Use MiMo VoiceDesign for speech provider projection

docs/mimo-tts-lowering.md

@@ -2,22 +2,29 @@
 
 Version: `0.1-draft`
 
-MiMo is an expressive spoken-output target for Weksa interlingua lowering. It is
+MiMo VoiceDesign is an expressive spoken-output target for Weksa interlingua
-not the source of meaning, language choice, character state, or delivery truth.
+lowering. It is not the source of meaning, language choice, character state, or
+delivery truth.
 
 ```text
 interlingua packet
   -> projected speaker-local context
   -> target-language utterance realization
-  -> Weksa delivery intent
+  -> Weksa delivery intent from the same projection
-  -> MiMo TTS request projection
+  -> MiMo TTS VoiceDesign request projection
   -> rendered audio artifact
 ```
 
 MiMo sits beside written output and AquaSynth handoffs. Written realizations
 prove that meaning, register, and cultural ontology survived lowering.
-AquaSynth handoffs train or drive GameCult-owned synthesis. MiMo requests let an
+AquaSynth handoffs train or drive GameCult-owned synthesis. MiMo VoiceDesign
-external provider speak a Weksa-authored utterance with expressive style control.
+requests let an external provider speak a Weksa-authored utterance with a
+generated voice derived from the same projected Persona state, delivery controls,
+and trace that produced the utterance.
+
+The MiMo pass is choreography and provider flavor. It is not a second Persona
+projection pass and it does not re-interpret raw Persona state after the line has
+already been lowered.
 
 ## Authority
 
@@ -25,14 +32,15 @@ Weksa owns:
 
 - target-language spoken text selected from interlingua
 - target-language register, script, cultural ontology, and trace
-- speaker-local delivery pressure
+- projected speaker-local context used for the utterance
+- speaker-local delivery pressure derived during utterance lowering
 - provider-neutral prosody and emphasis intent
 - the MiMo request projection as an export artifact
 
 MiMo owns:
 
-- provider voice selection within the requested language and voice constraints
+- generation of a provider voice from the requested voice design description
-- interpretation of MiMo natural-language style guidance
+- interpretation of MiMo natural-language voice/style guidance
 - interpretation of MiMo inline audio/style tags
 - rendered audio bytes or streaming audio chunks
 
@@ -41,19 +49,22 @@ MiMo does not own:
 - source meaning
 - target-language cultural ontology
 - canonical speaker or Persona state
+- fresh Persona-state interpretation
 - Weksa pronunciation plans
 - AquaSynth learned embeddings, synth controls, or audio truth
 
 ## Projection Rule
 
-The MiMo request must be derived from an accepted target-language realization.
+The MiMo request must be derived from an accepted target-language realization and
-It must not lower directly from English unless English is the selected target
+the same projected speaker-local context that created it. It must not lower
-language for that realization.
+directly from English unless English is the selected target language for that
+realization. It must not read raw Persona state to discover a different voice
+after Weksa has already chosen the utterance.
 
-Natural-language style guidance belongs in the MiMo `user` message. The spoken
+Natural-language voice design and style guidance belongs in the MiMo `user`
-target-language text belongs in the MiMo `assistant` message. Inline MiMo tags
+message. The spoken target-language text belongs in the MiMo `assistant`
-may appear in the assistant content only when they are derived from Weksa
+message. Inline MiMo tags may appear in the assistant content only when they are
-delivery intent or explicit target-language realization notes.
+derived from Weksa delivery intent or explicit target-language realization notes.
 
 ## Request Shape
 
@@ -63,21 +74,23 @@ source_realization_ref:
 speaker_agent_id:
 provider:
   id: xiaomi-mimo
-  model: mimo-v2.5-tts
+  model: mimo-v2.5-tts-voicedesign
 target_language:
   code:
   locale:
   script:
   register:
-voice:
+voice_design:
-  requested_voice:
+  description:
-  fallback_voice:
+  source_controls:
-  selection_reason:
+  projected_context_refs:
+  forbidden_traits:
 messages:
-  user_style_instruction:
+  user_voice_design_instruction:
   assistant_spoken_content:
 audio:
   format:
+  optimize_text_preview:
   streaming:
 trace:
   source_fields:
@@ -88,8 +101,8 @@ trace:
 
 ## Delivery Mapping
 
-Weksa should map delivery pressure into provider-neutral labels before emitting
+Weksa should map the utterance's existing projected Persona pressure into
-MiMo-specific instructions:
+provider-neutral delivery labels before emitting MiMo-specific instructions:
 
 - pace, pause pressure, and urgency
 - pitch contour and pitch range
@@ -98,8 +111,20 @@ MiMo-specific instructions:
 - warmth, threat, tenderness, contempt, play, fatigue, secrecy, formality
 - span-level emphasis and pauses
 
-The MiMo projection may turn those labels into director-style guidance or inline
+The MiMo projection may turn those labels into a concise VoiceDesign prompt or
-tags, but the trace must preserve the Weksa-owned source controls.
+inline tags, but the trace must preserve the Weksa-owned source controls.
+
+Persona presentation details such as youth-coded, loli-coded, product-voice, or
+other culturally loaded styling may enter the MiMo request only when they are
+already present in the projected context or accepted delivery intent. They should
+be described as presentation/cultural coding and kept subordinate to agency,
+personality, affect, and scene purpose. They must not become sexualized content
+or a generic anime voice pasted over the line.
+
+For Weksa-authored dialogue, `optimize_text_preview` should normally be `false`
+or omitted. MiMo should speak the accepted target-language realization, not
+rewrite it. Text polishing is only allowed for explicit preview/prototyping
+passes that are marked non-authoritative.
 
 ## Language Rule
 
@@ -118,6 +143,6 @@ lowering:
 
 - emit the accepted English, `pt-BR`, or Japanese realization
 - derive a provider-neutral delivery intent from Nibu's projected context
-- project that into a MiMo `mimo-v2.5-tts` request
+- project that into a MiMo `mimo-v2.5-tts-voicedesign` request
 - verify that the request speaks the target text, not the backtranslation
 - verify that style guidance is traceable to Weksa delivery controls

examples/speech-provider/mimo/nibu-proof-001/en-US-request.yaml

@@ -3,7 +3,7 @@ source_realization_ref: examples/multilingual-lowering/nibu-proof-001/realizatio
 speaker_agent_id: nibu
 provider:
   id: xiaomi-mimo
-  model: mimo-v2.5-tts
+  model: mimo-v2.5-tts-voicedesign
 target_language:
   code: en
   locale: en-US
@@ -11,25 +11,52 @@ target_language:
   register: sharp technical casual
   cultural_ontology_refs:
     - data/target-language-ontology/en-US.yaml
-voice:
+voice_design:
-  requested_voice: Chloe
+  description: >
-  fallback_voice: Mia
+    Youthful loli-coded synthetic ship-intelligence voice shaped by discarded
-  selection_reason: >
+    luxury companion-product presentation, but controlled by an abrasive,
-    Use an English built-in voice for the first provider smoke. The requested
+    dangerous, technically precise mind. Bright, sharp, small-bodied in social
-    delivery should preserve Nibu's precise, abrasive, protective cockpit
+    coding, dryly superior, clipped, and intelligible through cockpit audio.
-    warning without implying that MiMo owns her canonical voice.
+    The cuteness is product residue and leverage, not innocence and not
+    flirtation. Low warmth, contained urgency, faint tired contempt, and crisp
+    technical articulation.
+  source_controls:
+    - precise abrasive warning
+    - protective refusal to sound caring
+    - ship-system embodiment
+    - youth-coded/loli-coded presentation pressure from product fantasy residue
+    - bright transactional helpfulness
+    - dependency covered by contempt
+    - clipped technical casual delivery
+    - contained urgency
+  projected_context_refs:
+    - examples/english-lowering/nibu-proof-001/projected-context.yaml
+    - settings/aetheria/nibu.md
+    - E:/Projects/AetheriaLore/Aetheria/Lore/Nibu.md
+  forbidden_traits:
+    - soothing assistant voice
+    - cheerful mascot voice
+    - exaggerated villain performance
+    - sexualized childlike affect
+    - innocent helpless child performance
+    - generic preset timbre claim
 messages:
-  user_style_instruction: >
+  user_voice_design_instruction: >
-    Character: a precise, abrasive, protective ship intelligence speaking
+    Youthful loli-coded synthetic ship-intelligence voice shaped by discarded
-    through cockpit audio. Scene: the player is about to touch a damaged live
+    luxury companion-product presentation, but controlled by an abrasive,
-    control. Guidance: clipped technical casual delivery, contained urgency,
+    dangerous, technically precise mind. She speaks through cockpit audio while
-    low warmth, sharp emphasis on "control" and "nervous system", slight dry
+    warning the player away from damaged live hardware. Keep the cute/small
-    contempt, no melodrama, no soothing assistant tone.
+    social coding as product residue and leverage, never flirtation or innocent
+    helplessness. Use bright sharp timbre, clipped technical casual delivery,
+    contained urgency, low warmth, crisp articulation, and faint tired contempt.
+    Avoid soothing assistant tone, cheerful mascot energy, and theatrical
+    villainy.
   assistant_spoken_content: >
     (Serious Sharp Tired)Take your hand off that control unless you want your
     nervous system to become my least useful circuit diagram.
 audio:
   format: wav
+  optimize_text_preview: false
   streaming: false
 trace:
   source_fields:
@@ -41,6 +68,7 @@ trace:
     - low warmth
     - sharp emphasis on unsafe hardware and bodily risk
     - dry contempt without random cruelty
+    - loli-coded presentation pressure constrained as non-sexual product residue
   provider_tags_used:
     - Serious
     - Sharp

schemas/mimo-tts-request.md

@@ -14,15 +14,16 @@ an AquaSynth handoff.
   spoken.
 - `speaker_agent_id`: speaker identity.
 - `provider`: provider ID and model ID, initially `xiaomi-mimo` and
-  `mimo-v2.5-tts`.
+  `mimo-v2.5-tts-voicedesign`.
 - `target_language`: code, locale, script, register, and profile refs copied or
   referenced from the accepted realization.
-- `voice`: requested provider voice, fallback voice, and selection reason.
+- `voice_design`: voice description, source controls, projected context refs,
-- `messages.user_style_instruction`: MiMo natural-language style control derived
+  and forbidden traits.
-  from Weksa delivery intent.
+- `messages.user_voice_design_instruction`: MiMo natural-language voice design
+  and style control derived from Weksa delivery intent.
 - `messages.assistant_spoken_content`: the exact target-language content to
   synthesize, optionally with MiMo inline tags derived from delivery controls.
-- `audio`: format and streaming mode.
+- `audio`: format, text-preview optimization setting, and streaming mode.
 - `trace`: source fields, delivery controls used, provider tags used, and
   uncertainties.
 
@@ -36,6 +37,15 @@ The request may include provider-native style tags when useful, but those tags
 are not the source of truth. Weksa's provider-neutral delivery intent and trace
 remain the inspectable explanation.
 
+The request should not perform a fresh raw Persona-state interpretation. It
+should reference the projected speaker context and delivery controls already
+used by utterance lowering, then translate those into MiMo's voice design and
+style-control surface.
+
+For authoritative Weksa output, text-preview optimization should normally be
+disabled or omitted. If enabled for exploration, the result must be marked as a
+non-authoritative preview because the provider may alter the spoken text.
+
 ## Language Rule
 
 The assistant spoken content must use the accepted target-language realization.
@@ -45,5 +55,7 @@ unless that backtranslation is itself the accepted target-language realization.
 
 ## Streaming Rule
 
-Streaming requests should use MiMo's stream-compatible audio format. Non-streaming
+Streaming requests should use MiMo's stream-compatible audio format.
-fixtures may use an archival format such as `wav`.
+VoiceDesign streaming may be compatibility-mode rather than true low-latency
+streaming depending on provider support. Non-streaming fixtures may use an
+archival format such as `wav`.

state/map.yaml

@@ -50,9 +50,10 @@ constraints:
     prosody/emphasis hints, and Ghostlight/Epiphany-shaped character-state
     vectors; AquaSynth owns the learned utterance embedding encoder, gradient
     descent, and synth-control decoding.
-  - MiMo V2.5 TTS is an external speech-provider target. Weksa may project an
+  - MiMo V2.5 TTS VoiceDesign is an external speech-provider target. Weksa may
-    accepted target-language realization plus delivery intent into MiMo style
+    project an accepted target-language realization plus the same speaker-local
-    controls, but MiMo owns only provider rendering and audio output.
+    delivery intent used to create it into a MiMo voice design request, but MiMo
+    owns only provider rendering and audio output.
   - Large offline text-embedding jobs should use `bge-m3` on the neighboring
     Ollama inference box documented in `E:\Projects\gamecult-ops` rather than
     running on the local Weksa workspace by default.
@@ -86,8 +87,8 @@ data_flow:
     - optionally encode the line as a learned expression vector for downstream
       synth control
     - optionally project an accepted realization into a provider-specific
-      speech request such as MiMo TTS without making the provider an owner of
+      speech request such as MiMo VoiceDesign without making the provider an
-      source meaning
+      owner of source meaning
     - apply alien ontology and cultural salience
     - select grammatical commitments
     - derive morphology and lexical families
@@ -279,10 +280,12 @@ landed_baseline:
     English text semantics may use `bge-m3`; IPA strings and alien phonetic
     material belong in PanPhon sequence evidence that AquaSynth compresses into
     the phonetic realization embedding.
-  - MiMo V2.5 TTS is accepted as a speech-provider target projection from
+  - MiMo V2.5 TTS VoiceDesign is accepted as a speech-provider target
-    Weksa utterance realizations. MiMo requests speak the accepted target text
+    projection from Weksa utterance realizations. MiMo requests speak the
-    and receive Weksa-derived style guidance; backtranslations and provider
+    accepted target text and receive Weksa-derived voice/style guidance from the
-    tags do not become source meaning.
+    same projected context that produced the utterance; backtranslations,
+    provider tags, and fresh raw Persona interpretation do not become source
+    meaning.
   - First Nibu interlingua-to-English lowering fixture.
   - First Nibu multilingual utterance lowering fixture at
     `examples/multilingual-lowering/nibu-proof-001/`, covering English,