diff --git a/docs/asset-engine/services.yaml b/docs/asset-engine/services.yaml
index ae4c2ef..afa44db 100644
--- a/docs/asset-engine/services.yaml
+++ b/docs/asset-engine/services.yaml
@@ -26,7 +26,7 @@ services:
       60+ built-in voices in 8 languages. Voice mixing via inline weights.
       OpenAI-compatible /v1/audio/speech.
     category: tts
-    version: 1
+    version: 2
     host: irv-ml1
     endpoint: http://10.100.79.3:8193/v1/audio/speech
     method: POST
@@ -54,6 +54,35 @@ services:
         type: select
         options: [wav, mp3, opus, flac, pcm]
         default: wav
+      - name: speed
+        type: slider
+        label: Speed
+        required: false
+        min: 0.25
+        max: 4.0
+        step: 0.05
+        default: 1.0
+        description: Playback speed multiplier. 1.0 is natural.
+      - name: volume_multiplier
+        type: slider
+        label: Volume
+        required: false
+        min: 0.5
+        max: 2.0
+        step: 0.05
+        default: 1.0
+        description: >
+          Output gain. Useful for level-matching against music beds.
+          Upstream is unbounded; UI bounds (0.5–2.0) are a sensible default —
+          override the slider client-side if you need extremes.
+      - name: lang_code
+        type: text
+        label: Language code
+        required: false
+        description: >
+          Optional language hint (e.g. "a" for American English). When unset,
+          kokoro infers from the first letter of the voice name. Set when text
+          contains code-switching kokoro guesses wrong on.
       - name: stream
         type: bool
         default: false
@@ -75,6 +104,81 @@ services:
     notes: |
       Voice mixing: voice="name1(w1)+name2(w2)+..." normalizes weights.
       Custom voices persist at /worktank/kokoro/user_voices (bind-mounted).
+      v2 (2026-05-11): added speed, volume_multiplier, lang_code per
+      kokoro's OpenAPI surface.
+
+  - id: kokoro-captioned
+    name: Kokoro Captioned Speech
+    description: >
+      Kokoro TTS with word-level timestamps returned alongside the audio.
+      For subtitle generation and video sync. Same model as `kokoro`; this
+      is a separate catalog entry because the response shape is structured
+      JSON (audio inline + timestamps), not raw audio bytes.
+    category: tts
+    version: 1
+    host: irv-ml1
+    endpoint: http://10.100.79.3:8193/dev/captioned_speech
+    method: POST
+    content_type: application/json
+    model:
+      id: hexgrad/Kokoro-82M
+      revision: null
+      image: ghcr.io/remsky/kokoro-fastapi-gpu:v0.2.4-master
+    fields:
+      - name: input
+        type: textarea
+        label: Text
+        required: true
+        max_length: 5000
+      - name: voice
+        type: select
+        label: Voice
+        source_url: http://10.100.79.3:8193/v1/audio/voices
+        source_jsonpath: $.voices[*]
+        default: af_bella
+      - name: response_format
+        type: select
+        options: [wav, mp3, opus, flac, pcm]
+        default: wav
+      - name: speed
+        type: slider
+        label: Speed
+        required: false
+        min: 0.25
+        max: 4.0
+        step: 0.05
+        default: 1.0
+      - name: lang_code
+        type: text
+        label: Language code
+        required: false
+    response:
+      type: json
+      mime: application/json
+    reproducibility:
+      seedable: false
+      deterministic: true
+      notes: >
+        Same determinism story as kokoro proper. Response shape (verified
+        2026-05-11 against live API):
+          {
+            "audio": "<base64-encoded bytes in response_format>",
+            "audio_format": "audio/wav" (or matching response_format),
+            "timestamps": [{"word": str, "start_time": float, "end_time": float}, ...]
+          }
+        Consumer must base64-decode `audio` to play; `timestamps` drives
+        subtitle/karaoke UI. Audio_format string in the payload is
+        authoritative for the decoded bytes.
+    estimated_latency:
+      cold_start_s: 2
+      warm_per_unit: "~same as kokoro proper, plus minor overhead for timestamp emission"
+    license: Apache-2.0
+    notes: |
+      `return_timestamps` and `stream` upstream params are deliberately
+      omitted from the catalog: timestamps must be on for this endpoint
+      to be meaningful, and streaming + JSON-with-base64 don't compose.
+      `download_format` / `return_download_link` skipped — same reasoning
+      as kokoro proper.
 
   - id: chatterbox
     name: Chatterbox Turbo TTS
@@ -820,6 +924,11 @@ reproducibility_audit:
     model_deterministic: true
     image_tag_mutable: true
     notes: ":v0.2.4-master is mutable; pin to digest for v3."
+  - service: kokoro-captioned
+    seedable: false
+    model_deterministic: true
+    image_tag_mutable: true
+    notes: "Same image as kokoro proper; same mutability story. Response carries timestamps."
   - service: chatterbox
     seedable: false
     model_deterministic: true