feat(#393): implement Kokoro-FastAPI TTS provider with voice catalog
Some checks failed
ci/woodpecker/push/api Pipeline failed

Extract KokoroTtsProvider from factory into its own module with:
- Full voice catalog of 54 built-in voices across 8 languages
- Voice metadata parsing from ID prefix (language, gender, accent)
- Exported constants for supported formats and speed range
- Comprehensive unit tests (48 tests)
- Fix lint/type errors in chatterbox provider (Prettier + unsafe cast)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-02-15 02:27:47 -06:00
parent b5edb4f37e
commit 79b1d81d27
4 changed files with 767 additions and 24 deletions

View File

@@ -15,6 +15,8 @@
import { Logger } from "@nestjs/common";
import { BaseTTSProvider } from "./base-tts.provider";
import { ChatterboxTTSProvider } from "./chatterbox-tts.provider";
import { KokoroTtsProvider } from "./kokoro-tts.provider";
import type { ITTSProvider } from "../interfaces/tts-provider.interface";
import type { SpeechTier, AudioFormat } from "../interfaces/speech-types";
import type { SpeechConfig } from "../speech.config";
@@ -23,28 +25,6 @@ import type { SpeechConfig } from "../speech.config";
// Concrete provider classes
// ==========================================
/**
* Kokoro TTS provider (default tier).
* CPU-based, always available, Apache 2.0 license.
*/
class KokoroProvider extends BaseTTSProvider {
readonly name = "kokoro";
readonly tier: SpeechTier = "default";
}
/**
* Chatterbox TTS provider (premium tier).
* GPU required, voice cloning capable, MIT license.
*/
class ChatterboxProvider extends BaseTTSProvider {
readonly name = "chatterbox";
readonly tier: SpeechTier = "premium";
constructor(baseURL: string) {
super(baseURL, "default", "mp3");
}
}
/**
* Piper TTS provider via OpenedAI Speech (fallback tier).
* Ultra-lightweight CPU, GPL license.
@@ -78,7 +58,7 @@ export function createTTSProviders(config: SpeechConfig): Map<SpeechTier, ITTSPr
// Default tier: Kokoro
if (config.tts.default.enabled) {
const provider = new KokoroProvider(
const provider = new KokoroTtsProvider(
config.tts.default.url,
config.tts.default.voice,
config.tts.default.format as AudioFormat
@@ -89,7 +69,7 @@ export function createTTSProviders(config: SpeechConfig): Map<SpeechTier, ITTSPr
// Premium tier: Chatterbox
if (config.tts.premium.enabled) {
const provider = new ChatterboxProvider(config.tts.premium.url);
const provider = new ChatterboxTTSProvider(config.tts.premium.url);
providers.set("premium", provider);
logger.log(`Registered premium TTS provider: chatterbox at ${config.tts.premium.url}`);
}