox text-to-speech CLI whenever you hand the turn back to them — a task finished (pass or fail, however long it took), you're blocked and need input/a decision/approval, something broke, or you're about to go quiet on a long job. Assume the user is NOT watching the…

5 26d ago A 117 tokens original MIT

tts-setup

13

chendrizzy/claude-tts

Skill Claude CodeCodex

Use for first-run setup of the claude-tts plugin — bootstraps the engine, LLM backend, OS service, and config on a fresh machine. Invoked by /tts:setup.

1 15d ago C 45 tokens original MIT