--- license: apache-2.0 base_model: Supertone/supertonic-3 pipeline_tag: text-to-speech library_name: onnx tags: - text-to-speech - tts - supertonic - onnx - cpu - cuda - offline language: - en - ru - de - fr - es - pt - it - nl - pl - uk - cs - sk - sl - hr - bg - ro - hu - el - tr - ar - hi - id - vi - ja - ko - sv - da - fi - et - lv - lt --- # SuperClonica — a faster, cleaner engine for Supertonic 3 **SuperClonica** runs the [Supertonic 3](https://huggingface.co/Supertone/supertonic-3) text-to-speech model with the same voices and the same seeds — and gets more out of it: **1.6–1.7× faster** on CPU and GPU, speech that starts after **0.08 s instead of half a second**, no background noise in pauses, far fewer cut-off endings and numbers spelled out correctly in 27 languages. It works offline on your own computer and reads any Supertonic 3 voice-style JSON file. The original Supertonic repository was [archived](https://github.com/supertone-oss-archive/supertonic) in September 2026 and gets no more updates; SuperClonica runs the same Supertonic 3 model and is still developed. 🗣️ **Try it:** [online demo with free voices](https://huggingface.co/spaces/Superclonica/superclonica-tts) · ⬇️ [free voices on GitHub](https://github.com/superclonica/supertonic-voices) · 🎙️ [170+ voices in the marketplace](https://superclonica.com/en/explore?utm_source=huggingface&utm_medium=model) | | | |---|---| | Model | Supertonic 3 (about 99M parameters, ONNX), unchanged | | Languages | 31: en, ru, de, fr, es, pt, it, nl, pl, uk, cs, sk, sl, hr, bg, ro, hu, el, tr, ar, hi, id, vi, ja, ko, sv, da, fi, et, lv, lt | | Voices | any Supertonic 3 voice-style JSON (`style_ttl` + `style_dp`), including Supertone's own M1–M5 and F1–F5 | | Runs on | CPU (Windows, macOS, Linux) or NVIDIA GPU (Windows, Linux x86-64) | | Install | `pip install superclonica-cpu` or `pip install superclonica-gpu-cuda`, or the Docker image | | Output | 44.1 kHz mono WAV | ## Quick start ```bash python -m pip install superclonica-cpu # any CPU, Python 3.10+ # or, for an NVIDIA GPU (Python 3.11+; pip brings CUDA and cuDNN): python -m pip install superclonica-gpu-cuda ``` Install only one of the two packages. The Supertonic 3 model (about 400 MB) downloads on the first run. ```python from superclonica import Superclonica tts = Superclonica() # GPU if available, otherwise CPU; create it once and keep it audio, sample_rate = tts.synthesize( "Hello! Your new voice is ready.", voice="ciri.json", lang="en", seed=7 ) tts.save("hello.wav", audio) ``` Command line: ```bash superclonica --text "Hello! Your new voice is ready." --voice ciri.json --lang en --output hello.wav ``` HTTP server in Docker ([superclonica/superclonica](https://hub.docker.com/r/superclonica/superclonica)): ```bash docker run -d -p 8000:8000 -v superclonica-models:/models superclonica/superclonica:cpu docker run -d --gpus all -p 8000:8000 -v superclonica-models:/models superclonica/superclonica:cuda ``` A free voice to start with: [`ciri.json`](https://github.com/superclonica/supertonic-voices/raw/main/voices/ciri/ciri.json) and seven more in [superclonica/supertonic-voices](https://github.com/superclonica/supertonic-voices). ## Speed Same model, voice, text and seed for both engines, run in one process and taking turns on each phrase. | | Supertonic 3 (stock) | SuperClonica | |---|---:|---:| | GPU (RTX 5070 Ti), median per phrase | 202 ms | **117 ms** | | GPU, 10 phrases in a row | 2.03 s | **1.19 s** | | CPU (Ryzen 7 5800X, 4 threads), median per phrase | 855 ms | **530 ms** | | CPU, 24 phrases in 8 languages in a row | 22.03 s | **14.39 s** | On the GPU the whole model runs as recorded CUDA graphs; on the CPU the models are rewritten for multithreaded computation. SuperClonica was faster on all 10 GPU phrases and all 24 CPU phrases. ## Sound The model is the same, so the voice and intonation match. The difference is around the words. | On 10 sample phrases | Supertonic 3 | SuperClonica | |---|---:|---:| | Silence before the first word (median) | 0.50 s | **0.08 s** | | Silence after the last word (median) | 0.63 s | **0.20 s** | | Background in pauses (median, relative to peak) | −48 dB | **−92 dB** | | Abrupt cut at the end of a phrase | Supertonic 3 | SuperClonica | |---|---:|---:| | Russian, 312 clips | 11.9% | **1.0%** | | English, 300 clips | 17.7% | **2.0%** | | German, 132 clips | 10.6% | **0.0%** | From larger runs of our own checks: - **Stray sounds after the last word** (clicks, breaths, extra syllables): 27 and 26 in runs of 1,800 and 1,392 phrases with stock output; 0 and 3 after SuperClonica's cleanup. - **Words are never cut**: the cleanup is checked against the raw output with a phoneme recognizer — more than 25,000 generations in 30+ languages with zero confirmed cuts of real speech. - **Fewer stumbles on long text**: text is split at natural pauses into chunks of up to 160 characters (stock: 300). - **Numbers**: spelled out as words in 27 languages, where the model alone misreads large numbers in some languages (`numbers=False` keeps stock behaviour). - **No clipping**: a look-ahead limiter lowers only the peaks above full scale. Every recording of the comparison, with its loudness envelope: [Supertonic vs SuperClonica](https://superclonica.com/en/compare/supertonic?utm_source=huggingface&utm_medium=model). ## Where stock Supertonic 3 is better - **Startup**: SuperClonica prepares CUDA graphs or CPU-optimized models on launch — 9.5 s vs 1.2 s on the GPU, 4.0 s vs 0.9 s on the CPU. Create the engine once and keep it running. - **Long paragraphs on a GPU** can come out slightly slower because of the shorter chunks (not seen in our measurement). - **Numbers without grammatical case**: Russian ordinals and English years are read as plain numbers; use `numbers=False` to pass digits to the model as stock does. ## How it was measured Supertonic 1.3.1 (supertonic-3) without processing against SuperClonica 0.6.23 with default settings, speed 1.05, 8 steps, the same voice and seed per phrase. GPU: RTX 5070 Ti, ONNX Runtime GPU 1.26 (10 rounds). CPU: Ryzen 7 5800X, 4 threads for both, 24 chat phrases in 8 languages (2 rounds). A working machine with applications open: absolute times are lower on an idle machine, the ratio holds. ## Voices Every Supertonic 3 voice is one JSON file of about 0.3 MB. Free ones are on [GitHub](https://github.com/superclonica/supertonic-voices) and in the [online demo](https://huggingface.co/spaces/Superclonica/superclonica-tts); character, narrator and custom voices are in the [SuperClonica marketplace](https://superclonica.com/en/explore?utm_source=huggingface&utm_medium=model), where every voice page lets you voice your own phrase online. You can also [order a voice](https://superclonica.com/en/requests?utm_source=huggingface&utm_medium=model) trained on your recording or [train one for free](https://superclonica.com/en/studio?utm_source=huggingface&utm_medium=model) on your own computer. ## License The SuperClonica engine is released under the Apache License 2.0 (`pip show superclonica-cpu`). It runs the Supertonic 3 model, which is distributed by Supertone under its own license (OpenRAIL-M); its terms apply to the model and to what you generate with it. SuperClonica is an independent derivative of Supertonic, not an official Supertone release. Use voices responsibly: never to deceive, defraud or impersonate anyone ([terms](https://superclonica.com/en/terms?utm_source=huggingface&utm_medium=model)). ## Links [Website](https://superclonica.com/en/?utm_source=huggingface&utm_medium=model) · [Install guide](https://superclonica.com/en/superclonica?utm_source=huggingface&utm_medium=model) · [PyPI: superclonica-cpu](https://pypi.org/project/superclonica-cpu/) · [PyPI: superclonica-gpu-cuda](https://pypi.org/project/superclonica-gpu-cuda/) · [Docker Hub](https://hub.docker.com/r/superclonica/superclonica) · [Python guide](https://superclonica.com/en/guides/python-text-to-speech?utm_source=huggingface&utm_medium=model) · [Docker API guide](https://superclonica.com/en/guides/text-to-speech-api-docker?utm_source=huggingface&utm_medium=model)