Speech & Voice Models

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Voice cloning, dubbing, dictation and transcription, all running on one local machine.

Whisper in C++ — fast on plain hardware and excellent on Apple Silicon, with no Python and no CUDA.

Serves text, vision, speech, image and video models from one self-hosted service that imitates the paid interfaces.

Open-source text-to-speech that clones a voice from a short clip and reads it back in 23 languages, Russian included.

Whisper speech-to-text, rebuilt to run about four times faster and on less memory.

Speech-to-text with a start and end time on every word, plus optional speaker labels.

Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.

Fast local neural speech on plain CPU — the licensed replacement for edge-tts's grey area.