Speech-to-text with word timestamps, the usual source for caption timing in agent edits. BSD-2-Clause.
| Field | Value |
|---|---|
| Vendor | m-bain |
| Type | Captions |
| Categories | Captions and clipping, Video skills and MCP servers |
| Open source | Yes |
| License | BSD-2-Clause |
| GitHub stars | 25,048 (github-api) |
| Last release | 2026-05-25 v3.8.6 |
| Agents | Claude Code, Codex, Cursor |
| Max duration | — |
| Resolution | — |
| Native audio | — |
| 9:16 | — |
| 720p | — |
| 1080p | — |
| 4K | — |
| Rate, resolution not stated | — |
| Free tier | Self-host. No license fee under BSD-2-Clause. |
| API | No |
| Affiliate | No |
| Featured | No |
| Sponsored | No |
| Last verified | 2026-11-03 |