catalog(dia2): expose full /tts control surface + stable predefined voices

Repoint both dia2 entries from /v1/audio/speech to the wrapper's richer /tts
endpoint (CustomTTSRequest), exposing the levers that fix the random-voice
problem: voice_mode, clone_reference_filename, cfg_scale, temperature, top_p,
cfg_filter_top_k, speed_factor, seed, split_text, chunk_size, transcript,
max_tokens. All defaults are the wrapper's Pydantic blessed values (cfg 3.0 /
temp 1.3 / top_p 0.95 / top_k 35 / speed_factor 0.94 / chunk 300). Fields
grouped (basic/sampling/advanced). dia2 -> version 2 (field-shape change).

Voice stability: Dia2 samples a random speaker per call unless anchored. The
43 curated voices baked at /app/voices aren't reachable from /tts's clone path
(reference_audio dir only), so they're staged into reference_audio; the
clone_reference_filename picker now sources /get_reference_files. voice_mode=
clone + a reference filename pins voice/gender. Verified /tts clone end-to-end
(HTTP 200, Ogg/Opus 24 kHz). README documents the staging + two-instance shape.

docs/asset-engine/services.yaml

@@ -1248,77 +1248,159 @@ services:
       turn-taking in one pass with [S1]/[S2] speaker tags and nonverbals
       (laughs)/(coughs)/(sighs). 24 kHz. Served via devnen/Dia-TTS-Server.
     category: tts
-    version: 1
+    version: 2
     status: ready
     host: irv-ml1
     lifecycle:
       stack: dia
       vram_gb: 8
       gpu_device_id: 0
-    endpoint: http://10.100.79.3:8200/v1/audio/speech
+    endpoint: http://10.100.79.3:8200/tts
     method: POST
     content_type: application/json
     model:
       id: nari-labs/Dia2-2B
       revision: null
       image: local/dia:v2
+    section_groups:
+      - id: basic
+        label: Text & voice
+      - id: sampling
+        label: Sampling
+        hint: Wrapper-canonical Dia2 defaults; lower temperature/cfg for steadier output.
+      - id: advanced
+        label: Advanced
     fields:
-      - name: input
+      - name: text
         type: textarea
         label: Text ([S1]/[S2] dialogue + nonverbals)
+        section: basic
         required: true
         max_length: 5000
         default: "[S1] Hello Dia2!"  # canonical: nari-labs/dia2 README usage example
         description: >
           [S1]/[S2] tags mark speaker turns; nonverbals like (laughs),
           (coughs), (sighs), (clears throat) go inline.
-      - name: voice
+      - name: voice_mode
         type: select
-        label: Voice / mode
+        label: Voice mode
-        options: [dialogue, single_s1, single_s2, predefined]
+        section: basic
-        default: dialogue
+        options: [single_s1, single_s2, dialogue, clone]
+        default: single_s1
         description: >
-          Speaker mode from the model's voice set. `clone` (prefix_speaker)
+          Canonical default single_s1. Unconditioned modes (single_s1/s2,
-          needs a reference clip, so it isn't a plain picker choice here.
+          dialogue) sample a RANDOM speaker each call — gender varies. For a
-      - name: response_format
+          STABLE voice, set this to clone and pick a clone_reference_filename.
+      - name: clone_reference_filename
         type: select
+        label: Voice (clone reference)
+        section: basic
+        optional: true
+        source_url: http://10.100.79.3:8200/get_reference_files
+        source_jsonpath: $[*]
+        description: >
+          Required when voice_mode=clone. Lists the reference_audio library —
+          43 curated voices (singles + [S1]/[S2] dialogue pairs like
+          Abigail_Taylor.wav) staged there from the image's /app/voices, plus
+          any you upload. Pins voice/gender deterministically.
+      - name: transcript
+        type: textarea
+        label: Reference transcript
+        section: advanced
+        optional: true
+        description: >
+          Optional transcript of a custom clone reference (overrides its local
+          .txt sidecar). Leave blank for predefined voices.
+      - name: output_format
+        type: select
+        section: basic
         options: [opus, wav]
         default: opus
-        description: 24 kHz output (Dia2; note dia1 was 44.1 kHz).
+        description: 24 kHz (Dia2).
-      - name: speed
+      - name: cfg_scale
         type: slider
+        section: sampling
+        min: 1.0
+        max: 5.0
+        step: 0.1
+        default: 3.0
+        description: Classifier-free guidance scale (wrapper default 3.0).
+      - name: temperature
+        type: slider
+        section: sampling
+        min: 0.1
+        max: 1.5
+        step: 0.05
+        default: 1.3
+        description: Sampling temperature; lower = steadier (wrapper default 1.3).
+      - name: top_p
+        type: slider
+        section: sampling
+        min: 0.1
+        max: 1.0
+        step: 0.01
+        default: 0.95
+      - name: cfg_filter_top_k
+        type: number
+        section: sampling
+        required: false
+        default: 35
+        description: Top-k filter for CFG guidance (1–100; wrapper default 35).
+      - name: speed_factor
+        type: slider
+        section: sampling
         min: 0.5
         max: 2.0
-        step: 0.05
+        step: 0.01
-        default: 1.0
+        default: 0.94
-        description: Post-generation playback speed multiplier.
+        description: Playback speed (wrapper canonical default 0.94).
       - name: seed
         type: number
+        section: sampling
         required: false
         default: -1
-        description: -1 = random; any integer for repeatable (not byte-exact) output.
+        description: -1 = random; a fixed integer repeats the same take.
+      - name: split_text
+        type: bool
+        section: advanced
+        default: true
+        description: Auto-split long text into chunks.
+      - name: chunk_size
+        type: slider
+        section: advanced
+        min: 100
+        max: 1000
+        step: 10
+        default: 300
+        description: Target chunk length in chars when splitting (wrapper default 300).
+      - name: max_tokens
+        type: number
+        section: advanced
+        required: false
+        description: Max audio tokens per chunk; omit to use the model's internal default.
     response:
       type: audio
-      mime_from_field: response_format
+      mime_from_field: output_format
     reproducibility:
       seedable: true
       deterministic: false
       notes: >
-        Seed gives consistent voice/prosody but NOT byte-exact output (Dia2 is
+        Per the dia2 README, voices vary per generation unless anchored — set
-        temperature-sampled). Raw-bytes response carries no seed echo, so no
+        voice_mode=clone + a clone_reference_filename for a stable voice/gender.
-        seed_field. A richer custom /tts endpoint exposes
+        seed (-1=random) repeats a take but doesn't choose the voice;
-        cfg_scale/temperature/top_p/cfg_filter_top_k.
+        temperature-sampled, not byte-exact; raw bytes -> no seed_field. All
+        field defaults are the wrapper's CustomTTSRequest Pydantic blessed values.
     estimated_latency:
       cold_start_s: 30
       warm_per_unit: "dialogue one-pass; ~realtime on the 3090"
     license: "Apache-2.0 (Dia2 weights); MIT (devnen wrapper)"
     notes: |
-      One of two fixed-model instances in the `dia` stack; sibling dia2-1b
+      Routes to the wrapper's richer /tts endpoint (full control surface:
-      (:8202). `docker compose up` on the stack starts BOTH services — the
+      cfg_scale/temperature/top_p/cfg_filter_top_k/voice_mode/clone) rather than
-      lifecycle vram_gb here is this instance alone (~8 GB); budget for both
+      the OpenAI /v1/audio/speech. One of two fixed-model instances in the `dia`
-      if gating the whole stack. Image local/dia:v2 = upstream devnen wrapper
+      stack; sibling dia2-1b (:8202). `docker compose up` starts BOTH (~8 GB
-      + the dia2 package baked in (see stacks/dia/dia2-image/). Verified
+      here; budget both if gating the whole stack). Image local/dia:v2 (see
-      end-to-end 2026-05-31 (HTTP 200, Ogg/Opus 24 kHz).
+      stacks/dia/dia2-image/). Verified end-to-end 2026-05-31.
 
   - id: dia2-1b
     name: Dia2 1B (Streaming)
@@ -1327,73 +1409,156 @@ services:
       dialogue + nonverbals as dia2-2b, lower latency / lighter weight. 24 kHz.
       Served via devnen/Dia-TTS-Server.
     category: tts
-    version: 1
+    version: 2
     status: ready
     host: irv-ml1
     lifecycle:
       stack: dia
       vram_gb: 5
       gpu_device_id: 0
-    endpoint: http://10.100.79.3:8202/v1/audio/speech
+    endpoint: http://10.100.79.3:8202/tts
     method: POST
     content_type: application/json
     model:
       id: nari-labs/Dia2-1B
       revision: null
       image: local/dia:v2
+    section_groups:
+      - id: basic
+        label: Text & voice
+      - id: sampling
+        label: Sampling
+        hint: Wrapper-canonical Dia2 defaults; lower temperature/cfg for steadier output.
+      - id: advanced
+        label: Advanced
     fields:
-      - name: input
+      - name: text
         type: textarea
         label: Text ([S1]/[S2] dialogue + nonverbals)
+        section: basic
         required: true
         max_length: 5000
         default: "[S1] Hello Dia2!"  # canonical: nari-labs/dia2 README usage example
         description: >
           [S1]/[S2] tags mark speaker turns; nonverbals like (laughs),
           (coughs), (sighs), (clears throat) go inline.
-      - name: voice
+      - name: voice_mode
         type: select
-        label: Voice / mode
+        label: Voice mode
-        options: [dialogue, single_s1, single_s2, predefined]
+        section: basic
-        default: dialogue
+        options: [single_s1, single_s2, dialogue, clone]
+        default: single_s1
         description: >
-          Speaker mode from the model's voice set. `clone` (prefix_speaker)
+          Canonical default single_s1. Unconditioned modes (single_s1/s2,
-          needs a reference clip, so it isn't a plain picker choice here.
+          dialogue) sample a RANDOM speaker each call — gender varies. For a
-      - name: response_format
+          STABLE voice, set this to clone and pick a clone_reference_filename.
+      - name: clone_reference_filename
         type: select
+        label: Voice (clone reference)
+        section: basic
+        optional: true
+        source_url: http://10.100.79.3:8202/get_reference_files
+        source_jsonpath: $[*]
+        description: >
+          Required when voice_mode=clone. Lists the reference_audio library —
+          43 curated voices (singles + [S1]/[S2] dialogue pairs like
+          Abigail_Taylor.wav) staged there from the image's /app/voices, plus
+          any you upload. Pins voice/gender deterministically.
+      - name: transcript
+        type: textarea
+        label: Reference transcript
+        section: advanced
+        optional: true
+        description: >
+          Optional transcript of a custom clone reference (overrides its local
+          .txt sidecar). Leave blank for predefined voices.
+      - name: output_format
+        type: select
+        section: basic
         options: [opus, wav]
         default: opus
-        description: 24 kHz output.
+        description: 24 kHz (Dia2).
-      - name: speed
+      - name: cfg_scale
         type: slider
+        section: sampling
+        min: 1.0
+        max: 5.0
+        step: 0.1
+        default: 3.0
+        description: Classifier-free guidance scale (wrapper default 3.0).
+      - name: temperature
+        type: slider
+        section: sampling
+        min: 0.1
+        max: 1.5
+        step: 0.05
+        default: 1.3
+        description: Sampling temperature; lower = steadier (wrapper default 1.3).
+      - name: top_p
+        type: slider
+        section: sampling
+        min: 0.1
+        max: 1.0
+        step: 0.01
+        default: 0.95
+      - name: cfg_filter_top_k
+        type: number
+        section: sampling
+        required: false
+        default: 35
+        description: Top-k filter for CFG guidance (1–100; wrapper default 35).
+      - name: speed_factor
+        type: slider
+        section: sampling
         min: 0.5
         max: 2.0
-        step: 0.05
+        step: 0.01
-        default: 1.0
+        default: 0.94
-        description: Post-generation playback speed multiplier.
+        description: Playback speed (wrapper canonical default 0.94).
       - name: seed
         type: number
+        section: sampling
         required: false
         default: -1
-        description: -1 = random; any integer for repeatable (not byte-exact) output.
+        description: -1 = random; a fixed integer repeats the same take.
+      - name: split_text
+        type: bool
+        section: advanced
+        default: true
+        description: Auto-split long text into chunks.
+      - name: chunk_size
+        type: slider
+        section: advanced
+        min: 100
+        max: 1000
+        step: 10
+        default: 300
+        description: Target chunk length in chars when splitting (wrapper default 300).
+      - name: max_tokens
+        type: number
+        section: advanced
+        required: false
+        description: Max audio tokens per chunk; omit to use the model's internal default.
     response:
       type: audio
-      mime_from_field: response_format
+      mime_from_field: output_format
     reproducibility:
       seedable: true
       deterministic: false
       notes: >
-        Same determinism story as dia2-2b (temperature-sampled, seed gives
+        Same story as dia2-2b: voices vary per generation unless anchored
-        consistent prosody not byte-exact). No seed echo -> no seed_field.
+        (voice_mode=clone + clone_reference_filename); temperature-sampled,
+        not byte-exact; raw bytes -> no seed_field. Defaults are the wrapper's
+        CustomTTSRequest Pydantic blessed values.
     estimated_latency:
       cold_start_s: 30
       warm_per_unit: "streaming; lower latency than dia2-2b"
     license: "Apache-2.0 (Dia2 weights); MIT (devnen wrapper)"
     notes: |
-      Sibling of dia2-2b in the same `dia` stack (see its notes for the
+      Routes to the wrapper's richer /tts endpoint (same control surface as
-      single-model-per-endpoint rationale and the both-start-together caveat).
+      dia2-2b). Sibling of dia2-2b in the same `dia` stack (see its notes for
-      Image local/dia:v2. Verified end-to-end 2026-05-31 (HTTP 200, Ogg/Opus
+      the single-model-per-endpoint rationale + both-start-together caveat).
-      24 kHz).
+      Image local/dia:v2. Verified end-to-end 2026-05-31.
 
   - id: csm
     name: Sesame CSM (conversational)

stacks/dia/README.md

@@ -54,15 +54,50 @@ scripts/deploy-stack.sh irv-ml1 dia
 First boot pulls the checkpoint (~6-10 GB) into `DIA_CACHE_DIR` and can
 take several minutes; the healthcheck's 600 s `start_period` covers it.
 
+## Deployment shape (as of 2026-05-31)
+
+This stack now runs **two fixed-model instances** from `local/dia:v2`
+(the dia2-capable image — see [`dia2-image/Dockerfile`](dia2-image/Dockerfile)):
+
+| service | model | port | notes |
+|---|---|---|---|
+| `dia2-2b` | nari-labs/Dia2-2B | 8200 | highest quality |
+| `dia2-1b` | nari-labs/Dia2-1B | 8202 | streaming / lower latency |
+
+The wrapper is single-model and ignores per-request model selection, so
+one fixed instance per model is the only way to offer both as real
+asset-engine choices. Legacy Dia 1.6B was retired. `local/dia:v2` is built
+in two stages: upstream wrapper → `local/dia:v1`, then `dia2-image/` layers
+in the dia2 package + its deps. Each instance pins its model via a mounted
+`/opt/docker/conf/dia2-*/config.yaml`.
+
+## Voices — stabilizing the random-voice behavior
+
+Dia2 samples a **random speaker (random gender) per generation** unless
+anchored (per the dia2 README: "voices vary per generation … use with
+prefix … for stable output"). To pin a voice, use the richer **`/tts`**
+endpoint with `voice_mode: clone` + a `clone_reference_filename`.
+
+The image bakes **43 curated voices** at `/app/voices` (singles +
+`[S1]/[S2]` dialogue pairs like `Abigail_Taylor.wav`), but `/tts`'s clone
+path only reads the **reference_audio** dir — so they're **staged** into it:
+
+```bash
+# one-time per host (writes through the shared /worktank/dia/reference_audio mount):
+docker exec dia2-2b sh -c 'cp -n /app/voices/* /app/reference_audio/'
+```
+
+After staging, `GET /get_reference_files` lists them and asset-engine's
+`clone_reference_filename` picker (sourced from that endpoint) offers a
+stable, known voice. Restic-included, so it survives once staged.
+
 ## Notes
 
-- **Pin `DIA_SHA`** to a full 40-char commit before relying on this —
+- **Model switching** within an instance is config.yaml-driven (the mounted
-  `.env.example` ships `main` for convenience, but `main` is not
+  `config.yaml` pins `model.repo_id`); the Web UI can hot-swap live but only
-  reproducible (chatterbox learned this when an upstream restructure
+  the mounted config survives recreate.
-  broke its `main` build).
+- Endpoints: `/tts` (rich: cfg_scale/temperature/top_p/cfg_filter_top_k/
-- **Model switching** is config.yaml-driven in the wrapper, or live from
+  voice_mode/clone — what asset-engine targets), `/v1/audio/speech`
-  the Web UI at `http://10.100.79.3:8200/`. To pin a non-default model
+  (OpenAI-compat; its `voice` param also resolves predefined voices by name),
-  declaratively, mount a host `config.yaml` (see the commented volume in
+  `/get_reference_files`, `/get_predefined_voices`, `/health`,
-  `compose.yaml`).
+  `/api/model-status`, `/api/model-info`.
-- Endpoints: `/v1/audio/speech` (OpenAI-compat), `/health` (liveness),
-  `/api/model-status` (download/load progress), `/api/model-info`.