@clipwright/mcp-server 0.22.0 → 0.23.0

package/CHANGELOG.md

@@ -16,6 +16,50 @@ a customer reading it should not miss what appeared in the product. Like *Server
 they are live from the day the web app was deployed, not from the package release they are
 listed under.
 
+## [0.23.0] - 2026-10-02
+
+Russian speech moves to `eleven_v4`: the server names it by default, and the client texts say which voices speak it.
+Clients older than 0.22.0 fail on the new model name.
+
+### Changed
+
+- **Breaking:** *Server-side:* Russian speech uses `eleven_v4` when you name no `tts_model`. That covers the presets
+  `owner_ru_clone` and `daria_ru_female`, the catalog voices named `ru_*`, and a raw `voice_id` whose script is mostly
+  Cyrillic. Every other voice stays on `eleven_v3`, and an explicit `tts_model` always wins. Clients older than 0.22.0
+  read the model as one of three fixed values and fail on a response that names `eleven_v4`: `list_voices` fails
+  whenever the listing holds a Russian voice, as the unfiltered one always does, and `quote` fails for those Russian
+  voices. Upgrade to 0.22.0 or later. The contract version is `2026-10-02`. (clipwright#452)
+- **Breaking:** `resolveTtsModel` in `@clipwright/core` requires `script`, the whole spoken text of the run: a raw
+  `voice_id` takes its model from it. (clipwright#452)
+- *Server-side:* a script, or the line of one actor segment, that holds nothing but `<break time="…" />` tags is
+  refused before any charge on `eleven_v4`. The model gets the text with those tags cut, and nothing would be left
+  to say. (clipwright#452)
+- *Server-side:* the warnings for a model that misreads stress marks name both models that read them, `eleven_v4`
+  and `eleven_v3`, instead of advising `eleven_v3` alone. (clipwright#452)
+- *Server-side:* the quote and the reserve for a Russian script on `eleven_v4` assume 2.18 words per second, the
+  measured pace, instead of 2.3. `duration_estimate_sec` and `credits_estimate` come out about 5% higher: 153 Russian
+  words are quoted at 70 seconds and 2,100 credits instead of 67 seconds and 2,010. The charge still follows the
+  measured duration. A Russian script on an explicit `eleven_v3` and every other language are quoted as before.
+  (clipwright#452)
+- *Server-side:* the long-form qualification ceiling (`segments` or `inserts`) moves from 300 to 327 seconds of
+  estimated output, for every run. A Russian script on an `eleven_v4` voice passes up to 713 words, against the 691
+  that passed while Russian voices spoke `eleven_v3`. A Russian script on an explicit `eleven_v3` passes up to 753
+  words and an English one up to 851. A longer script is refused before any charge. (clipwright#452)
+- The `tts_model` and `script` descriptions say which voices speak `eleven_v4` by default, name both models that read
+  stress marks, and say that break tags are not counted toward the `eleven_v4` script limit. (clipwright#452)
+
+### Fixed
+
+- `SKILL.md` and the CLI README no longer say that every preset and catalog voice speaks `eleven_v3`, and no longer
+  advise keeping Russian scripts on `eleven_v3`. They name the voices that speak `eleven_v4` when you name no model:
+  the presets `owner_ru_clone` and `daria_ru_female`, the catalog voices named `ru_*`, and a raw `voice_id` with a
+  mostly Cyrillic script. They name both models that read stress marks, `eleven_v4` and `eleven_v3`, and say that
+  `eleven_v4` gives no pause for a `<break time="…" />` tag and gets the text with the tag cut. `SKILL.md` lists the
+  5,000-character script limit of `eleven_v4`. The behavior is the one the entries above describe; only these texts
+  were out of date. (clipwright#452)
+- The `--tts-model` help of `clipwright make` says that an omitted flag means the voice's default model. It said
+  "the preset's model", which was wrong for a catalog voice and for `--voice-id`. (clipwright#452)
+
 ## [0.22.0] - 2026-10-01
 
 A new speech model: `tts_model` accepts `eleven_v4`, and the clients no longer fail on a model they do not know.

package/SKILL.md

@@ -319,11 +319,15 @@ is, the contract MINUS the rejected fields: they simply are not there, and listi
 them here would mean offering what the server punishes you for (section 3).
 
 `script` (required while `segments` is rejected; length is limited by the resolved
-TTS model, as reported by `tools/list`: `eleven_v3` allows 5000 characters,
+TTS model, as reported by `tools/list`: `eleven_v3` and `eleven_v4` allow 5000 characters,
 `eleven_flash_v2_5` and `eleven_turbo_v2_5` allow 10000. Spaces, audio tags and stress
 marks count; emoji may count as two characters. There is no word-count limit or fixed
-duration implied by it), `tts_model` (every preset and catalog voice speaks `eleven_v3`, the most
-expressive model; `eleven_flash_v2_5` and `eleven_turbo_v2_5` cost less and suit
+duration implied by it), `tts_model` (omit it and the voice decides: the Russian presets
+`owner_ru_clone` and `daria_ru_female` and the catalog voices named `ru_*` speak
+`eleven_v4`, every other preset and catalog voice speaks `eleven_v3`; a raw `voice_id`
+speaks `eleven_v4` when at least 60% of the script's Cyrillic and Latin letters are
+Cyrillic, and `eleven_v3` otherwise; an explicit `tts_model` always wins;
+`eleven_flash_v2_5` and `eleven_turbo_v2_5` cost less and suit
 languages other than Russian), optionally `person` OR
 `image` (a public `https` URL) with `actor_gender` (`female`/`male`, only next to
 `image`), plus `name`, `captions` (defaults to `false` —
@@ -334,13 +338,20 @@ differ), `resolution` (`720p`/`1080p`/`4k`), `voice`/`voice_id`.
 
 **Russian stress marks.** Tell a user who writes in Russian that they can fix stress:
 write the stressed vowel as a capital inside a lowercase word — `потОм`, `зАмок` — and
-Clipwright sends `eleven_v3` the stress mark U+0301 (`пото́м`). A capital that starts a
+Clipwright sends `eleven_v4` and `eleven_v3` the stress mark U+0301 (`пото́м`). A capital that starts a
 word stays a capital, a word with a second capital or an inner capital consonant
 (`ВУЗы`, all caps) stays as written, and a U+0301 typed directly is kept. A single
-inner capital vowel always reads as stress, so `ЯндексЕда` needs a space. Keep Russian scripts on `eleven_v3`: the 2.5 models misread the mark, so a script
+inner capital vowel always reads as stress, so `ЯндексЕда` needs a space. Keep Russian
+scripts on `eleven_v4` or `eleven_v3`: the 2.5 models misread the mark, so a script
 carrying it draws a warning there, and so does any Cyrillic script. Retrying never
 fixes stress; only the text does.
 
+**Break tags on `eleven_v4`.** The model gives no pause for `<break time="1.5s" />`.
+Clipwright cuts every tag of that form (`time` in `s` or `ms`) from the text it sends to
+`eleven_v4`, leaves it out of the character count, and names the cut in `warnings[]` of
+the quote and the run. A script that holds nothing but break tags is refused before any
+charge. The other models get the tag as written.
+
 The exact list is always available from the tool schema itself: `tools/list` is
 generated from the same shape, and fields that are not honoured carry
 `NOT HONORED YET` right in their own `description`.
@@ -429,8 +440,9 @@ Two mutually exclusive optional fields in the `make_ugc` input:
 When the user sends a photo and asks for no particular voice, pass the gender of
 the person in it as `actor_gender`. Ask the user only when you cannot tell.
 
-For a Russian script, keep `eleven_v3` and mark stress with a capital vowel
-(see **Russian stress marks** above).
+For a Russian script, leave `tts_model` out or name `eleven_v4` or `eleven_v3` — both
+read stress marks — and mark stress with a capital vowel (see **Russian stress marks**
+above). A Russian voice speaks `eleven_v4` on its own.
 
 ### `get_run` — status polling
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@clipwright/mcp-server",
-  "version": "0.22.0",
+  "version": "0.23.0",
   "description": "MCP server for Clipwright: generate UGC videos from your coding agent",
   "mcpName": "io.clipwright/mcp",
   "keywords": [
@@ -34,8 +34,8 @@
   "dependencies": {
     "@modelcontextprotocol/sdk": "^1.29.0",
     "zod": "^4.4.3",
-    "@clipwright/core": "0.22.0",
-    "@clipwright/sdk": "0.22.0"
+    "@clipwright/core": "0.23.0",
+    "@clipwright/sdk": "0.23.0"
   },
   "devDependencies": {
     "@types/node": "^26.1.1"