feat(cli): add tts command for local text-to-speech via Kokoro-82M (#201)

* feat(cli): add `tts` command for local text-to-speech via Kokoro-82M

Adds `hyperframes tts` — generate speech audio locally using Kokoro-82M
(ONNX), no API key needed. Mirrors the transcribe command architecture.

- New command: `hyperframes tts "text" --voice af_heart --output speech.wav`
- 54 voices across 8 languages, ~5x realtime on CPU
- Auto-downloads model (~311 MB) + voices (~27 MB) to ~/.cache/hyperframes/tts/
- Requires Python 3.8+ with kokoro-onnx installed
- Extracted shared `downloadFile` utility from whisper/manager.ts with
  atomic .tmp→rename to prevent partial download corruption
- Added hyperframes-tts skill with voice selection guide
- Updated CLAUDE.md with TTS docs, voice table, and skill reference

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* docs(tts): improve skill per skill-creator guidelines

- Move trigger info from body to frontmatter description
- Remove `trigger` field (not a valid frontmatter field)
- Remove CLI flag docs Claude can derive from --help
- Remove redundant voice tables (keep content-to-voice mapping)
- Fix composition audio example to use actual <audio> element pattern
- Keep non-obvious workflows: TTS+transcribe for captions, long scripts

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* docs(tts): add guidance for using external TTS sources

Help users understand when to use cloud TTS (voice cloning, broader
languages, higher quality) vs the built-in Kokoro model, and how
external audio integrates into the same composition workflow.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* docs(tts): prioritize HeyGen API as recommended cloud TTS

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* docs(tts): remove external TTS section for now

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(tts): set required: false on input arg so --list works standalone

Citty treats positional args as required by default unless explicitly
set to required: false. Without this, `hyperframes tts --list` fails
with "Missing required positional argument".

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat(tts): add --help examples and fix required:false for --list

Add examples section to `tts --help` matching the pattern from other
commands (transcribe, render, etc.). Fix citty positional arg requiring
explicit `required: false` for --list to work standalone.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* docs: add CLI command checklist to CLAUDE.md

Ensure new commands always get --help examples in help.ts.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
James Russo
2026-04-02 14:09:25 -07:00
committed by GitHub
co-authored by Claude Opus 4.6
parent cb0b17062a
commit 7389c0c89b
10 changed files with 638 additions and 29 deletions
+99
View File
@@ -0,0 +1,99 @@
import { existsSync, mkdirSync } from "node:fs";
import { homedir } from "node:os";
import { join } from "node:path";
import { downloadFile } from "../utils/download.js";
const CACHE_DIR = join(homedir(), ".cache", "hyperframes", "tts");
const MODELS_DIR = join(CACHE_DIR, "models");
const VOICES_DIR = join(CACHE_DIR, "voices");
const DEFAULT_MODEL = "kokoro-v1.0";
const MODEL_URLS: Record<string, string> = {
"kokoro-v1.0":
"https://github.com/thewh1teagle/kokoro-onnx/releases/download/model-files-v1.0/kokoro-v1.0.onnx",
};
const VOICES_URL =
"https://github.com/thewh1teagle/kokoro-onnx/releases/download/model-files-v1.0/voices-v1.0.bin";
// ---------------------------------------------------------------------------
// Voices — Kokoro ships 54 voices across 8 languages. We expose a curated
// default set and allow users to specify any valid Kokoro voice ID.
// ---------------------------------------------------------------------------
export interface VoiceInfo {
id: string;
label: string;
language: string;
gender: "female" | "male";
}
export const BUNDLED_VOICES: VoiceInfo[] = [
{ id: "af_heart", label: "Heart", language: "en-US", gender: "female" },
{ id: "af_nova", label: "Nova", language: "en-US", gender: "female" },
{ id: "af_sky", label: "Sky", language: "en-US", gender: "female" },
{ id: "am_adam", label: "Adam", language: "en-US", gender: "male" },
{ id: "am_michael", label: "Michael", language: "en-US", gender: "male" },
{ id: "bf_emma", label: "Emma", language: "en-GB", gender: "female" },
{ id: "bf_isabella", label: "Isabella", language: "en-GB", gender: "female" },
{ id: "bm_george", label: "George", language: "en-GB", gender: "male" },
];
export const DEFAULT_VOICE = "af_heart";
// ---------------------------------------------------------------------------
// Public API
// ---------------------------------------------------------------------------
/**
* Ensure the Kokoro ONNX model is downloaded and cached.
* Returns the path to the .onnx model file.
*/
export async function ensureModel(
model: string = DEFAULT_MODEL,
options?: { onProgress?: (message: string) => void },
): Promise<string> {
const modelPath = join(MODELS_DIR, `${model}.onnx`);
if (existsSync(modelPath)) return modelPath;
const url = MODEL_URLS[model];
if (!url) {
throw new Error(
`Unknown TTS model: ${model}. Available: ${Object.keys(MODEL_URLS).join(", ")}`,
);
}
mkdirSync(MODELS_DIR, { recursive: true });
options?.onProgress?.(`Downloading TTS model ${model} (~311 MB)...`);
await downloadFile(url, modelPath);
if (!existsSync(modelPath)) {
throw new Error(`Model download failed: ${model}`);
}
return modelPath;
}
/**
* Ensure the Kokoro voices bundle is downloaded and cached.
* Returns the path to the voices .bin file.
*/
export async function ensureVoices(options?: {
onProgress?: (message: string) => void;
}): Promise<string> {
const voicesPath = join(VOICES_DIR, "voices-v1.0.bin");
if (existsSync(voicesPath)) return voicesPath;
mkdirSync(VOICES_DIR, { recursive: true });
options?.onProgress?.("Downloading voice data (~27 MB)...");
await downloadFile(VOICES_URL, voicesPath);
if (!existsSync(voicesPath)) {
throw new Error("Voice data download failed");
}
return voicesPath;
}
export { MODELS_DIR, VOICES_DIR, DEFAULT_MODEL };