Fix Kokoro TTS integration - correct KPipeline API

- Removed model_path parameter (not supported by kokoro package)
- Removed repo_id parameter (causes KeyError)
- Use default KPipeline initialization with only lang_code
- Kokoro package handles model download automatically

Tested and working:
- American English voices (alloy, af_sarah, am_michael, etc.)
- British English voices (bm_george, bf_emma, etc.)
- Audio generation produces valid MP3 files

🦝 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

README.md

@@ -9,9 +9,11 @@
 **Original Notice:** This software was mostly obsolete and no longer updated by the original maintainer.
 
 **Raccoon Mission:** We're bringing it back to life with:
-- ✅ Working Piper TTS (tts-1) with absolute paths
+- ✅ Working Piper TTS (tts-1) - 55 voices, fast CPU inference
-- ✅ Working XTTS v2 (tts-1-hd) with voice cloning
+- ✅ Working XTTS v2 (tts-1-hd) - 8 voices with cloning capability
-- 🎯 Planning integration of 10+ abandoned TTS engines (Silero, StyleTTS2, Fish Speech, etc.)
+- ✅ Working Silero TTS (tts-1-silero) - 148 voices, 5 languages, CPU-friendly
+- ✅ Working Kokoro TTS (tts-1-kokoro) - 34 voices, lightweight decoder
+- 🎯 Next integrations: StyleTTS2 (best quality), Fish Speech (fast multilingual)
 - 📚 Comprehensive documentation in `docs/`
 - 🛠️ Makefile-driven deployment workflow
 - 🔒 AGPL v3 - keeps TTS libre forever
@@ -30,10 +32,12 @@ An OpenAI API compatible text to speech server.
 Full Compatibility:
 * `tts-1`: `alloy`, `echo`, `fable`, `onyx`, `nova`, and `shimmer` (configurable)
 * `tts-1-hd`:  `alloy`, `echo`, `fable`, `onyx`, `nova`, and `shimmer` (configurable, uses OpenAI samples by default)
+* `tts-1-silero`: `alloy`, `echo`, `fable`, `onyx`, `nova`, and `shimmer` (148 total voices available)
+* `tts-1-kokoro`: `alloy`, `echo`, `fable`, `onyx`, `nova`, and `shimmer` (34 total voices available)
 * response_format: `mp3`, `opus`, `aac`, `flac`, `wav` and `pcm`
 * speed 0.25-4.0 (and more)
 
-Details:
+Available TTS Engines:
 * Model `tts-1` via [piper tts](https://github.com/rhasspy/piper) (very fast, runs on cpu)
   * You can map your own [piper voices](https://rhasspy.github.io/piper-samples/) via the `voice_to_speaker.yaml` configuration file
 * Model `tts-1-hd` via [coqui-ai/TTS](https://github.com/coqui-ai/TTS) xtts_v2 voice cloning (fast, but requires around 4GB GPU VRAM)
@@ -42,9 +46,35 @@ Details:
   * [Custom fine-tuned XTTS model support](#custom-fine-tuned-model-support)
   * Configurable [generation parameters](#generation-parameters)
   * Streamed output while generating
+* Model `tts-1-silero` via [Silero TTS](https://github.com/snakers4/silero-models) (fast CPU inference, actively maintained)
+  * 148 voices across 5 languages (English, Russian, German, Spanish, French)
+  * 48kHz sample rate, excellent quality/speed ratio
+  * No GPU required, real-time capable on CPU
+* Model `tts-1-kokoro` via [Kokoro TTS](https://github.com/hexgrad/kokoro) (lightweight decoder-only architecture)
+  * 34 voices (American and British English)
+  * 82M parameters, fast inference
+  * 24kHz sample rate, Apache 2.0 license
 * Occasionally, certain words or symbols may sound incorrect, you can fix them with regex via `pre_process_map.yaml`
 * Tested with python 3.9-3.11, piper does not install on python 3.12 yet
 
+## High Priority Integration Targets
+
+We're actively working on integrating these state-of-the-art TTS engines:
+
+  1. **StyleTTS2** ⭐⭐⭐⭐⭐
+     - Why: State-of-the-art quality, best prosody and naturalness
+     - License: MIT (permissive)
+     - Challenge: Complex dependencies (phonemizer), slower inference
+     - Priority: HIGH - Best quality available
+
+  2. **Fish Speech** ⭐⭐⭐⭐
+     - Why: Fast, modern, active development, good multilingual support
+     - License: Apache 2.0
+     - Challenge: Newer/less proven
+     - Priority: MEDIUM-HIGH - Good balance of quality and speed
+
+See [docs/MODELS.md](docs/MODELS.md) for the complete integration roadmap and detailed documentation on all supported and planned TTS engines.
+
 
 If you find a better voice match for `tts-1` or `tts-1-hd`, please let me know so I can update the defaults.
 

docs/CLAUDE.md

@@ -122,14 +122,31 @@ uncloseai-speech/
 
 ### Working
 - ✅ Piper TTS (tts-1) - Fast, 100+ voices, absolute paths working
-- ⚠️ XTTS v2 (tts-1-hd) - High quality, needs speaker samples
+- ✅ XTTS v2 (tts-1-hd) - High quality voice cloning, multilingual
+- ✅ Silero TTS (tts-1-silero) - Fast CPU-friendly, 148 voices, 5 languages
+- ✅ Kokoro TTS (tts-1-kokoro) - Lightweight decoder (82M params), 34 voices
 
 ### High Priority Integration
-- 🎯 Silero TTS - Active project, fast, good quality
-- 🎯 StyleTTS2 - Best quality available
-- 🎯 Fish Speech - Modern, multilingual
 
-See `docs/MODELS.md` for complete roadmap.
+  1. **StyleTTS2** ⭐⭐⭐⭐⭐
+     - Why: State-of-the-art quality, best prosody and naturalness
+     - License: MIT (permissive)
+     - Challenge: Complex dependencies (phonemizer), slower inference
+     - Priority: HIGH - Best quality available
+
+  2. **Fish Speech** ⭐⭐⭐⭐
+     - Why: Fast, modern, active development, good multilingual support
+     - License: Apache 2.0
+     - Challenge: Newer/less proven
+     - Priority: MEDIUM-HIGH - Good balance of quality and speed
+
+  3. **Chatterbox** ⭐⭐⭐⭐
+     - Why: Emotion control, 23 languages, zero-shot cloning
+     - License: Apache 2.0
+     - Challenge: Production complexity
+     - Priority: MEDIUM-HIGH - Unique emotion features
+
+See `docs/MODELS.md` for complete roadmap and detailed model documentation.
 
 ## Deployment Workflow
 

speech.py

@@ -175,9 +175,8 @@ class kokoro_wrapper():
     Kokoro is a lightweight decoder-only TTS model (82M params)
     Output: 24kHz audio
     """
-    def __init__(self, lang_code='a', model_path='/app/voices/kokoro'):
+    def __init__(self, lang_code='a'):
         self.lang_code = lang_code
-        self.model_path = model_path
         self.sample_rate = 24000  # Kokoro outputs 24kHz
 
         logger.info(f"Loading Kokoro TTS pipeline for language '{lang_code}'")
@@ -186,7 +185,8 @@ class kokoro_wrapper():
             from kokoro import KPipeline
             import numpy as np
 
-            self.pipeline = KPipeline(lang_code=lang_code, model_path=model_path)
+            # KPipeline will use default repo_id if not specified
+            self.pipeline = KPipeline(lang_code=lang_code)
             logger.info(f"Successfully loaded Kokoro pipeline for lang={lang_code}")
         except Exception as e:
             logger.error(f"Failed to load Kokoro model: {e}")