software-mansion/Reverb-TTS
text-to-speech model by software-mansion
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
GitHub · Demo · Quick start · Benchmarks Reverb is a text-to-speech model designed for high-quality voice-cloning. Give it a few seconds of someone speaking and their transcript, and it speaks any text in that voice, with the speaker's timbre, prosody, and emotion. It's built on one of the leading open-weight TTS models. them. iPhone 17 at batch 1. Qualcomm NPUs (QNN). 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: to 2048, KV groups from 8 to 6, and the text vocabulary from 151,676 to 62,035 tokens. The pruned model learns to match OmniVoice's predictions. as Emilia and variants of YODAS2, such as yodas2-sidon. rankings. The result has 297M parameters, less than half of OmniVoice's 613M. Additional performance improvements let…
Read the full model card ↗ · Preview checked 2026-11-20T10:15:07.370Z
Inside the original model card — Document outline
- Reverb-TTS
- What is Reverb?
- Quality, size and speed
- Try it
- Usage
- Clone a voice
- Use a preset voice
- Speak another language
- On your Mac with Native
- In the browser with ruNNtime
- Text preprocessing
- Model variants
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: cc-by-nc-4.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
software-mansion/Reverb-TTS is a text-to-speech model repository published by software-mansion on Hugging Face. The source reports the reverb-tts library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-speech
- Library
- reverb-tts
- Recent downloads (30 days)
- 46
- Cumulative likes
- 41
- Hugging Face trending score
- 40
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- cc-by-nc-4.0
- Access
- Not gated by Hugging Face
- Created
- 2026-10-01T21:47:49.000Z
- Last modified
- 2026-11-19T15:36:37.000Z
Compatibility and lineage
Reported languages: en, de, fr, es, it, pl, pt
Reported base models: k2-fsa/OmniVoice
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-20T07:00:14.581Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.