sakasegawa/drama-3-GGUF
text-to-speech model by sakasegawa
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.
Built with Fish Audio. These files run only in speech.cpp 0.8.8 or later. Their layout is speech.cpp's own, so llama.cpp, LM Studio, Ollama and other programs that read GGUF cannot run them. They are not made, sponsored or endorsed by Fish Audio. Each file holds Fish Audio's Drama 3, a speech model of 35B parameters with 3B active, and its 44.1 kHz codec, converted to GGUF from the official checkpoint. It speaks a text in any of 83 languages as one speaker or as a scene of up to 16, with cues such as [laughs] or [whispers] written in the text, in voices cloned from recordings and their words or in voices the model chooses, and passes the audio as it makes it. Install speech.cpp (install), then: drama-3 is the name speech.cpp gives this model; speech fetches the Q4K file from this repository the first time, and drama-3:q80 or another…
Read the full model card ↗ · Preview checked 2026-11-01T14:22:39.965Z
Inside the original model card — Document outline
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: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
sakasegawa/drama-3-GGUF is a text-to-speech model repository published by sakasegawa on Hugging Face. A library was not reported.
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
- Not reported
- Recent downloads (30 days)
- 34,708
- Cumulative likes
- 3
- Hugging Face trending score
- 1
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-10-15T17:31:03.000Z
- Last modified
- 2026-10-15T21:17:55.000Z
Compatibility and lineage
Reported languages: af, am, ar, as, az, be, bg, bn, bo, br, bs, ca, cs, cy, da, de, el, en, es, et, eu, fa, fi, fo, fr, gl, gu, he, hi, hr, ht, hu, hy, id, is, it, ja, jv, ka, kk
Reported base models: fishaudio/drama-3
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 2026-11-01T06:52:33.137Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.