Namespace Mabs.AudioCpp
Classes
- AlignmentClient
Forced alignment against
POST /v1/audio/alignments(multipart only).
- AudioCppClient
Client for the audio.cpp server protocol. One instance maps to one server base URL and is thread-safe; share it. The per-area sub-clients (Speech, Transcriptions, Alignments, Tasks, Recipes) carry the endpoint groups; readiness, model, voice and unload routes sit directly on this type.
- RecipeClient
Multi-model recipes against
POST /v1/recipes/run. Role-specific option prefixes (tts.,avatar.,conversation., …) are the caller's responsibility: put them directly in Options keys, e.g.options["avatar.reference_image_file"] = "/path/portrait.png".
- SpeechClient
Speech synthesis against
POST /v1/audio/speechand/v1/audio/speech/live.
- TaskClient
Generic framework tasks against
POST /v1/tasks/run,/v1/tasks/streamand/v1/tasks/batch.
- TranscriptionClient
Transcription against
POST /v1/audio/transcriptions, its details/batch/live siblings, and SSE streaming.