VoxMel offline, voice clone, 2 languages
Dubs your subtitles in English and Mandarin with VoxDance Lab's VoxMel, in each speaker's own voice cloned closely from the video and its subtitles, or in one of eight preset voices. It runs on your own computer, and the add-on, the model and the voices are all Apache-2.0.
Settings Add-ons VoxMel (offline, voice clone, 2 languages) Install
Subtitld downloads it, checks its SHA-256, and keeps it updated.
- Languages
- 2
- Models
- 1
- Voices
- 9
- Add-on download
- 15–19 MB
- RAM, at least
- 2 GB
Listen
What it does
Subtitld cuts a few seconds of each speaker from the video and sends them with the subtitles spoken in them. VoxMel clones that voice closely, in English or Mandarin.
Two women and two men for each language, for speakers you don't want to clone. VoxMel made them itself: no person's voice was recorded for them.
A cloned line takes two to four seconds per second of speech on a recent laptop processor.
The add-on, the audio.cpp engine, the VoxMel weights and the preset voices are all Apache-2.0.
Before you install
- Disk: about 1.2 GB, most of it the 1.04 GB model, downloaded on the first line you dub.
- Memory: about 2 GB free.
- Time: on an Intel Core i7-13700T, a line in the speaker's own voice took two to four seconds per second of speech. On an Apple Silicon Mac it runs on the GPU.
- Languages: English and Mandarin only. For other languages, VoxCPM2 clones voices in 30 and OmniVoice in 646.
Voices
In the Speakers tab, choose VoxMel as a speaker's Dubbing engine, then pick a Voice. Turn on Fit dub to subtitle duration for the speaker to stretch or squeeze each line to its subtitle: VoxMel itself has no control of pace.
9 voices in 2 languages.
en4zh4
The cloned voice
With Speaker's own voice, Subtitld cuts a sample of that speaker from the project's audio, from one of their subtitles of 3 to 12 seconds, or several short ones joined, and sends the subtitle text with it. VoxMel needs both the sample and its words. The Fallback reference clip in the add-on's settings, with its transcript, is used only when no sample can be cut.
VoxMel clones best within a language. An English dub of a Mandarin speaker works well; a Mandarin dub of an English speaker may slur some words.
Clone the timbre only doesn't work with this add-on, because VoxMel can't clone without the words of the sample. Leave it off for speakers who use VoxMel.
Preset voices
Each preset is a short clip that VoxMel made without any reference recording, kept with its exact words. Every line of a speaker given a preset clones that clip, so the voice stays the same through the video. English presets suit English lines and Mandarin presets Mandarin lines.
Models
There is one model, VoxMel 0.6B with its Vocos vocoder, its weights stored in 8 bits, as the audio.cpp project converted it. It is not inside the add-on: it downloads into Subtitld's shared model cache the first time you dub, from Hugging Face at a pinned revision, and is checked. An interrupted download resumes where it stopped. Updating or removing the add-on keeps the model.
| Model | Download | Good for |
|---|---|---|
| VoxMel 0.6B (8-bit) Default voxmel | Every voice, in English and Mandarin |
The first line also loads the model, so it takes longer than the ones after it. On an Apple Silicon Mac, the very first time, the add-on also speaks one short test line on the GPU, and uses the CPU if that doesn't work. Cancel stops a line between two steps, or stops the download.
Options
In Settings › Add-ons › VoxMel (offline, voice clone, 2 languages) › Configure.
32How finely VoxMel draws each moment of speech. 32 is VoxMel's own setting; fewer is faster, with less detail.
3.5How closely the speech follows the text. 3.5 is VoxMel's own setting.
3How closely a cloned voice follows the clip. 3.0 is VoxMel's own setting; higher can sound closer, or strained.
00 picks the performance cores on CPUs that also have efficiency cores. Fewer threads keep the computer more responsive while it dubs.
A clip for the cloned voice when Subtitld can't cut one from the video, for example with no video open: 3 to 15 seconds of one person speaking.
Exactly what is said in the fallback clip, word for word. VoxMel clones from the clip and its words, so the fallback clip is refused without it.
Languages
English and Mandarin Chinese. VoxMel reads the language from the text.
enzh
Platforms
| System | Download | Tested |
|---|---|---|
| Linux x86-64 | 18.8 MB | Dubbed with the real model on a real machine and on AlmaLinux 8; in CI, the installed add-on downloads the model, speaks, clones a voice and cancels a line |
| macOS (Apple silicon) | 18.1 MB | In CI, the installed add-on downloads the model, speaks, clones a voice and cancels a line (Apple Silicon) |
| Windows x86-64 | 15.4 MB | In CI, the installed add-on downloads the model, speaks, clones a voice and cancels a line |
Linux x86-64 (any distribution from 2018 on, glibc 2.28 or newer), macOS 13.3 or newer on Apple Silicon, and Windows x86-64. Each release is built on all three, and on each CI installs the add-on, downloads the model, and has it speak, clone a voice and cancel a line.
Troubleshooting
network_unavailableThe model couldn't be downloaded. Check your connection and try again: the download resumes.disk_fullNot enough disk space for the model. It needs about 1.2 GB free.oomOut of memory. Close other programs; VoxMel needs about 2 GB free.bad_paramsThe line has no text, or the cloned voice got no sample or no words with it. The message says which. For a cloned voice, open the video and leave Clone the timbre only off.unsupported_voiceThe project names a voice this version doesn't have. Pick the voice again in the Speakers tab.internalSomething failed inside the add-on; the message has the details.
License
Fine for commercial work: the add-on, its preset voices, the audio.cpp engine and the VoxMel weights are all Apache-2.0, and the Vocos vocoder and ggml are MIT. The dubs you make are yours. A cloned voice sounds like a real person: clone voices you have the right to use, and say that a dub is synthetic where it matters.
Versions
- 26.11.1
The first release: text-to-speech for Subtitld with VoxDance Lab's VoxMel 0.6B, in English and Mandarin.
- The speaker's own voice, cloned closely from the clip Subtitld cuts from the video and its subtitles. VoxMel needs the clip's words, so "Clone the timbre only" doesn't work with this add-on. It clones best within a language: an English dub of a Mandarin speaker works well, a Mandarin dub of an English speaker may slur some words.
- Eight preset voices, two women and two men in each language. VoxMel made them itself, with no reference recording, and every line of a speaker clones the same clip, so the voice stays the same.
- Runs on the CPU, or on the GPU of an Apple Silicon Mac once a short test line shows that works there. A cloned line takes two to four seconds per second of speech on a recent laptop CPU.
- The 1.04 GB model downloads on the first line, pinned and checked; about 2 GB of memory. The archives are about 17 MB, and the Linux one runs on glibc 2.28 and newer.
The add-on, its preset voices, audio.cpp and the VoxMel weights are Apache-2.0; the Vocos vocoder, ggml, cJSON, libyaml, utf8proc and llama.cpp's tokenizer are MIT. Each archive carries THIRD_PARTY_LICENSES/, with the one change we made to audio.cpp (a step callback for cancel and progress).
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.
-
Coqui XTTS Clone
Voice cloning in 16 languages, with a non-commercial model license.
-
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.
-
Scylla's Band Offline
Fourteen voices in six languages, light and fast on a CPU. Built-in voices only.
-
Audio8 TTS Clone
The speaker's own voice in 23 languages, Cantonese and Arabic included. Slow on a CPU.
-
Inflect Offline
Natural English speech from a tiny model, fast on any CPU.
-
Paradee Offline
Four natural English voices, American and British, from one 8.5 MB model.
-
BlueTTS Clone
Hebrew and Yiddish, plus five more languages. The speaker's own voice, fast on a CPU.
-
ZONOS3-Mini Clone
43 languages, from Arabic to Vietnamese. The speaker's own voice, on a CPU.
-
Reverb Clone
Seven European languages and the speaker's own voice, on a CPU; non-commercial model.
-
OmniVoice Clone
646 languages, the speaker's own voice across languages; non-commercial model.
-
tiny-voca Offline
Two American English voices from a 4.5M-parameter model, with nothing to download.
-
Chatterbox Clone
The speaker's own voice in 20 languages, on a CPU, with no account.