mirror of
https://github.com/mudler/LocalAI.git
synced 2026-08-01 19:09:42 -04:00
3bb0d1cb49
* feat(backend): add moss-tts-cpp text-to-speech backend Add a Go + purego backend wrapping the moss-tts.cpp ggml port of the OpenMOSS MOSS-TTS-Local v1.5 text-to-speech model (GPT-J local transformer decoded through MOSS-Audio-Tokenizer-v2), producing 48 kHz stereo audio with optional reference-audio voice cloning. Mirrors the qwen3-tts-cpp backend: dlopen the static-ggml shared library, bind the moss-tts.cpp C-API via purego, and serve the gRPC TTS method. A thin C shim holds the pipeline handle and copies engine PCM into a Go-freeable buffer. Wires the CI registration: backend-matrix.yml (CPU, CUDA 12/13, Intel SYCL f16/f32, Vulkan, ROCm, NVIDIA L4T, plus Darwin metal), backend/index.yaml metas and image entries pointing at mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF, the root Makefile build targets, and the changed-backends.js path mapping. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs: list the moss-tts-cpp backend among the LocalAI-maintained engines Add moss-tts.cpp to the README "Backends built by us" table, the Text-to-Speech compatibility table, and the reference-audio voice-cloning backend list, so the new backend is documented alongside its peers. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(moss-tts-cpp): pin moss-tts.cpp to the squashed single-commit release moss-tts.cpp history was collapsed to a single commit; repoint MOSSTTS_CPP_VERSION to ee722b8e9205ee9b1b1c398a4e87e4e393e9be41. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(moss-tts-cpp): add the moss-tts-cpp-development gallery meta The gallery had the -development image entries but no matching -development meta anchor (as locate-anything-cpp and depth-anything-cpp have), so the master build was not installable as a gallery backend. Add moss-tts-cpp-development mirroring the production meta with the -development capability image names. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
50 lines
1.7 KiB
Go
50 lines
1.7 KiB
Go
package main
|
|
|
|
import (
|
|
"path/filepath"
|
|
|
|
pb "github.com/mudler/LocalAI/pkg/grpc/proto"
|
|
. "github.com/onsi/ginkgo/v2"
|
|
. "github.com/onsi/gomega"
|
|
)
|
|
|
|
// These specs pin the voice-selection logic in resolveRequest, in particular
|
|
// the config-level audio_path (tts.audio_path -> ModelOptions.AudioPath) being
|
|
// used as the default voice-cloning reference. MOSS-TTS-Local takes the
|
|
// reference as a WAV path (the engine decodes it), so resolveRequest is pure
|
|
// path logic and needs no model / C library.
|
|
var _ = Describe("resolveRequest voice/clone selection", func() {
|
|
var dir, refWav string
|
|
|
|
BeforeEach(func() {
|
|
dir = GinkgoT().TempDir()
|
|
refWav = filepath.Join(dir, "ref.wav")
|
|
})
|
|
|
|
It("uses the config audio_path as the clone reference when Voice is empty", func() {
|
|
m := &MossTtsCpp{audioPath: refWav}
|
|
ref, seed := m.resolveRequest(&pb.TTSRequest{Text: "hi"})
|
|
Expect(ref).To(Equal(refWav))
|
|
Expect(seed).To(Equal(0)) // zero-value loadOptions seed
|
|
})
|
|
|
|
It("lets a per-request audio Voice override audio_path", func() {
|
|
other := filepath.Join(dir, "other.wav")
|
|
m := &MossTtsCpp{audioPath: refWav}
|
|
ref, _ := m.resolveRequest(&pb.TTSRequest{Text: "hi", Voice: other})
|
|
Expect(ref).To(Equal(other))
|
|
})
|
|
|
|
It("does not clone for a bare-token Voice, falling back to audio_path", func() {
|
|
m := &MossTtsCpp{audioPath: refWav}
|
|
ref, _ := m.resolveRequest(&pb.TTSRequest{Text: "hi", Voice: "serena"})
|
|
Expect(ref).To(Equal(refWav))
|
|
})
|
|
|
|
It("reads a per-request seed override from params", func() {
|
|
m := &MossTtsCpp{opts: loadOptions{seed: -1}}
|
|
_, seed := m.resolveRequest(&pb.TTSRequest{Text: "hi", Params: map[string]string{"seed": "123"}})
|
|
Expect(seed).To(Equal(123))
|
|
})
|
|
})
|