Chatterbox v3 T3 — GGUF

CielVox Chatterbox v3 T3 model for voice cloning with the S3Gen codec.

Input: reference audio + reference text
Output: cloned voice speech
Use with --backend chatterbox --codec-model <s3gen.gguf>

Files

File	Size	Description
`chatterbox-v3-t3-q8_0.gguf`	609 MB	T3 model, Q8_0 quantization

Usage

./build/bin/stelnettts \
  --backend chatterbox \
  -m /path/to/chatterbox-v3-t3-q8_0.gguf \
  --codec-model /path/to/chatterbox-v3-s3gen-q8_0.gguf \
  --voice <ref.wav> --ref-text "<text>" \
  --tts "Hello." --tts-output /tmp/out.wav \
  --i-have-rights --speaker-identity synthetic

Note

Documentation under construction. Parameters and integration details may change.

Downloads last month: 73

GGUF

Model size

0.5B params

Architecture

chatterbox

Hardware compatibility

8-bit