⚡ Suzune S1 Flash (82M Flagship Multilingual Edge TTS)

Suzune S1 Flash is an 82-million parameter studio-grade multilingual Text-to-Speech (TTS) foundation model engineered by Sorika Labs.

Designed for real-time edge intelligence, Suzune S1 Flash produces broadcast-quality speech with sub-25ms latency on CPUs, Apple Silicon (M1/M2/M3), and GPUs, featuring native English and Hindi studio voices.

---

🏛️ Base Model & Lineage

Lineage & Attribution: Suzune S1 Flash is developed and released by Sorika Labs. The model architecture is adapted and fine-tuned from the open-source hexgrad/Kokoro-82M and StyleTTS2 foundation (released under Apache 2.0).

Sorika Labs Enhancements & Customizations:

1. Signature Studio Voices: Specially trained and calibrated flagship voices (ira, kian, kagami, phi).
2. Dedicated Hindi Studio Voices: Native Indian speech synthesis with studio voices (ananya, aarav, priya, rohan).
3. Built-in Pure Python Devanagari G2P: Zero-dependency grapheme-to-phoneme engine for pure Hindi Devanagari text (नमस्ते! यह सोज़ूने है...) — works universally across Windows, macOS, Linux, Kaggle, and Colab with zero external C-libraries like espeak-ng.
4. Native ONNX Quantized Engine: Up to 5x faster CPU inference via companion repository sorika-labs/suzune-s1-flash-gguf.
5. Unified SDK: High-level suzune-flash Python runtime with streaming, multi-voice interpolation, and CLI.

---

🚀 Installation

pip install suzune-flash

Or install the master unified framework:

pip install suzune

---

🎙️ Python Quickstart

1. Flagship Studio English Voice (ira / kian)

import suzune_flash

# Load Suzune Flash (default signature voice: 'ira')
tts = suzune_flash.load(voice="ira", device="cpu")

# Synthesize speech
audio, sr = tts.speak(
    "Hello! This is Suzune Flash by Sorika Labs, delivering breathtaking studio quality speech.",
    output="english_studio.wav"
)

2. Native Hindi Studio Voice (ananya / aarav)

Suzune Flash automatically detects Devanagari script and handles complete phonemization seamlessly:

import suzune_flash

# Load native Hindi female voice 'ananya' or male voice 'aarav'
tts = suzune_flash.load(voice="ananya", device="cpu")

hindi_text = "नमस्ते! यह सोज़ूने फ़्लैश है, जिसे सोरिका लैब्स द्वारा विकसित किया गया है। यह तकनीक आपके कंप्यूटर पर सीधे बेहतरीन आवाज़ तैयार करती है।"

audio, sr = tts.speak(hindi_text, output="hindi_studio.wav")

3. Real-Time Streaming for AI Voice Agents

import suzune_flash

tts = suzune_flash.load(voice="kian")

for text_chunk, phonemes, audio_chunk in tts.stream("Streaming live neural speech token by token."):
    play_audio_chunk(audio_chunk)

---

🎭 Available Voices

🌟 Sorika Signature Voices

🇮🇳 Native Hindi Studio Voices

🌍 International Studio Voices

• British English: emma_british_f, george_british_m
• French: chloe_french_f
• Spanish: sofia_spanish_f, mateo_spanish_m
• Italian: giulia_italian_f, marco_italian_m
• Portuguese: camila_portuguese_f, lucas_portuguese_m

---

💻 Terminal Command Line (CLI)

# English
suzune-flash "Hello from Sorika Labs on-device AI!" --voice ira --output output.wav

# Hindi
suzune-flash "नमस्ते! सोरिका लैब्स में आपका स्वागत है।" --voice ananya --output hindi.wav

---

📜 License & Citation

Suzune S1 Flash is open-source software licensed under the Apache 2.0 License.

@misc{sorika2026suzuneflash,
  author = {Sorika Labs},
  title = {Suzune S1 Flash: Flagship Multilingual On-Device Neural Speech Foundation Model},
  year = {2026},
  publisher = {Hugging Face},
  journal = {Hugging Face repository},
  howpublished = {\url{https://huggingface.co/sorika-labs/suzune-s1-flash}}
}