code wiki / voice

topic: voice

13 modules sharing the voice name family (derived from the tree's prefix discipline).

The 'voice' topic family in the Nishi sovereign ecosystem focuses on creating and evaluating realistic audio synthesis and encoding. It includes modules like nx_voice_clone_synth, which generates new audio, and nx_voice_codec_v2, the core LPC-residual voice codec that enables efficient encoding and decoding of PCM frames. The nx_voice_eval module serves as an objective evaluator, assessing the naturalness of synthesized audio, ensuring the system maintains high-quality voice reproduction across its modular architecture.

auto-narrated by the local model from this topic's module headers; links verified against the wiki index.

narrated overview -- maintained by the narration lane, module links verified against this wiki.

moduledescriptionlinesfuncs
nx_voice_clone_synth.nxVOICE-CLONE-001 rung 2: CREATE new audio in a782
nx_voice_clone_synth_gate.nxREFEREE for VOICE-CLONE-001 rung 2 (create).1555
nx_voice_codec.nxNishiVoice v1: the composition primitive that3536
nx_voice_codec_tier.nxtier-adaptive parameter selection.1092
nx_voice_codec_v1_adapter.nxwraps NishiVoice v1 behind nx_codec.2305
nx_voice_codec_v2.nxNishiVoice v2: the REAL LPC-residual voice codec the v1 skeleton described but didn't build.13510
nx_voice_codec_v2_gate.nxproves the v2 voice codec (nx_voice_codec_v2) as a real encode/decode PAIR: PCM frame ->657
nx_voice_eval.nxTHE RULER (voice-realism census V0): a sovereign OBJECTIVE audio-naturalness evaluator so1454
nx_voice_fec.nxforward error correction for the Nishi voice1927
nx_voice_frame.nxPhase 4a foundation: sovereign voice-codec1906
nx_voice_read.nxVOICE-CLONE-001 rung 5-FUSE: a CLONED VOICE READING WORDS.823
nx_voice_read_gate.nxREFEREE for VOICE-CLONE-001 rung 5-FUSE (voice reads words).1558
nx_voice_v2_gate.nxproves the NishiVoice v2 q/bit path end-to-end: real LPC residual + entropy coding + inverse1178