diff --git a/README.md b/README.md
index 6bc6165..0fc05b6 100644
--- a/README.md
+++ b/README.md
@@ -1,16 +1,38 @@
# Supertonic β Lightning Fast, On-Device, Accurate TTS
-[](https://huggingface.co/spaces/Supertone/supertonic-3)
-[](https://huggingface.co/Supertone/supertonic-3)
-[](https://github.com/supertone-inc/supertonic/tree/release/supertonic-2)
-[-Demo-lightgrey)](https://huggingface.co/spaces/Supertone/supertonic#interactive-demo)
-[-Models-lightgrey)](https://huggingface.co/Supertone/supertonic)
-
-**Supertonic** is a lightning-fast, on-device text-to-speech system designed for local inference with minimal overhead. Powered by ONNX Runtime, it runs entirely on your deviceβno cloud, no API calls, no privacy concerns.
+[](https://github.com/supertone-inc/supertonic)
+[](https://huggingface.co/Supertone/supertonic-3)
+[](https://huggingface.co/spaces/Supertone/supertonic-3)
+[](https://supertonic3.github.io/)
+[](https://supertonic.supertone.ai/voice_builder)
+[](https://github.com/supertone-inc/supertonic-py)
+[](https://supertone-inc.github.io/supertonic-py/)
+
+
+ 
+
+
+**Supertonic** is a lightning-fast, on-device multilingual text-to-speech system designed for local inference with minimal overhead. Powered by ONNX Runtime, it runs entirely on your deviceβno cloud, no API calls, no privacy concerns.
+
+### β¨ Highlights
+
+- β‘ **Blazingly Fast** β Low-latency, real-time synthesis across desktop, browser, mobile, and edge β fast enough to turn an entire webpage into audio in under a second
+- π **31-Language Multilingual** β Synthesize directly from text across 31 languages, or pass `lang="na"` to let Supertonic process the text language-agnostically when you don't know the input language β no separate language adapters needed
+- πͺΆ **99M-Parameter Open-Weight Model** β A compact, fully open-weight checkpoint β a fraction of the size of 0.7Bβ2B class open TTS systems β for smaller downloads, faster cold starts, and lower memory footprint
+- π± **Edge-Device Ready** β Runs locally on desktop, mobile, browsers, and resource-constrained hardware like Raspberry Pi or e-readers, with zero network dependency, complete privacy, and no GPU required
+- π **44.1kHz High-Quality Audio** β Outputs studio-grade 44.1kHz 16-bit WAV directly, ready for production playback without any external upsampler
+- π **Expression Tags** β 10 inline tags (e.g. ``, ``, ``) bring natural human nuance into generated speech without prompt engineering or reference audio
+- π οΈ **Multi-Runtime SDKs** β Ready-to-use examples through ONNX Runtime across Python, Node.js, Browser (WebGPU), Java, C++, C#, Go, Swift, iOS, Rust, and Flutter
+
+### π Supported Languages (31)
+
+Arabic (`ar`), Bulgarian (`bg`), Croatian (`hr`), Czech (`cs`), Danish (`da`), Dutch (`nl`), English (`en`), Estonian (`et`), Finnish (`fi`), French (`fr`), German (`de`), Greek (`el`), Hindi (`hi`), Hungarian (`hu`), Indonesian (`id`), Italian (`it`), Japanese (`ja`), Korean (`ko`), Latvian (`lv`), Lithuanian (`lt`), Polish (`pl`), Portuguese (`pt`), Romanian (`ro`), Russian (`ru`), Slovak (`sk`), Slovenian (`sl`), Spanish (`es`), Swedish (`sv`), Turkish (`tr`), Ukrainian (`uk`), Vietnamese (`vi`)
+
+> **Not sure which language your text is in?** Pass `lang="na"` and Supertonic will handle the input in a language-agnostic way β no explicit language tag required.
### π° Update News
@@ -22,6 +44,8 @@
- **2025.12.08** - Optimized ONNX models via [OnnxSlim](https://github.com/inisis/OnnxSlim) now available on [Hugging Face Models](https://huggingface.co/Supertone/supertonic)
- **2025.11.24** - Added Flutter SDK support with macOS compatibility
+---
+
## Quick Start
Install the Python SDK and generate speech immediately. On the first run, Supertonic downloads the model assets from Hugging Face automatically.
@@ -40,11 +64,23 @@ tts = TTS(auto_download=True)
style = tts.get_voice_style(voice_name="M1")
-text = "A gentle breeze moved through the open window while everyone listened to the story."
-wav, duration = tts.synthesize(text, voice_style=style, lang="en")
+text = "Supertonic is a lightning fast, on-device TTS system."
+
+wav, duration = tts.synthesize(
+ text=text,
+ lang="en", # Language code (e.g., "en", "ko", "na" for language-agnostic)
+ voice_style=style, # Voice style object
+ total_steps=8, # Quality: 5 (low) to 12 (high), default 8 (medium)
+ speed=1.05, # Speed: 0.7 (slow) to 2.0 (fast)
+)
+# wav: numpy array of shape (1, num_samples,) with dtype=np.float32, sampled at 44100 Hz
+# duration: numpy array of shape (1,) containing the duration of the generated audio in seconds
tts.save_audio(wav, "output.wav")
-print(f"Generated {duration:.2f}s of audio")
+# import soundfile as sf
+# sf.write("output.wav", wav.squeeze(), 44100)
+
+print(f"Generated {duration[0]:.2f}s of audio")
```
## Getting Started
@@ -157,13 +193,14 @@ In Xcode: Targets β ExampleiOSApp β Signing: select your Team, then choose y
+---
### Technical Details
- **Runtime**: ONNX Runtime for cross-platform inference
- **Browser Support**: onnxruntime-web for client-side inference
- **Batch Processing**: Supports batch inference for improved throughput
-- **Audio Output**: Outputs 16-bit WAV files
+- **Audio Output**: Outputs 44.1kHz 16-bit WAV files
## Performance Highlights
@@ -175,7 +212,40 @@ Supertonic 3 is designed for practical on-device inference: compact enough to ru
-Across measured languages, Supertonic 3 stays within a competitive WER/CER range against much larger open TTS models such as VoxCPM2, while preserving a lightweight on-device deployment path. Asterisked languages use CER; the others use WER.
+Evaluated on the **[Minimax-MLS-test](https://huggingface.co/datasets/MiniMaxAI/TTS-MLS-Test) benchmark**, Supertonic 3 stays within a competitive WER/CER range against much larger open TTS models such as VoxCPM2, while preserving a lightweight on-device deployment path. Asterisked languages (`*`) use CER; the others use WER.
+
+
+π Detailed per-language results (WER / CER*)
+
+
+
+| Lang | VoxCPM2 | OmniVoice | Qwen3-TTS | Supertonic 2 | **Supertonic 3** |
+|---|:---:|:---:|:---:|:---:|:---:|
+| arabic\* | 4.14 | 1.74 | β | β | **2.14** |
+| czech | 23.73 | 2.40 | β | β | **3.02** |
+| dutch | 0.84 | 0.77 | β | β | **1.47** |
+| english | 2.11 | 2.02 | 2.25 | 2.52 | **2.06** |
+| finnish | 2.29 | 3.94 | β | β | **5.40** |
+| french | 4.41 | 4.74 | 3.82 | 5.09 | **4.89** |
+| german | 0.85 | 0.96 | 0.52 | β | **0.86** |
+| greek | 3.22 | 2.96 | β | β | **3.54** |
+| hindi\* | 5.85 | 5.14 | β | β | **5.34** |
+| indonesian | 1.25 | 1.67 | β | β | **1.34** |
+| italian | 1.74 | 1.29 | 1.40 | β | **1.75** |
+| japanese\* | 3.35 | 3.81 | 3.67 | β | **4.61** |
+| korean\* | 4.70 | 3.22 | 4.07 | 3.65 | **3.26** |
+| polish | 1.30 | 0.64 | β | β | **1.63** |
+| portuguese | 1.74 | 1.40 | 1.21 | 1.52 | **2.48** |
+| romanian | 22.39 | 2.29 | β | β | **2.19** |
+| russian | 3.31 | 4.53 | 4.48 | β | **3.99** |
+| spanish | 1.34 | 0.99 | 0.75 | 1.81 | **1.13** |
+| turkish | 0.88 | 2.18 | β | β | **1.00** |
+| ukrainian | 5.85 | 0.71 | β | β | **1.23** |
+| vietnamese | 1.48 | 0.79 | β | β | **4.49** |
+
+> Lower is better. `*` indicates CER (character error rate); all other rows use WER (word error rate). Dashes (`β`) indicate the model does not officially support the language or no result is available.
+
+
### Supertonic 2 to Supertonic 3
@@ -223,29 +293,7 @@ Turns any webpage into audio in under one second, delivering lightning-fast, on-
https://github.com/user-attachments/assets/cc8a45fc-5c3e-4b2c-8439-a14c3d00d91c
-## Why Supertonic?
-
-- **Blazingly Fast**: Optimized for low-latency, on-device speech generation across desktop, browser, and edge deployments
-- **Lightweight**: Compact ONNX assets designed for efficient local execution
-- **On-Device Capable**: Complete privacy and zero network dependency
-- **Accurate Reading**: Improved reading stability with fewer repeat and skip failures
-- **Expressive Tags**: Supports simple expression tags such as ``, ``, and ``
-- **Flexible Deployment**: Ready-to-use examples across Python, JavaScript, browser, mobile, and native runtimes
-
-## Language Support
-
-Supertonic 3 supports 31 languages:
-
-| Code | Language | Code | Language | Code | Language | Code | Language |
-|------|----------|------|----------|------|----------|------|----------|
-| `en` | English | `ko` | Korean | `ja` | Japanese | `ar` | Arabic |
-| `bg` | Bulgarian | `cs` | Czech | `da` | Danish | `de` | German |
-| `el` | Greek | `es` | Spanish | `et` | Estonian | `fi` | Finnish |
-| `fr` | French | `hi` | Hindi | `hr` | Croatian | `hu` | Hungarian |
-| `id` | Indonesian | `it` | Italian | `lt` | Lithuanian | `lv` | Latvian |
-| `nl` | Dutch | `pl` | Polish | `pt` | Portuguese | `ro` | Romanian |
-| `ru` | Russian | `sk` | Slovak | `sl` | Slovenian | `sv` | Swedish |
-| `tr` | Turkish | `uk` | Ukrainian | `vi` | Vietnamese | | |
+## Programming Language Support
We provide ready-to-use TTS inference examples across multiple ecosystems:
@@ -373,6 +421,19 @@ Supertonic is designed to handle complex, real-world text inputs that contain na
| **Transformers.js** | Hugging Face's JS library with Supertonic support | [GitHub PR](https://github.com/huggingface/transformers.js/pull/1459) Β· [Demo](https://huggingface.co/spaces/webml-community/Supertonic-TTS-WebGPU) |
| **Pinokio** | 1-click localhost cloud for Mac, Windows, and Linux | [Pinokio](https://pinokio.co/) Β· [GitHub](https://github.com/SUP3RMASS1VE/SuperTonic-TTS) |
+## Models & Versions
+
+| | **Supertonic 3** | Supertonic 2 | Supertonic 1 |
+|---|:---:|:---:|:---:|
+| **Status** | π’ Latest | Stable | Legacy |
+| **Parameters** | ~99M | ~66M | ~66M |
+| **Languages** | 31 | 5 | 1 (en) |
+| **Expression Tags** | β
10 tags | β | β |
+| **Code** | [main](https://github.com/supertone-inc/supertonic) | [release/supertonic-2](https://github.com/supertone-inc/supertonic/tree/release/supertonic-2) | β |
+| **Weights** | [π€ HF](https://huggingface.co/Supertone/supertonic-3) | [π€ HF](https://huggingface.co/Supertone/supertonic-2) | [π€ HF](https://huggingface.co/Supertone/supertonic) |
+| **Interactive Demo** | [π€ Space](https://huggingface.co/spaces/Supertone/supertonic-3) | [π€ Space](https://huggingface.co/spaces/Supertone/supertonic-2) | [π€ Space](https://huggingface.co/spaces/Supertone/supertonic#interactive-demo) |
+| **Audio Samples** | [DemoPage](https://supertonic3.github.io/) | β | [DemoPage](https://supertonictts.github.io/) |
+
## Citation
The following papers describe the core technologies used in Supertonic. If you use this system in your research or find these techniques useful, please consider citing the relevant papers:
diff --git a/cpp/helper.cpp b/cpp/helper.cpp
index 5933c9e..1545c99 100644
--- a/cpp/helper.cpp
+++ b/cpp/helper.cpp
@@ -12,7 +12,7 @@
using json = nlohmann::json;
// Available languages for multilingual TTS
-const std::vector AVAILABLE_LANGS = {"en", "ko", "ja", "ar", "bg", "cs", "da", "de", "el", "es", "et", "fi", "fr", "hi", "hr", "hu", "id", "it", "lt", "lv", "nl", "pl", "pt", "ro", "ru", "sk", "sl", "sv", "tr", "uk", "vi"};
+const std::vector AVAILABLE_LANGS = {"en", "ko", "ja", "ar", "bg", "cs", "da", "de", "el", "es", "et", "fi", "fr", "hi", "hr", "hu", "id", "it", "lt", "lv", "nl", "pl", "pt", "ro", "ru", "sk", "sl", "sv", "tr", "uk", "vi", "na"};
// Global tensor buffers for memory management
static std::vector> g_tensor_buffers_float;
diff --git a/csharp/Helper.cs b/csharp/Helper.cs
index 72867b9..3569ea1 100644
--- a/csharp/Helper.cs
+++ b/csharp/Helper.cs
@@ -13,7 +13,7 @@ namespace Supertonic
// Available languages for multilingual TTS
public static class Languages
{
- public static readonly string[] Available = { "en", "ko", "ja", "ar", "bg", "cs", "da", "de", "el", "es", "et", "fi", "fr", "hi", "hr", "hu", "id", "it", "lt", "lv", "nl", "pl", "pt", "ro", "ru", "sk", "sl", "sv", "tr", "uk", "vi" };
+ public static readonly string[] Available = { "en", "ko", "ja", "ar", "bg", "cs", "da", "de", "el", "es", "et", "fi", "fr", "hi", "hr", "hu", "id", "it", "lt", "lv", "nl", "pl", "pt", "ro", "ru", "sk", "sl", "sv", "tr", "uk", "vi", "na" };
}
// ============================================================================
diff --git a/flutter/lib/helper.dart b/flutter/lib/helper.dart
index ed554b6..734380e 100644
--- a/flutter/lib/helper.dart
+++ b/flutter/lib/helper.dart
@@ -12,7 +12,7 @@ final logger = Logger(
);
// Available languages for multilingual TTS
-const List availableLangs = ['en', 'ko', 'ja', 'ar', 'bg', 'cs', 'da', 'de', 'el', 'es', 'et', 'fi', 'fr', 'hi', 'hr', 'hu', 'id', 'it', 'lt', 'lv', 'nl', 'pl', 'pt', 'ro', 'ru', 'sk', 'sl', 'sv', 'tr', 'uk', 'vi'];
+const List availableLangs = ['en', 'ko', 'ja', 'ar', 'bg', 'cs', 'da', 'de', 'el', 'es', 'et', 'fi', 'fr', 'hi', 'hr', 'hu', 'id', 'it', 'lt', 'lv', 'nl', 'pl', 'pt', 'ro', 'ru', 'sk', 'sl', 'sv', 'tr', 'uk', 'vi', 'na'];
bool isValidLang(String lang) => availableLangs.contains(lang);
diff --git a/go/helper.go b/go/helper.go
index f3c1d97..f456469 100644
--- a/go/helper.go
+++ b/go/helper.go
@@ -19,7 +19,7 @@ import (
)
// Available languages for multilingual TTS
-var AvailableLangs = []string{"en", "ko", "ja", "ar", "bg", "cs", "da", "de", "el", "es", "et", "fi", "fr", "hi", "hr", "hu", "id", "it", "lt", "lv", "nl", "pl", "pt", "ro", "ru", "sk", "sl", "sv", "tr", "uk", "vi"}
+var AvailableLangs = []string{"en", "ko", "ja", "ar", "bg", "cs", "da", "de", "el", "es", "et", "fi", "fr", "hi", "hr", "hu", "id", "it", "lt", "lv", "nl", "pl", "pt", "ro", "ru", "sk", "sl", "sv", "tr", "uk", "vi", "na"}
// Config structures
type SpecProcessorConfig struct {
diff --git a/ios/ExampleiOSApp/TTSService.swift b/ios/ExampleiOSApp/TTSService.swift
index 58a25b8..65c9096 100644
--- a/ios/ExampleiOSApp/TTSService.swift
+++ b/ios/ExampleiOSApp/TTSService.swift
@@ -35,7 +35,8 @@ final class TTSService {
case tr = "tr"
case uk = "uk"
case vi = "vi"
-
+ case na = "na"
+
var displayName: String {
switch self {
case .en: return "English"
@@ -69,6 +70,7 @@ final class TTSService {
case .tr: return "Turkish"
case .uk: return "Ukrainian"
case .vi: return "Vietnamese"
+ case .na: return "Auto (language-agnostic)"
}
}
}
diff --git a/java/Helper.java b/java/Helper.java
index 0f1c978..e09cbad 100644
--- a/java/Helper.java
+++ b/java/Helper.java
@@ -22,7 +22,7 @@ import java.util.regex.Matcher;
* Available languages for multilingual TTS
*/
class Languages {
- public static final List AVAILABLE = Arrays.asList("en", "ko", "ja", "ar", "bg", "cs", "da", "de", "el", "es", "et", "fi", "fr", "hi", "hr", "hu", "id", "it", "lt", "lv", "nl", "pl", "pt", "ro", "ru", "sk", "sl", "sv", "tr", "uk", "vi");
+ public static final List AVAILABLE = Arrays.asList("en", "ko", "ja", "ar", "bg", "cs", "da", "de", "el", "es", "et", "fi", "fr", "hi", "hr", "hu", "id", "it", "lt", "lv", "nl", "pl", "pt", "ro", "ru", "sk", "sl", "sv", "tr", "uk", "vi", "na");
public static boolean isValid(String lang) {
return AVAILABLE.contains(lang);
diff --git a/nodejs/helper.js b/nodejs/helper.js
index 2bfedfc..a455e76 100644
--- a/nodejs/helper.js
+++ b/nodejs/helper.js
@@ -5,7 +5,7 @@ import * as ort from 'onnxruntime-node';
const __filename = fileURLToPath(import.meta.url);
-const AVAILABLE_LANGS = ["en", "ko", "ja", "ar", "bg", "cs", "da", "de", "el", "es", "et", "fi", "fr", "hi", "hr", "hu", "id", "it", "lt", "lv", "nl", "pl", "pt", "ro", "ru", "sk", "sl", "sv", "tr", "uk", "vi"];
+const AVAILABLE_LANGS = ["en", "ko", "ja", "ar", "bg", "cs", "da", "de", "el", "es", "et", "fi", "fr", "hi", "hr", "hu", "id", "it", "lt", "lv", "nl", "pl", "pt", "ro", "ru", "sk", "sl", "sv", "tr", "uk", "vi", "na"];
/**
* Unicode text processor
diff --git a/py/example_pypi.py b/py/example_pypi.py
index 26f091f..d1c1c6f 100644
--- a/py/example_pypi.py
+++ b/py/example_pypi.py
@@ -13,4 +13,5 @@ wav, duration = tts.synthesize(text, voice_style=style)
# duration: np.ndarray, shape = (1,)
# Save to file
-tts.save_audio(wav, "results/example_pypi.wav")
\ No newline at end of file
+tts.save_audio(wav, "results/example_pypi.wav")
+print(f"Generated {duration[0]:.2f}s of audio")
\ No newline at end of file
diff --git a/py/helper.py b/py/helper.py
index c0f12a3..ff9e4da 100644
--- a/py/helper.py
+++ b/py/helper.py
@@ -10,7 +10,7 @@ import onnxruntime as ort
import re
-AVAILABLE_LANGS = ["en", "ko", "ja", "ar", "bg", "cs", "da", "de", "el", "es", "et", "fi", "fr", "hi", "hr", "hu", "id", "it", "lt", "lv", "nl", "pl", "pt", "ro", "ru", "sk", "sl", "sv", "tr", "uk", "vi"]
+AVAILABLE_LANGS = ["en", "ko", "ja", "ar", "bg", "cs", "da", "de", "el", "es", "et", "fi", "fr", "hi", "hr", "hu", "id", "it", "lt", "lv", "nl", "pl", "pt", "ro", "ru", "sk", "sl", "sv", "tr", "uk", "vi", "na"]
class UnicodeProcessor:
diff --git a/rust/src/helper.rs b/rust/src/helper.rs
index 032541f..8f3acbd 100644
--- a/rust/src/helper.rs
+++ b/rust/src/helper.rs
@@ -15,7 +15,7 @@ use rand_distr::{Distribution, Normal};
use regex::Regex;
// Available languages for multilingual TTS
-pub const AVAILABLE_LANGS: &[&str] = &["en", "ko", "ja", "ar", "bg", "cs", "da", "de", "el", "es", "et", "fi", "fr", "hi", "hr", "hu", "id", "it", "lt", "lv", "nl", "pl", "pt", "ro", "ru", "sk", "sl", "sv", "tr", "uk", "vi"];
+pub const AVAILABLE_LANGS: &[&str] = &["en", "ko", "ja", "ar", "bg", "cs", "da", "de", "el", "es", "et", "fi", "fr", "hi", "hr", "hu", "id", "it", "lt", "lv", "nl", "pl", "pt", "ro", "ru", "sk", "sl", "sv", "tr", "uk", "vi", "na"];
pub fn is_valid_lang(lang: &str) -> bool {
AVAILABLE_LANGS.contains(&lang)
diff --git a/swift/Sources/Helper.swift b/swift/Sources/Helper.swift
index cc551ee..f9f4260 100644
--- a/swift/Sources/Helper.swift
+++ b/swift/Sources/Helper.swift
@@ -4,7 +4,7 @@ import OnnxRuntimeBindings
// MARK: - Available Languages
-let AVAILABLE_LANGS = ["en", "ko", "ja", "ar", "bg", "cs", "da", "de", "el", "es", "et", "fi", "fr", "hi", "hr", "hu", "id", "it", "lt", "lv", "nl", "pl", "pt", "ro", "ru", "sk", "sl", "sv", "tr", "uk", "vi"]
+let AVAILABLE_LANGS = ["en", "ko", "ja", "ar", "bg", "cs", "da", "de", "el", "es", "et", "fi", "fr", "hi", "hr", "hu", "id", "it", "lt", "lv", "nl", "pl", "pt", "ro", "ru", "sk", "sl", "sv", "tr", "uk", "vi", "na"]
func isValidLang(_ lang: String) -> Bool {
return AVAILABLE_LANGS.contains(lang)
diff --git a/web/helper.js b/web/helper.js
index 3513e8d..8e16388 100644
--- a/web/helper.js
+++ b/web/helper.js
@@ -1,7 +1,7 @@
import * as ort from 'onnxruntime-web';
// Available languages for multilingual TTS
-export const AVAILABLE_LANGS = ['en', 'ko', 'ja', 'ar', 'bg', 'cs', 'da', 'de', 'el', 'es', 'et', 'fi', 'fr', 'hi', 'hr', 'hu', 'id', 'it', 'lt', 'lv', 'nl', 'pl', 'pt', 'ro', 'ru', 'sk', 'sl', 'sv', 'tr', 'uk', 'vi'];
+export const AVAILABLE_LANGS = ['en', 'ko', 'ja', 'ar', 'bg', 'cs', 'da', 'de', 'el', 'es', 'et', 'fi', 'fr', 'hi', 'hr', 'hu', 'id', 'it', 'lt', 'lv', 'nl', 'pl', 'pt', 'ro', 'ru', 'sk', 'sl', 'sv', 'tr', 'uk', 'vi', 'na'];
export function isValidLang(lang) {
return AVAILABLE_LANGS.includes(lang);