Omni Voice
OmniVoiceApache 2.0audio

Omni Voice

Updated Jun 7, 2026
Parameters
0.6B
Context
8,192
License
Apache 2.0
Updated
Jun 7, 2026

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Runs on your 24 GB - best at FP16
1 of 1 quantizations fit Omni Voice with real runtime overhead.
FP16
2 GB
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve k2-fsa/OmniVoice

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

Omni Voice

Omni Voice by k2-fsa is an efficient text-to-speech model with 2.57 million monthly downloads on HuggingFace. At just 0.6 billion parameters, it delivers quality TTS on modest hardware.

Key features

  1. 0.6B params - lightweight, runs on CPU
  2. 2.57M monthly downloads - highly popular
  3. Apache 2.0 - fully open license
  4. GGUF support - further quantization available

When to use

  • Lightweight TTS - when Kokoro is too small but Qwen3-TTS is too large
  • Edge deployment - Raspberry Pi, phones, embedded
  • Voice assistants - local TTS without GPU

Frequently asked

Quick answers to common questions

How much VRAM does Omni Voice need?

Omni Voice with 0.6B parameters needs approximately 2 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is Omni Voice better than other OmniVoice models?

Omni Voice has 0.6B parameters with 8,192 context - a strong choice for text-to-speech.

What license is Omni Voice under?

Omni Voice is released under the Apache 2.0 license, making it suitable for most commercial and personal projects.

What hardware runs Omni Voice well?

With 0.6B parameters, Omni Voice requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.

What is the best quantization for Omni Voice?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Step up to Q5_K_M or Q8_0 only if you have spare VRAM. Use our VRAM calculator to compare.

What models compete with Omni Voice?

Omni Voice competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Compare & pair with

Similar models and recommended hardware

Nearby options

Similar models and compatible hardware by spec

Comments coming soon

Configure NEXT_PUBLIC_GISCUS_REPO_ID and NEXT_PUBLIC_GISCUS_CATEGORY_ID at giscus.app to enable.