Coqui XTTS (offline + voice clone)
Clones each speaker's voice from a few seconds of the video and speaks your subtitles in 16 languages, on your own computer. The model is free for non-commercial use only.
Settings Add-ons Coqui XTTS-v2 (offline + voice clone) Install
Subtitld downloads it, checks its SHA-256, and keeps it updated.
- Languages
- 16
- Models
- 3
- Voices
- 3
- Add-on download
- 302–443 MB
- RAM, at least
- 6 GB
What it does
Pick Custom voice and Subtitld gives the model a few seconds of that speaker, cut from the video. It works best with 6 seconds or more.
XTTS female 1 and XTTS male 1, for speakers you don't clone.
It speaks in the project's language, or in English when the project has none set.
The first line waits for the model to load, and the first time also to download; the rest reuse it. On the CPU a long sentence can take half a minute.
Non-commercial model. The XTTS-v2 weights are under the Coqui Public Model License (CPML): free for non-commercial use, with a paid license from Coqui needed for anything else. The add-on agrees to Coqui's terms prompt for you when it loads the model, so you won't see it; the terms apply all the same.
Voices
In the Speakers tab, choose Coqui XTTS as a speaker's Dubbing engine, then pick a Voice. Custom voice is at the top of the list. Each line comes out as long as the model makes it; turn on Fit dub to subtitle duration for the speaker to stretch or squeeze it to its subtitle.
3 voices in 1 language.
en2
The sample for the clone
When a speaker's voice is Custom voice, Subtitld cuts a sample of that speaker from the project's audio:
- their longest subtitle between 3 and 12 seconds;
- if none fits, the first 12 seconds of a longer one;
- if all are shorter than 3 seconds, several in a row, joined until they reach 3.
XTTS works best with 6 seconds or more, so give each speaker at least one line between 6 and 12 seconds. If you have separated music from voice for this video, the sample comes from the voice alone. Default voice reference in the add-on's settings is used only when no sample can be cut, for example with no video open.
Subtitld keeps each speaker's sample and cuts it again only if the audio file changes. After you retime a speaker's lines, delete their sample to get a fresh one; its name ends with the speaker's name.
| System | Folder |
|---|---|
| Linux | ~/.cache/subtitld/clone-refs |
| macOS | ~/Library/Caches/subtitld/clone-refs |
| Windows | %LOCALAPPDATA%\subtitld\subtitld\Cache\clone-refs |
Models
One model, downloaded the first time you generate a line; the two small files beside it are its settings and vocabulary. The add-on keeps it loaded until it has been idle for five minutes.
| Model | Download |
|---|---|
| xtts_v2 | |
| xtts_v2_config | |
| xtts_v2_vocab |
Options
The add-on reads these when it starts, so a change applies once it has been idle for five minutes, or after you restart Subtitld.
In Settings › Add-ons › Coqui XTTS-v2 (offline + voice clone) › Configure.
cpuLeave this on CPU. The released builds are made with PyTorch's CPU package, so CUDA won't work with them; MPS is marked beta.
A clip to copy when Subtitld can't take a sample of the speaker from the video, for example with no video open. A sample from the video always comes first. While this is set, the two built-in voices copy this clip too.
Languages
The add-on passes the project's language to the model, without its region; with no language set, it speaks English.
enesfrdeitptpltrrunlcsarzh-cnjahuko
Platforms
| System | Download | Tested |
|---|---|---|
| Linux x86-64 | 442.7 MB | Built and started in CI |
| macOS (universal) | 323.1 MB | Built and started in CI |
| Windows x86-64 | 302.2 MB | Built and started in CI |
Each release is built on Linux, macOS and Windows, and CI checks that the program starts and lists its voices. CI doesn't generate speech.
Troubleshooting
bad_paramsEither the subtitle has no text, or the clone got no sample: Subtitld couldn't cut one (no video open, or no subtitles for that speaker) and no default clip is set. Give the subtitle text, open the video, or set Default voice reference.internalThe model failed to load or to speak the line; the message says which. A failed download on first use ends here too: check your connection and free disk space, and try again. Also check that the project's language is one of those listed above.
License
Not for commercial work unless you have a commercial license from Coqui for the XTTS-v2 weights. The add-on's own code is MIT.
Versions
- 1.0.7
Automated release for coqui-xtts v1.0.7.
Other Voices add-ons
-
Piper Offline
158 offline voices in 49 languages, each a separate small download.
-
Kokoro Offline
54 offline voices in nine languages, all from one 82 MB model.
-
Supertonic Offline
Ten offline voices, each able to speak all 31 of its languages.
-
sanoTTS Offline
Tiny offline voices, 28 in 14 languages, each under 10 MB.
-
Parler-TTS Offline
English voices that follow a written description; 34 named speakers.
-
Qwen3-TTS Clone
Ten languages, nine voices, and cloning from 3 seconds of a speaker.
-
F5-TTS Clone
Voice cloning only, in English and Chinese; non-commercial model.
-
VoxCPM2 Clone
30 languages at 48 kHz, in the speaker's own voice or a described one. Heavy.
-
Pocket TTS Offline
Fast and light, CPU only. 23 voices in seven European languages.
-
Sopro Clone
The speaker's own voice, fast on a CPU. Four languages.
-
KittenTTS 2 Clone
The speaker's own voice in 16 languages, on a CPU. Weights under a restrictive licence.
-
Ming-3.0-tts Clone
7 languages at 44.1 kHz: cloned, built-in or described voices, with emotion. Heavy.
-
Chatterbox Clone
Offline TTS in 20 languages, in the speaker's own voice cloned from a few seconds of the video or in one of 8 preset…