F5-TTS
Source: https://github.com/swivid/f5-tts
Structured fields
{
"archived": false,
"checked_at": "2026-10-17T00:00:00.000Z",
"usefulness": "Flow-matching diffusion-transformer TTS (F5-TTS and E2 TTS reproduction) with zero-shot voice cloning. Code is MIT but the pretrained models are CC-BY-NC because of the Emilia training data.",
"source_type": "repository",
"availability": "available",
"source_owner": "SWivid / F5-TTS authors",
"next_check_at": "2026-10-18T00:00:00.000Z",
"known_limitations": [
"Non-commercial model weights."
],
"upstream_updated_at": "2026-10-14T15:09:13.000Z"
}Evidence claims
- [upstream_claim] README: F5-TTS is a Diffusion Transformer with ConvNeXt V2; E2 TTS is a reproduction; Sway Sampling is an inference-time flow-step sampling strategy. · locator: README, intro source
- [sourced_fact] README License: code released under MIT; the pre-trained models are licensed under CC-BY-NC due to the training data Emilia, an in-the-wild dataset. · locator: README, License source
- [sourced_fact] GitHub metadata: MIT, not archived, last push 2026-10-14. · locator: repository metadata source
- [upstream_claim] Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| code | MIT | permitted | permitted | permitted | unknown | MIT code per README. |
| model_weights | CC-BY-NC | restricted | restricted | restricted | unknown | README: pretrained models CC-BY-NC (non-commercial) because of Emilia training data; exact CC version not stated in the excerpt read. |