README.md

metadata

license: cc-by-nc-4.0
language:
  - en
  - de
  - fr
  - es
  - it
  - pl
  - pt
base_model: k2-fsa/OmniVoice
pipeline_tag: text-to-speech
tags:
  - text-to-speech
  - voice-cloning
  - zero-shot

Reverb-TTS

Reverb is a text-to-speech model designed for high-quality voice cloning. Built on top of one of the leading open-weight TTS models, it combines an exceptional quality of mimicking any reference speaker, including prosody, emotions and voice timbre, while staying lightweight and fast enough to run locally on mobile and desktop devices.

What is Reverb?

Reverb starts from OmniVoice, a 0.6B masked-diffusion TTS model that fills in a grid of audio-codec tokens over several passes, conditioned on the text and on a reference speaker's audio. We made Reverb from it in three stages:

1. Pruning with distillation. 4 of the 28 transformer layers are removed, the feed-forward layers shrink from 3072 to 2048, and the text vocabulary from 151,676 to 62,035 tokens. The pruned model learns to match OmniVoice's predictions.
2. Supervised retraining in Reverb's seven languages, on cleaned and selected subsets of open speech datasets such as Emilia and variants of YODAS2, such as yodas2-sidon.
3. RLHF-style post-training: several rounds of iterative DPO with an automatic judge fitted on human preference rankings.

The result has 297M parameters, less than half of OmniVoice's 613M. Additional performance improvements let it generate speech 10× to 20× faster than the original model.

Quality, size and speed

We compare Reverb with open-weight voice-cloning models on the MiniMax Multilingual Test Set, restricted to Reverb's seven languages: 700 sentences, 100 per language, each spoken in the voice of one of two reference speakers of that language. Every model generates one take per sentence with its default settings. WER (Whisper large-v3) and speaker similarity (SIM-o) come from OmniVoice's evaluation scripts and are averaged over the languages.

Model	Parameters (model + codec decoder)	WER ↓	SIM-o ↑
Reverb	319M	1.35%	0.818
OmniVoice	634M	1.64%	0.835
Audio8-TTS-Realistic	732M	1.97%	0.750
Qwen3-TTS 0.6B Base	1,020M	11.96%¹	0.781
Qwen3-TTS 1.7B Base	2,031M	1.52%¹	0.781
VoxCPM2	2,336M	1.55%	0.810

Parameters count the generating model and the decoder of its audio codec; encoders used only to process the reference recording are not counted.
¹ Qwen3-TTS does not support Polish, so its WER is averaged over the other six languages.

Generation speed, in × real time (seconds of audio per second of compute; higher is better), on MiniMax English sentences. Timing runs from the text and an already-encoded reference voice to the waveform, codec decoding included. Every model runs its default settings in bf16.

Hardware	Reverb	OmniVoice	Audio8	Qwen3-TTS 0.6B	Qwen3-TTS 1.7B	VoxCPM2	Fish S2 Pro
NVIDIA RTX 5090, batch 32	164.9×	13.2×	4.2×	3.3×	4.0×	3.0ײ	0.18ײ
Apple M4 Pro, batch 1	21.6׳	0.84×	0.76×	0.51×	0.52×	0.69×	–

² No batched generation: sentences run one at a time.
³ Reverb's ExecuTorch MLX program (fp16) with the Core ML codec decoder. In PyTorch on the GPU (MPS), as the other models run on the M4 Pro: 12.3×.

Usage

pip install reverb-tts

import soundfile as sf
from reverb_tts import TTS

tts = TTS.from_pretrained("software-mansion/Reverb-TTS")
voice = tts.voice("reference.wav", "The exact transcript of the reference recording.", language="en")
audio = tts.generate("Hello! This is my cloned voice.", voice, language="en")
sf.write("output.wav", audio, tts.sample_rate)

The reference should be 3 to 20 seconds of clean speech from one speaker, with its exact transcript. Languages: en, de, fr, es, it, pl, pt.

Model variants

Variant	Weights	Activations	Size
fp32	fp32	full precision	1.19 GB
int8 (default)	int8, one scale per output channel	full precision	307 MB
int8a8	int8, one scale per output channel	int8, one scale per token	307 MB
int4	int4, one scale per group of 32 inputs	full precision	191 MB

Select one with TTS.from_pretrained(..., variant="int4"). The weights are in model/safetensors/<variant>/. In automatic scoring, int8 and int8a8 show no measurable loss against fp32, and int4 a small one. ExecuTorch programs for on-device use are in model/executorch/: MLX (Apple GPUs) in fp16, int8 and int4, and Vulkan (Android GPUs) in int4. voices/ holds ready-made reference voices.

License and acknowledgments

• Code: Apache 2.0; see LICENSE.
• Model weights: CC BY-NC 4.0, for non-commercial use with attribution.

Reverb's weights were initialized from OmniVoice by the k2-fsa team, and its target-length rule and prompt format come from OmniVoice's code. We thank its authors for releasing the model and code openly. Reverb uses the Higgs Audio v2 tokenizer as its audio codec, and Verbalis prepares its text.