mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-05 12:31:15 +02:00

Files

T

Concedo bfd6500450 Merge commit '873e5d8e39feb34a376e0efd01bf3f665dfffeb5' into concedo_experimental

# Conflicts:
#	.github/workflows/build-cmake-pkg.yml
#	.github/workflows/build-cpu.yml
#	.github/workflows/make-release.yml
#	.github/workflows/release.yml
#	.pi/gg/SYSTEM.md
#	CMakeLists.txt
#	cmake/arm64-windows-llvm.cmake
#	docs/backend/ET.md
#	docs/build.md
#	docs/development/HOWTO-add-model.md
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cpu/kleidiai/kernels.cpp
#	ggml/src/ggml-cpu/kleidiai/kleidiai.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/rope-ops.c
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/mul_mv_q6_k_f32_flat.cl
#	ggml/src/ggml-opencl/kernels/rope.cl
#	ggml/src/ggml-sycl/dmmv.cpp
#	ggml/src/ggml-sycl/dpct/helper.hpp
#	ggml/src/ggml-sycl/element_wise.cpp
#	ggml/src/ggml-sycl/esimd.hpp
#	ggml/src/ggml-sycl/fattn-mkl.cpp
#	ggml/src/ggml-sycl/fattn-onednn.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/im2col.cpp
#	ggml/src/ggml-sycl/norm.cpp
#	ggml/src/ggml-sycl/rope.cpp
#	ggml/src/ggml-sycl/set_rows.cpp
#	ggml/src/ggml-vulkan/CMakeLists.txt
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/rope.wgsl
#	ggml/src/ggml-zendnn/CMakeLists.txt
#	scripts/make-release-desc.sh
#	scripts/sync-ggml.last
#	tests/test-backend-ops.cpp
#	tests/test-json-schema-to-grammar.cpp
#	tools/cli/README.md
#	tools/server/README.md
#	tools/ui/src/lib/constants/settings.constants.ts
#	tools/ui/src/lib/services/chat.service.ts

2026-08-24 21:15:18 +08:00

README.md

mtmd: support pocket-tts (#26871 )

2026-08-11 14:18:30 +02:00

tts.cpp

mtmd: add --mmproj-device argument (#23255 )

2026-08-20 18:45:37 +02:00

README.md

llama.cpp TTS

This is a tool to demonstrate audio generation capability in llama.cpp via libmtmd. It was added via PR #26254

Note: this tool used to serve as a demo for OuteTTS, but it was converted to a more model-agnostic tool.

Common usage

Simple usage:

llama-tts -hf ggml-org/Qwen3-TTS-12Hz-1.7B-Base-GGUF -p "Hello world" --output out.wav

Common params:

Sampling params such as --top-k, --top-p, --temp, etc.
-n <number_of_frames> limits the output length, e.g. -n 500. Note that how many milliseconds each frame represents varies by model
Core inference params such as -ngl, -b, -ub, etc.

Qwen3-TTS

Available params:

--tts-lang can be zh, en, de, it, pt, es, ja, ko, fr, ru (default: en)
--tts-speaker-file should point to a speaker reference audio file (wav, mp3)

Example usage:

llama-tts -hf ggml-org/Qwen3-TTS-12Hz-1.7B-Base-GGUF \
    -p "Hello world" \
    --tts-lang english \
    --tts-speaker-file speaker.mp3 \
    --output out.wav

Pocket TTS

Available params:

--tts-speaker-file should point to a speaker reference audio file (wav, mp3). It is required, the model produces almost no audio without it
Note: lang is not used, the language is a property of the weights

Example usage:

llama-tts -m pocket-tts.gguf \
    -mm mmproj-pocket-tts.gguf \
    -p "Hello world" \
    --tts-speaker-file speaker.mp3 \
    --output out.wav

Note for GGUF conversion:

The upstream repository holds one complete model per language under languages/, next to a set of shared files at the root. Convert one of the languages/<name> directories, not the root directory:

python convert_hf_to_gguf.py path/to/pocket-tts/languages/english --outfile pocket-tts.gguf
python convert_hf_to_gguf.py path/to/pocket-tts/languages/english --mmproj --outfile mmproj-pocket-tts.gguf