Ettore Di Giacinto db09452d54 feat(tts): support multi-reference personalities ...

Saved profiles previously resolved to one audio path and transcript, so
cloning backends could not use several examples of one personality.

Store ordered audio and transcript pairs while preserving the legacy
first-reference fields. Fish Speech and audio.cpp receive all pairs,
including on distributed workers. Other backends retain their
single-reference behavior.

Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

2026-09-11 21:56:08 +00:00

..

.gitignore

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

audio_io_ctest.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

audio_io.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

audio_io.h

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

audio_units_test.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

audio_units.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

audio_units.h

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

capability_routing_test.cpp

chore: ⬆️ Update 0xShug0/audio.cpp to 3407559d7c83b543bd60ca8fa2b630374e71083f (#11474)

2026-08-18 09:46:56 +02:00

capability_routing.cpp

chore: ⬆️ Update 0xShug0/audio.cpp to 3407559d7c83b543bd60ca8fa2b630374e71083f (#11474)

2026-08-18 09:46:56 +02:00

capability_routing.h

chore: ⬆️ Update 0xShug0/audio.cpp to 3407559d7c83b543bd60ca8fa2b630374e71083f (#11474)

2026-08-18 09:46:56 +02:00

CMakeLists.txt

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

family_gate_test.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

family_gate.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

family_gate.h

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

generation_request_ctest.cpp

feat(tts): support multi-reference personalities

2026-09-11 21:56:08 +00:00

generation_request.cpp

feat(tts): support multi-reference personalities

2026-09-11 21:56:08 +00:00

generation_request.h

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

grpc-server.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

inference_lane_test.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

inference_lane.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

inference_lane.h

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

live_watchdog_test.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

live_watchdog.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

live_watchdog.h

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

loaded_model.cpp

feat(audio-cpp): add ROCm backend image

2026-09-11 21:53:43 +00:00

loaded_model.h

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

Makefile

fix(audio-cpp): normalize HIP target list

2026-09-11 21:53:43 +00:00

model_options_test.cpp

feat(audio-cpp): add ROCm backend image

2026-09-11 21:53:43 +00:00

model_options.cpp

feat(audio-cpp): add ROCm backend image

2026-09-11 21:53:43 +00:00

model_options.h

feat(audio-cpp): add ROCm backend image

2026-09-11 21:53:43 +00:00

package.sh

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

result_map_ctest.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

result_map.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

result_map.h

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

run.sh

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

stem_selection_test.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

stem_selection.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

stem_selection.h

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

stream_delta_test.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

stream_delta.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

stream_delta.h

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

streaming_driver_ctest.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

transcript_assembly_test.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

transcript_assembly.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

transcript_assembly.h

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

upstream_absence_ctest.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

wav_header_test.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

wav_header.cpp

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00

wav_header.h

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00