Model Gallery

5 models from 1 repositories

Filter by type:

Filter by tags:

qwen3-tts-cpp-1.7b-voicedesign
Qwen3-TTS 1.7B VoiceDesign (C++ / GGML, qwentts.cpp), Q8_0. Synthesises a speaker from a free-text attribute instruction - REQUIRES the OpenAI `instructions` field (e.g. "male, young adult, moderate pitch"); requests without it are rejected. Streaming, 24kHz mono, 11 languages.

Repository: localaiLicense: mit

qwen3-tts-cpp-1.7b-voicedesign-q4
Qwen3-TTS 1.7B VoiceDesign (C++ / GGML, qwentts.cpp), Q4_K_M. Synthesises a speaker from a free-text attribute instruction - REQUIRES the `instructions` field. Streaming, 24kHz mono, 11 languages.

Repository: localaiLicense: mit

omnivoice-cpp
OmniVoice (C++ / GGML) - native text-to-speech with voice cloning and voice design. 24kHz mono output, 646 languages, streaming synthesis. Q8_0 GGUFs (~945 MB total): 612M Qwen3 backbone + RVQ audio codec.

Repository: localaiLicense: apache-2.0

omnivoice-cpp-hq
OmniVoice (C++ / GGML), BF16 high-quality variant - text-to-speech with voice cloning and voice design. 24kHz mono, 646 languages, streaming. BF16 GGUFs (~1.6 GB total).

Repository: localaiLicense: apache-2.0

audio-cpp-irodori-voicedesign
Irodori TTS 600M v3 VoiceDesign (audio.cpp, Q8_0) - describe the voice you want in words instead of supplying a reference clip, served by the audio-cpp backend. Drive it through /v1/audio/speech with the `instructions` field: the backend routes a request carrying instructions to audio.cpp's vdes task, so "a calm elderly woman speaking slowly with a warm, gentle tone" shapes the delivery of whatever you put in `input`. Without instructions this build still answers as ordinary TTS, and with a reference WAV in `voice` it clones instead; the request decides which of the three it gets. The model is Japanese-first and handles English, so an English ASR round trip recovers the words with accent drift rather than cleanly.

Repository: localaiLicense: mit