{"kind":"compare","slug":"xtts","path":"/compare/xtts","title":"Coqui XTTS-v2 Alternative for Commercial Use | SuperClonica","description":"XTTS-v2 or SuperClonica: Coqui's cloning model is non-commercial and its original repository unmaintained; Supertonic 3 voices run fast on CPU under OpenRAIL-M.","h1":"Coqui XTTS-v2 vs SuperClonica: a Coqui TTS alternative","intro":"XTTS-v2 is the voice cloning model from Coqui, published with the open-source Coqui TTS library. From a short reference clip it speaks in that voice in 17 languages, and it can carry a voice from one language into another.\n\nTwo things matter if you plan to build on it today: the original coqui-ai/TTS repository is no longer maintained, and the license of the XTTS weights does not allow commercial use. If you are looking for a Coqui TTS alternative, here is how SuperClonica compares. XTTS is not in our comparison table, so we give no speed or quality scores for it.","sections":[{"heading":"What XTTS-v2 does","paragraphs":["XTTS-v2 clones a voice from a few seconds of audio: the model card mentions a 6-second clip, the documentation 3 seconds. It speaks English, Spanish, French, German, Italian, Portuguese, Polish, Turkish, Russian, Dutch, Czech, Arabic, Chinese, Japanese, Hungarian, Korean and Hindi, outputs 24 kHz audio and transfers emotion and style from the reference.","It can stream, and the authors state latency under 200 ms without naming the hardware. The examples in the documentation run it on CUDA, and fine-tuning code is included."]},{"heading":"XTTS license: why commercial use is off the table","paragraphs":["The XTTS-v2 weights are under the Coqui Public Model License. It allows only non-commercial use, and it covers the generated audio as well as the model: as soon as you are paid, directly or indirectly, for the model or its output, you are outside it. Companies may use it only for testing, evaluation and non-commercial research.","The Coqui TTS code itself is MPL-2.0, so the code is not the obstacle; the weights are. Supertonic 3 uses OpenRAIL-M, a royalty-free license with a list of prohibited uses instead of a non-commercial clause. Voices bought on SuperClonica are for your own projects and may not be resold."]},{"heading":"Coqui TTS today","paragraphs":["The original coqui-ai/TTS repository is no longer maintained. Idiap keeps a fork that is published on PyPI as coqui-tts, with prebuilt wheels for Linux, macOS and Windows and newer additions such as caching for cloned voices. The XTTS-v2 weights and their license stayed the same."]},{"heading":"Cloning on every request or a trained voice file","paragraphs":["XTTS rebuilds the voice from the reference clip on each request, so the result depends on the clip you pass. SuperClonica trains the voice once into a Supertonic 3 file: a clean recording of 5 to 10 seconds with its exact transcript, your own NVIDIA GPU, no fee. You can also commission the voice from an author or pick one from the catalog.","The file then runs offline on an ordinary CPU. By our estimate SuperClonica speaks 6.4–9.7× faster than real time on a desktop 8-core processor, a 10-second line in about 1.0–1.6 seconds."]},{"heading":"When XTTS-v2 is the better choice","paragraphs":["Choose SuperClonica for paid projects, for machines without a GPU and for voices you want to keep as a file. XTTS-v2 still fits these cases:"],"points":["Personal, research and hobby projects where the non-commercial license is no obstacle.","Instant cloning from a few seconds of audio, with no training step.","Chinese speech, which Supertonic 3 does not have yet.","Pipelines already built on the Coqui TTS library."]}],"faq":[{"question":"Can I use XTTS-v2 commercially?","answer":"Not under its license. The Coqui Public Model License allows only non-commercial use of the model and of the audio it generates. The Coqui TTS code is MPL-2.0, but that does not change the terms of the weights."},{"question":"Is Coqui TTS still maintained?","answer":"The original coqui-ai/TTS repository is not. A fork by Idiap continues the library on PyPI as coqui-tts."},{"question":"What is a Coqui TTS alternative for commercial voice cloning?","answer":"One option is a Supertonic 3 voice trained from your recording and run with SuperClonica: the model is OpenRAIL-M and the voice is a file you keep. If you need instant cloning instead, read the licenses of other models closely; the official F5-TTS weights, for example, are non-commercial too."},{"question":"Does XTTS-v2 need a GPU?","answer":"The official examples run it on CUDA, and the documentation gives no CPU figures. Supertonic 3 needs no GPU according to its authors, and SuperClonica runs its voices on an ordinary CPU."}],"cta":{"catalog":"Browse ready voices","install":"Install SuperClonica"},"sources":[{"label":"XTTS-v2 model card (Hugging Face)","url":"https://huggingface.co/coqui/XTTS-v2"},{"label":"Coqui Public Model License","url":"https://huggingface.co/coqui/XTTS-v2/blob/main/LICENSE.txt"},{"label":"XTTS documentation (coqui-tts)","url":"https://coqui-tts.readthedocs.io/en/latest/models/xtts.html"},{"label":"Coqui TTS fork by Idiap (GitHub)","url":"https://github.com/idiap/coqui-ai-TTS"},{"label":"Original coqui-ai/TTS repository","url":"https://github.com/coqui-ai/TTS"},{"label":"Supertonic 3 model card","url":"https://huggingface.co/supertone-oss-archive/supertonic-3"}],"published":"2026-10-17","updated":"2026-10-23","pages":[{"slug":"text-to-speech","path":"/text-to-speech","h1":"Text-to-speech that runs on your own computer"},{"slug":"supertonic","path":"/compare/supertonic","h1":"Supertonic vs SuperClonica: same model, faster and cleaner"},{"slug":"fish-audio","path":"/compare/fish-audio","h1":"Fish Audio and Fish Speech vs SuperClonica"},{"slug":"omnivoice","path":"/compare/omnivoice","h1":"OmniVoice vs SuperClonica: more languages or more speed"},{"slug":"qwen3-tts","path":"/compare/qwen3-tts","h1":"Qwen3-TTS vs SuperClonica for local text-to-speech"},{"slug":"voxcpm","path":"/compare/voxcpm","h1":"VoxCPM 2 vs SuperClonica: studio sound or CPU speed"},{"slug":"f5-tts","path":"/compare/f5-tts","h1":"F5-TTS vs SuperClonica: zero-shot cloning or fast CPU speech"},{"slug":"elevenlabs","path":"/compare/elevenlabs","h1":"An offline alternative to ElevenLabs"},{"slug":"kokoro","path":"/compare/kokoro","h1":"Kokoro TTS vs SuperClonica: two small models for local speech"},{"slug":"piper","path":"/compare/piper","h1":"Piper TTS vs SuperClonica: tiny devices or custom voices"},{"slug":"xtts","path":"/compare/xtts","h1":"Coqui XTTS-v2 vs SuperClonica: a Coqui TTS alternative"},{"slug":"chatterbox","path":"/compare/chatterbox","h1":"Chatterbox TTS vs SuperClonica: instant cloning or a trained voice file"}],"related":[{"slug":"offline-text-to-speech","path":"/guides/offline-text-to-speech","h1":"How to convert text to speech offline on your computer"},{"slug":"voice-cloning","path":"/guides/voice-cloning","h1":"Voice cloning: how to get a voice that sounds like a recording"},{"slug":"best-free-tts-models","path":"/guides/best-free-tts-models","h1":"The best free text-to-speech models for local use in 2026"},{"slug":"text-to-speech-for-videos","path":"/guides/text-to-speech-for-videos","h1":"Text to speech for videos, audiobooks, games and apps"},{"slug":"supertonic-3-voices","path":"/guides/supertonic-3-voices","h1":"Supertonic 3 voices: where to get custom voices and how to use them"},{"slug":"python-text-to-speech","path":"/guides/python-text-to-speech","h1":"Text to speech in Python: offline, free and with natural voices"},{"slug":"text-to-speech-api-docker","path":"/guides/text-to-speech-api-docker","h1":"Self-hosted text-to-speech API in Docker"}]}