OmniVoice
OmniVoice is a multilingual zero-shot text-to-speech model built for voice cloning, voice design, and general speech synthesis at massive language scale. It supports more than 600 languages, uses a diffusion language model-style architecture, and is positioned for high-quality speech generation with fast inference.
- Type
- Audio
- Weights
- Open
- Downloads
- 1.4M
- Likes
- 1.4k
- Pipeline
- text to speech
- Library
- omnivoice
Model hub
k2-fsa/OmniVoice
- Repo
- k2-fsa/OmniVoice
- Access
- Public
Technical tags and languages
Related tools
1
More from Xiaomi
11
-
99k DL
MiMo V2 Flash
Text
I cannot find public technical documentation for a distinct “MiMo v2 Flash” model beyond Xiaomi’s MiMo-7B and…
-
5.8k DL
MiMo V2.5 ASR
Multimodal
MiMo-V2.5-ASR is Xiaomi MiMo’s state-of-the-art end-to-end ASR model for robust transcription across Mandarin…
-
2k DL
MiMo V2.5 Pro
Text
MiMo-V2.5-Pro is Xiaomi’s latest agentic language model, built for stronger long-horizon coherence, complex s…
-
MiMo V2.5 Pro UltraSpeed
Text
MiMo-V2.5-Pro-UltraSpeed is Xiaomi MiMo’s 1T-parameter high-speed reasoning model variant built with TileRT t…
-
Pixel Perfect Depth
Image
Pixel-Perfect Depth is a monocular depth estimation model that uses pixel-space diffusion transformers to pre…
-
Xiaomi MiMo V2 Omni
Multimodal
MiMo-V2-Omni is an omni foundation model that unifies multimodal understanding with agentic capability, built…
-
Xiaomi MiMo V2 Pro
Text
MiMo-V2-Pro is Xiaomi’s flagship foundation model built for real-world agent workloads, designed to act as th…
-
Xiaomi MiMo V2 TTS
Audio
MiMo-V2-TTS is Xiaomi’s large-scale speech synthesis model built for expressive agent voice, aiming for natur…
About Xiaomi
1
Consumer electronics and smart device company making smartphones, wearables, IoT products, home appliances, smart TVs, scooters, and connected lifestyle hardware.
Tools using OmniVoice
8