@slatesvideo/shared 0.6.11 → 0.7.1

package/skills/slates-prompting-inworld-tts.md

@@ -1,174 +1,174 @@
----
-name: slates-prompting-inworld-tts
-description: How to use Inworld Realtime TTS-2, the VOICE seat. Read before calling slates_generate_audio with model inworld-tts-2. Speech in a SPECIFIC voice, billed per character - the prompt is the words spoken, verbatim. Covers the identity-versus-acoustics rule (what a reference clip does and does not carry), how to write a line so it is performed rather than read, when to reach for seed-audio instead, and the voice-consent rule.
----
-
-# Inworld Realtime TTS-2 — the voice seat
-
-<!-- @card:start -->
-<!-- slates-only -->
-<!-- MACHINE-READ. Everything between the @card markers is extracted by
-     src/prompts/craft-cards.ts and returned on every cost estimate for this
-     model, so it is the ONE piece of positive craft guidance the agent cannot
-     skip. Keep it under 2,400 characters (the build fails above that) and keep
-     the rationale and the worked examples in the body below. -->
-<!-- /slates-only -->
-**Card — Inworld TTS-2.** Speech in a SPECIFIC voice. The prompt is the words spoken, verbatim — not a description of them. Text length determines the bill.
-
-**IDENTITY, NOT ACOUSTICS — the rule that decides whether cloning works**
-A reference carries WHO is speaking: timbre, pitch, accent, age, vowel shape. It does NOT carry WHERE they are — room tone, distance, phone EQ, reverb and mic character are *acoustics*, and this model reproduces the identity while discarding the room. So:
-1. **A noisy reference does not give a noisy read — it gives a WORSE identity.** Music, a second speaker or heavy reverb corrupt what is being extracted. Use a clean single-speaker recording.
-2. **You cannot get "on a payphone" by cloning a payphone recording.** Acoustics come from the MIX, or from `seed-audio` which renders a room.
-
-**DIRECTION GOES IN SQUARE BRACKETS. PARENTHESES ARE SPOKEN ALOUD.** `[whispering] I hope nobody notices` is whispered; `(quietly) I hope nobody notices` says the word "quietly" out loud. Verified by ear — the easiest way to ruin a take.
-
-- **Plain English works inside them** — it is natural-language steering, not a fixed vocabulary: `[very quiet]`, `[whisper in a hushed style]`, `[very slow]`, `[say excitedly]`. Non-verbals are their own tags: `[laugh]`, `[sigh]`, `[breathe]`, `[clear throat]`.
-- **A tag it does not recognise is still consumed, and still changes the read.** Never spoken, never an error — so a mistyped tag fails SILENTLY and only listening catches it.
-- **Tags persist across sentences** until changed; `[reset]` returns to normal.
-- **Punctuation is the timing.** `Wait. Stop.` differs from `Wait, stop.`
-- **One line, one take.** Split a paragraph so a bad clause costs one re-roll.
-- **Spell numbers and titles aloud:** `twenty twenty-six`, `Doctor Reyes`.
-
-**Route elsewhere when:** the scene needs dialogue mixed with effects and room tone in one pass (`seed-audio`), or it is a single non-speech sound (`eleven-sfx`). This surface makes ONE voice saying ONE thing, cleanly.
-
-**Hard constraints:** no duration parameter — length falls out of the text. Exactly one voice source: a preset `voiceId` from `slates_list_voices`, a clip as `voiceReferenceAssetId` (a character's voice clip to speak AS the character, or any clean clip of one speaker), or `voiceDescription`.
-<!-- @card:end -->
-
-<!-- @banned:start -->
-<!-- slates-only -->
-<!-- MACHINE-READ. Every `backticked` token between the @banned markers is
-     extracted by src/prompts/banned-tokens.ts and returned on this model's cost
-     estimate, and every submitted prompt is matched against it. Keep entries
-     backticked and prose outside the backticks. -->
-<!-- /slates-only -->
-**Never use** — the prompt on this surface is SPOKEN ALOUD, so anything that describes the audio instead of being the audio gets read out as words:
-
-- `SFX`, `Ambient noise`, `Background music` as labels — this model speaks; it does not render a scene. Use `seed-audio` for those.
-- shot language: `wide shot`, `slow push in`, `warm tungsten` — video-prompt words, and here they would literally be said aloud
-- `voiceover`, `narrator says`, `he says` as stage directions wrapping the line — write only the words that should come out of the speaker
-<!-- @banned:end -->
-
-## Why the prompt is not a prompt
-
-On every other surface in Slates the prompt DESCRIBES what you want and the model interprets it. Here the prompt IS the deliverable: each character is spoken aloud and each character is billed. `a gravelly man says he is tired` produces a voice saying the words "a gravelly man says he is tired".
-
-That also means the two numbers a user cares about are the same number. The text length sets the price (in 250-character buckets) and sets the length of the audio. There is nothing to choose and nothing to reconcile.
-
-## Steering the delivery
-
-`VERIFIED BY EAR, 2026-09-05.` Every claim in this section was listened to, not
-inferred — an earlier draft of this skill documented tag forms that had only been
-probed for an HTTP 200, which proves the request was accepted and nothing about
-whether it was obeyed.
-
-**Square brackets are consumed. Parentheses are read aloud.** That is the whole
-rule, and getting it wrong is not a subtle degradation — the audience hears a
-narrator say the word "quietly" in the middle of your line.
-
-| Written | What comes out |
-|---|---|
-| `[whispering] I really hope nobody notices that.` | whispered, tag not spoken ✅ |
-| `[very quiet] I really hope nobody notices that.` | very quiet, tag not spoken ✅ |
-| `[whisper in a hushed style] …` | hushed, tag not spoken ✅ |
-| `[very slow] …` | slowed right down, tag not spoken ✅ |
-| `[laugh] …` | an actual laugh, then the line ✅ |
-| `(quietly, under his breath) …` | 🚨 **the words "quietly, under his breath" are SPOKEN** |
-
-**Plain English works — it is natural-language steering, not a fixed vocabulary.**
-Both the documented phrasings (`[whisper in a hushed style]`) and ordinary adverbs
-(`[whispering]`) were obeyed. Write the direction the way you would say it to an
-actor.
-
-The eight dimensions the model steers on, with a working example of each:
-
-| Dimension | Example |
-|---|---|
-| Emotion | `[say excitedly]`, `[sound sad]`, `[sound terrified]` |
-| Articulation | `[say with force]`, `[articulate clearly]` |
-| Intonation | `[say with a rising pitch]` |
-| Volume | `[very quiet]`, `[very loud]` |
-| Pitch | `[say in a low tone]` |
-| Range | `[say playfully]`, `[say with no pitch variation]` |
-| Speed | `[very fast]`, `[very slow]` |
-| Vocal style | `[whisper in a hushed style]`, `[give a nasal quality]` |
-
-Non-verbals sit inline where they happen: `[laugh]`, `[sigh]`, `[cough]`,
-`[breathe]`, `[yawn]`, `[clear throat]`.
-
-### Four rules that are not obvious
-
-1. 🚨 **A tag it does not recognise is still consumed, and still changes the read.**
-   `[zzzqqq]` is not spoken and does not error — it produces a different, arbitrary
-   delivery. So a typo in a tag is SILENT: there is no rejection, no warning, and no
-   way to catch it except listening to the take. Treat an unexpected performance as
-   a possible misspelled tag before you blame the voice.
-2. **Tags persist across sentences.** A `[very slow]` at the top governs everything
-   after it until something changes it. Use `[reset]` to go back to normal rather
-   than assuming the next sentence starts clean.
-3. **Do not stack opposing directions.** `[whisper in a hushed style]` together with
-   `[very loud]` produces unpredictable results — the model is resolving a
-   contradiction, and which side wins is not something you can rely on.
-4. **Tags COUNT toward the billed characters**, even though they are never spoken.
-   They are part of the text sent to the vendor, so the vendor charges for them and
-   so do we — billing what was actually sent is the only honest basis. It rarely
-   matters (a 13-character tag inside a 250-character bucket), but a line sitting
-   just under a bucket boundary can be pushed into the next one by a long
-   direction. Prefer `[very slow]` over `[say this one very slowly please]`.
-
-## Identity versus acoustics, at length
-
-This is the distinction that decides whether the feature feels good, and it is worth being precise about because the failure is quiet — you get a usable clip that is subtly not the person.
-
-**What a reference clip transfers:** vocal timbre, pitch range, accent and regional vowels, apparent age, speech rate tendencies, and the particular rasp or breathiness of the source speaker.
-
-**What it does not transfer:** the room, the microphone, the codec, the distance from the mic, any processing on the source, and any other sound present in it.
-
-So the ideal reference is boring: one person, close to a microphone, no music, no second speaker, no heavy reverb, five to fifteen seconds, speaking normally rather than performing. A phone voice memo in a quiet room beats a beautifully produced clip with a music bed underneath it.
-
-**Two failure modes, both common:**
-
-- *"I cloned my podcast intro and it doesn't sound like me."* The intro had music under it. The model averaged the music into the identity. Re-clone from a clean stretch.
-- *"I want the line to sound like it's coming through a car radio."* Clone the clean voice, then EQ and process the returned clip on the timeline. A radio-sounding reference makes a worse voice, not a radio effect.
-
-## Getting the voice onto the call
-
-Exactly one source per call, and none of them requires a character to exist first:
-
-- **A preset:** `slates_list_voices` lists stock voices with gender, age, accent and tags — filter by any of them, or search the descriptions ("gravelly", "narration"). Pass the chosen `voiceId`. Presets clone nothing, so they are the fastest path and avoid the clone-creation rate ceiling.
-- **Speak AS a character:** `voiceReferenceAssetId: <its voiceAssetId>` (the clip on the row `slates_list_characters` returns). The seat clones the clip for that take and discards the vendor voice afterwards, so there is nothing to reconcile — but cloning shares a ceiling of two new voices a minute across every Slates user, so a run of lines in one cloned voice pauses between takes rather than failing. Send each line once; do not re-send one that already came back. Any other clean clip of one speaker works the same way.
-- **A voice with no recording:** `voiceDescription` (7–1000 characters of words). If it will be used again, keep the returned clip on a character with `slates_update_character` (`voiceAssetId`) so later lines clone the same clip instead of designing a new voice each time — a convenience, never a requirement.
-
-## Consent
-
-Cloning a real person's voice needs that person's explicit, documented permission, scoped to what you are making. Clone from original human recordings only — never from another model's output. This is the same gate the real-face route applies to likeness, and it applies here for the same reason.
-
-## Worked examples
-
-**A line with a direction**
-
-```
-[very quiet] I heard what you said in there. I'm not going to pretend I didn't.
-```
-
-**A line that needs its numbers spoken**
-
-```
-The vote was three hundred and twelve to eighty-nine. It carried at four minutes past midnight.
-```
-
-**A paragraph, split into three takes** — so one bad clause costs one re-roll:
-
-```
-1. You keep asking me why I stayed.
-2. It wasn't loyalty. It wasn't even fear, not by the end.
-3. [very slow] It was that I couldn't picture the version of me that left.
-```
-
-**What NOT to send**
-
-```
-(gravelly, tired) a tired old man narrates the opening of the film, wide shot, warm tungsten
-```
-
-Every word of that is spoken aloud — **including the parenthetical**, which is the
-trap: it looks like a stage direction and is treated as dialogue. Describe the voice when you are CHOOSING one (`voiceDescription`, or the desktop's voice picker); the prompt is only ever the words.
+---
+name: slates-prompting-inworld-tts
+description: How to use Inworld Realtime TTS-2, the VOICE seat. Read before calling slates_generate_audio with model inworld-tts-2. Speech in a SPECIFIC voice, billed per character - the prompt is the words spoken, verbatim. Covers the identity-versus-acoustics rule (what a reference clip does and does not carry), how to write a line so it is performed rather than read, when to reach for seed-audio instead, and the voice-consent rule.
+---
+
+# Inworld Realtime TTS-2 — the voice seat
+
+<!-- @card:start -->
+<!-- slates-only -->
+<!-- MACHINE-READ. Everything between the @card markers is extracted by
+     src/prompts/craft-cards.ts and returned on every cost estimate for this
+     model, so it is the ONE piece of positive craft guidance the agent cannot
+     skip. Keep it under 2,400 characters (the build fails above that) and keep
+     the rationale and the worked examples in the body below. -->
+<!-- /slates-only -->
+**Card — Inworld TTS-2.** Speech in a SPECIFIC voice. The prompt is the words spoken, verbatim — not a description of them. Text length determines the bill.
+
+**IDENTITY, NOT ACOUSTICS — the rule that decides whether cloning works**
+A reference carries WHO is speaking: timbre, pitch, accent, age, vowel shape. It does NOT carry WHERE they are — room tone, distance, phone EQ, reverb and mic character are *acoustics*, and this model reproduces the identity while discarding the room. So:
+1. **A noisy reference does not give a noisy read — it gives a WORSE identity.** Music, a second speaker or heavy reverb corrupt what is being extracted. Use a clean single-speaker recording.
+2. **You cannot get "on a payphone" by cloning a payphone recording.** Acoustics come from the MIX, or from `seed-audio` which renders a room.
+
+**DIRECTION GOES IN SQUARE BRACKETS. PARENTHESES ARE SPOKEN ALOUD.** `[whispering] I hope nobody notices` is whispered; `(quietly) I hope nobody notices` says the word "quietly" out loud. Verified by ear — the easiest way to ruin a take.
+
+- **Plain English works inside them** — it is natural-language steering, not a fixed vocabulary: `[very quiet]`, `[whisper in a hushed style]`, `[very slow]`, `[say excitedly]`. Non-verbals are their own tags: `[laugh]`, `[sigh]`, `[breathe]`, `[clear throat]`.
+- **A tag it does not recognise is still consumed, and still changes the read.** Never spoken, never an error — so a mistyped tag fails SILENTLY and only listening catches it.
+- **Tags persist across sentences** until changed; `[reset]` returns to normal.
+- **Punctuation is the timing.** `Wait. Stop.` differs from `Wait, stop.`
+- **One line, one take.** Split a paragraph so a bad clause costs one re-roll.
+- **Spell numbers and titles aloud:** `twenty twenty-six`, `Doctor Reyes`.
+
+**Route elsewhere when:** the scene needs dialogue mixed with effects and room tone in one pass (`seed-audio`), or it is a single non-speech sound (`eleven-sfx`). This surface makes ONE voice saying ONE thing, cleanly.
+
+**Hard constraints:** no duration parameter — length falls out of the text. Exactly one voice source: a preset `voiceId` from `slates_list_voices`, a clip as `voiceReferenceAssetId` (a character's voice clip to speak AS the character, or any clean clip of one speaker), or `voiceDescription`.
+<!-- @card:end -->
+
+<!-- @banned:start -->
+<!-- slates-only -->
+<!-- MACHINE-READ. Every `backticked` token between the @banned markers is
+     extracted by src/prompts/banned-tokens.ts and returned on this model's cost
+     estimate, and every submitted prompt is matched against it. Keep entries
+     backticked and prose outside the backticks. -->
+<!-- /slates-only -->
+**Never use** — the prompt on this surface is SPOKEN ALOUD, so anything that describes the audio instead of being the audio gets read out as words:
+
+- `SFX`, `Ambient noise`, `Background music` as labels — this model speaks; it does not render a scene. Use `seed-audio` for those.
+- shot language: `wide shot`, `slow push in`, `warm tungsten` — video-prompt words, and here they would literally be said aloud
+- `voiceover`, `narrator says`, `he says` as stage directions wrapping the line — write only the words that should come out of the speaker
+<!-- @banned:end -->
+
+## Why the prompt is not a prompt
+
+On every other surface in Slates the prompt DESCRIBES what you want and the model interprets it. Here the prompt IS the deliverable: each character is spoken aloud and each character is billed. `a gravelly man says he is tired` produces a voice saying the words "a gravelly man says he is tired".
+
+That also means the two numbers a user cares about are the same number. The text length sets the price (in 250-character buckets) and sets the length of the audio. There is nothing to choose and nothing to reconcile.
+
+## Steering the delivery
+
+`VERIFIED BY EAR, 2026-09-05.` Every claim in this section was listened to, not
+inferred — an earlier draft of this skill documented tag forms that had only been
+probed for an HTTP 200, which proves the request was accepted and nothing about
+whether it was obeyed.
+
+**Square brackets are consumed. Parentheses are read aloud.** That is the whole
+rule, and getting it wrong is not a subtle degradation — the audience hears a
+narrator say the word "quietly" in the middle of your line.
+
+| Written | What comes out |
+|---|---|
+| `[whispering] I really hope nobody notices that.` | whispered, tag not spoken ✅ |
+| `[very quiet] I really hope nobody notices that.` | very quiet, tag not spoken ✅ |
+| `[whisper in a hushed style] …` | hushed, tag not spoken ✅ |
+| `[very slow] …` | slowed right down, tag not spoken ✅ |
+| `[laugh] …` | an actual laugh, then the line ✅ |
+| `(quietly, under his breath) …` | 🚨 **the words "quietly, under his breath" are SPOKEN** |
+
+**Plain English works — it is natural-language steering, not a fixed vocabulary.**
+Both the documented phrasings (`[whisper in a hushed style]`) and ordinary adverbs
+(`[whispering]`) were obeyed. Write the direction the way you would say it to an
+actor.
+
+The eight dimensions the model steers on, with a working example of each:
+
+| Dimension | Example |
+|---|---|
+| Emotion | `[say excitedly]`, `[sound sad]`, `[sound terrified]` |
+| Articulation | `[say with force]`, `[articulate clearly]` |
+| Intonation | `[say with a rising pitch]` |
+| Volume | `[very quiet]`, `[very loud]` |
+| Pitch | `[say in a low tone]` |
+| Range | `[say playfully]`, `[say with no pitch variation]` |
+| Speed | `[very fast]`, `[very slow]` |
+| Vocal style | `[whisper in a hushed style]`, `[give a nasal quality]` |
+
+Non-verbals sit inline where they happen: `[laugh]`, `[sigh]`, `[cough]`,
+`[breathe]`, `[yawn]`, `[clear throat]`.
+
+### Four rules that are not obvious
+
+1. 🚨 **A tag it does not recognise is still consumed, and still changes the read.**
+   `[zzzqqq]` is not spoken and does not error — it produces a different, arbitrary
+   delivery. So a typo in a tag is SILENT: there is no rejection, no warning, and no
+   way to catch it except listening to the take. Treat an unexpected performance as
+   a possible misspelled tag before you blame the voice.
+2. **Tags persist across sentences.** A `[very slow]` at the top governs everything
+   after it until something changes it. Use `[reset]` to go back to normal rather
+   than assuming the next sentence starts clean.
+3. **Do not stack opposing directions.** `[whisper in a hushed style]` together with
+   `[very loud]` produces unpredictable results — the model is resolving a
+   contradiction, and which side wins is not something you can rely on.
+4. **Tags COUNT toward the billed characters**, even though they are never spoken.
+   They are part of the text sent to the vendor, so the vendor charges for them and
+   so do we — billing what was actually sent is the only honest basis. It rarely
+   matters (a 13-character tag inside a 250-character bucket), but a line sitting
+   just under a bucket boundary can be pushed into the next one by a long
+   direction. Prefer `[very slow]` over `[say this one very slowly please]`.
+
+## Identity versus acoustics, at length
+
+This is the distinction that decides whether the feature feels good, and it is worth being precise about because the failure is quiet — you get a usable clip that is subtly not the person.
+
+**What a reference clip transfers:** vocal timbre, pitch range, accent and regional vowels, apparent age, speech rate tendencies, and the particular rasp or breathiness of the source speaker.
+
+**What it does not transfer:** the room, the microphone, the codec, the distance from the mic, any processing on the source, and any other sound present in it.
+
+So the ideal reference is boring: one person, close to a microphone, no music, no second speaker, no heavy reverb, five to fifteen seconds, speaking normally rather than performing. A phone voice memo in a quiet room beats a beautifully produced clip with a music bed underneath it.
+
+**Two failure modes, both common:**
+
+- *"I cloned my podcast intro and it doesn't sound like me."* The intro had music under it. The model averaged the music into the identity. Re-clone from a clean stretch.
+- *"I want the line to sound like it's coming through a car radio."* Clone the clean voice, then EQ and process the returned clip on the timeline. A radio-sounding reference makes a worse voice, not a radio effect.
+
+## Getting the voice onto the call
+
+Exactly one source per call, and none of them requires a character to exist first:
+
+- **A preset:** `slates_list_voices` lists stock voices with gender, age, accent and tags — filter by any of them, or search the descriptions ("gravelly", "narration"). Pass the chosen `voiceId`. Presets clone nothing, so they are the fastest path and avoid the clone-creation rate ceiling.
+- **Speak AS a character:** `voiceReferenceAssetId: <its voiceAssetId>` (the clip on the row `slates_list_characters` returns). The seat clones the clip for that take and discards the vendor voice afterwards, so there is nothing to reconcile — but cloning shares a ceiling of two new voices a minute across every Slates user, so a run of lines in one cloned voice pauses between takes rather than failing. Send each line once; do not re-send one that already came back. Any other clean clip of one speaker works the same way.
+- **A voice with no recording:** `voiceDescription` (7–1000 characters of words). If it will be used again, keep the returned clip on a character with `slates_update_character` (`voiceAssetId`) so later lines clone the same clip instead of designing a new voice each time — a convenience, never a requirement.
+
+## Consent
+
+Cloning a real person's voice needs that person's explicit, documented permission, scoped to what you are making. Clone from original human recordings only — never from another model's output. This is the same gate the real-face route applies to likeness, and it applies here for the same reason.
+
+## Worked examples
+
+**A line with a direction**
+
+```
+[very quiet] I heard what you said in there. I'm not going to pretend I didn't.
+```
+
+**A line that needs its numbers spoken**
+
+```
+The vote was three hundred and twelve to eighty-nine. It carried at four minutes past midnight.
+```
+
+**A paragraph, split into three takes** — so one bad clause costs one re-roll:
+
+```
+1. You keep asking me why I stayed.
+2. It wasn't loyalty. It wasn't even fear, not by the end.
+3. [very slow] It was that I couldn't picture the version of me that left.
+```
+
+**What NOT to send**
+
+```
+(gravelly, tired) a tired old man narrates the opening of the film, wide shot, warm tungsten
+```
+
+Every word of that is spoken aloud — **including the parenthetical**, which is the
+trap: it looks like a stage direction and is treated as dialogue. Describe the voice when you are CHOOSING one (`voiceDescription`, or the desktop's voice picker); the prompt is only ever the words.

package/skills/slates-prompting-kling-v3.md

@@ -163,7 +163,7 @@ Every reference rule below is a corollary of that one sentence, which is why "pr
 Identity = a few flat-lit neutral angles; one reference per role, named inline; 2-4 refs not 12; describe environments instead of feeding a grid.
 
 1. **2-4 strong references beat both extremes.** Not 1 (warps toward itself), not 12 (averages worse). Start with 2-3 focused refs — each one adds context AND another variable to balance.
-2. **One reference per ROLE, named in the prompt** — identity / style-grade / environment. The model does **not** infer a reference's role from its position in the list; the inline name carries it. Same-role competitors drift (two "identity" refs of different people blend into a third face). Slates composes the naming for you from your `@mentions` / `#tags` — you never hand-write role labels.
+2. **One reference per ROLE, named in the prompt** — identity / style-grade / environment. The model does **not** infer a reference's role from its position in the list; the inline name carries it. Same-role competitors drift (two "identity" refs of different people blend into a third face). Slates resolves `@mentions` / `#tags` into numbered citations. You can also bind references directly in scene prose, naming what each image supplies.
 3. **One identity sheet per character, named inline.** A character's identity is a single asset (dominant portrait + body panels), so attach that one asset rather than a pile of views: **fewer competing renderings of a face is better, because the model cannot tell which one is authoritative and averages them.** Slates cites it as `Marcus (image 1)`. **Do NOT hand-write a "Reference Image Instructions" block or role essays** ("use for identity, ignore the outfit, render a neutral expression") — that drags the sheet's studio lighting and wardrobe into a scene that asked for neither. The prompt leads; the user's words own wardrobe, expression, lighting, and action.
 4. **Flat-light identity refs.** Prep identity references with flat, even, shadowless lighting on a plain neutral background. A studio-lit or scene-lit character sheet bleeds its lighting into every generation — the failure looks like the subject was green-screen-pasted in front of the location. Reference prep beats prompting here.
 5. **Environment: describe it, don't feed a grid.** Default to describing the location in words and let the model build a space that fits the shot. Reserve an environment reference for a mandatory exact-match, and then use ONE clean establishing image with natural ambient light that reads as the location's real light — never a multi-panel grid fed whole.
@@ -185,11 +185,11 @@ Kling exposes `negative_prompt` on the fal endpoint (different from Seedance whi
 
 ```
 blurry, low quality, watermark, text overlay, distorted hands, extra fingers,
-duplicate limbs, unnatural skin texture, overly saturated colors, lens flare,
+duplicate limbs, unnatural skin texture, overly saturated colors,
 floating objects, inconsistent shadows, jittery, flickering, morphing face
 ```
 
-Layer scene-specific suppressions on top.
+Layer scene-specific suppressions on top, and never suppress something the prompt asks for. This block carried `lens flare` until 2026-09-15, which silently cancelled every flare a prompt described (`slates-cinematic-look` → `source-flare`); add it back only for a shot that must have none.
 
 ## Cinematic tactics
 

package/skills/slates-prompting-lip-sync.md

@@ -60,7 +60,7 @@ Seedance can generate the performance rather than bolting a mouth onto finished
 That is the same endpoint the old `engine=seedance-2` branch called — it just built the sentence for you, invisibly, and it presupposed a "video 1" that might not exist. Writing the prompt is the whole difference, and it is the part you want control of.
 
 - Driving clips must be 2–15s; output duration is whatever you set (4–15s).
-- Video references bill COMBINED input+output seconds (`seedance-2*-vref-*` keys) — pass the clip duration and quote before confirming.
+- Video references bill COMBINED input+output seconds (`seedance-2*-vref-*` keys) — pass the clip duration and quote before confirming. On Seedance 2.5's AI-face route (EvoLink) the input side counts as at least the output's length: max(input, output) + output.
 - Faces go through the normal cascade: `seedanceFace` for a character, `[REAL_FACE_DETECTED]` → `seedanceRealFace` + `realFaceConsent` for a real person.
 
 Everything below is about the Kling tool.

package/skills/slates-prompting-minimax-h3.md

@@ -1,6 +1,6 @@
 ---
 name: slates-prompting-minimax-h3
-description: How to prompt MiniMax H3 and MiniMax H3 Max. Read before calling slates_generate_video with model minimax-h3 or minimax-h3-max. H3 is the only Slates video seat where AUDIO IS AUTHORED rather than toggled — synchronised dialogue, scene sound and an audience-only score are three separate sections of the prompt, generated in one pass — and the only one where a reference carries a DECLARED RELATIONSHIP (kept whole, partly kept, transferred onto a different subject, or a loose echo). Base minimax-h3 runs 480p/768p/2K/4K and reads 9 images + 3 video + 3 audio references; minimax-h3-max is fal's faster post-train, capped at 768p, and costs MORE than base H3 at 768p — a deliberate speed pick, never the default and never the cheap one; it animates start and end frames AND takes the same 9+3+3 omni-reference set (corrected 2026-09-09), so the seats differ on ladder and price, not on what they accept. Two hazards live here: reference images past the free allowance are billed (5 free then +4 credits on base H3; pooled media tokens on Max), and audio written into the wrong section is dropped or duplicated.
+description: How to prompt MiniMax H3, H3 Max and H3 Max Turbo. Read before calling slates_generate_video with model minimax-h3, minimax-h3-max or minimax-h3-max-turbo. H3 is the only Slates video seat where AUDIO IS AUTHORED rather than toggled — synchronised dialogue, scene sound and an audience-only score are three separate sections of the prompt, generated in one pass — and the only one where a reference carries a DECLARED RELATIONSHIP (kept whole, partly kept, transferred onto a different subject, or a loose echo). Base minimax-h3 runs 480p/768p/2K/4K and reads 9 images + 3 video + 3 audio references; minimax-h3-max is fal's faster post-train, runs 480p/768p plus a 1080p refinement of its 768p render, and costs MORE than base H3 at 768p — a deliberate speed pick, never the default and never the cheap one; it animates start and end frames AND takes the same 9+3+3 omni-reference set (corrected 2026-09-09). minimax-h3-max-turbo is a second fal post-train with Max's ladder at half Max's rate; it takes start and end frames but has NO reference endpoint. Two hazards live here: reference images past the free allowance are billed (5 free then +4 credits on base H3; pooled media tokens on Max), and audio written into the wrong section is dropped or duplicated.
 ---
 
 # MiniMax H3 — prompting
@@ -28,7 +28,7 @@ description: How to prompt MiniMax H3 and MiniMax H3 Max. Read before calling sl
 - `A woman sits still at a kitchen table for a beat, then looks up. She says in English, "You said Tuesday." Scene sound: a fridge hum, a spoon set down on formica. Score: none.`
 - `Two mechanics either side of an open bonnet. The younger one wipes his hands, waits, then speaks in Spanish, "No es el alternador." Scene sound: a socket wrench, a radio two bays over. Score: a low sustained cello under the last three seconds, audience only.`
 
-**Hard constraint:** the two seats differ in what the ENDPOINT accepts, not in grammar. Base H3 reaches 2K/4K and takes references; `minimax-h3-max` tops out at 768p rather than 4K, takes the same 9+3+3 references, and costs MORE at the tier they share — it is a speed pick, never the cheap one. H3's top two resolution tiers are UPSCALES of the native render: judge at native. Reference inputs affect the quote; include every attached modality when estimating.
+**Hard constraint:** the three seats differ in what the ENDPOINT accepts, not in grammar. Base H3 reaches 2K/4K and takes references; `minimax-h3-max` tops out at 1080p, takes the same 9+3+3 references, and costs MORE at the tier they share — a speed pick, never the cheap one; `minimax-h3-max-turbo` has Max's ladder at half its rate and takes frames only, NO references. Every tier above 768p is built from the native 768p render: judge at native. Reference inputs affect the quote; include every attached modality when estimating.
 <!-- @card:end -->
 
 <!-- @banned:start -->
@@ -50,21 +50,31 @@ German, Italian, Japanese, Korean, Portuguese, Russian, Spanish). That single fa
 everything below — the prompt is not a shot description with sound bolted on, it is a **timeline
 with three audio layers you author separately**.
 
-**Two seats, one grammar.** Everything in this file applies to both. They differ only in what the
-endpoint accepts:
+**Three seats, one grammar.** Everything in this file applies to all three. They differ only in
+what the endpoint accepts:
 
-| | `minimax-h3` | `minimax-h3-max` |
-|---|---|---|
-| Resolution | 480p / 768p / **2K / 4K** | 480p / 768p |
-| References | 9 images + 3 video + 3 audio (12 files) | 9 images + 3 video + 3 audio (12 files) |
-| Frames | start and/or end | start and/or end |
-| Price at 768p | **$0.060/s** | $0.080/s |
-| Why pick it | resolution, references, and the cheaper second | **speed** — a 5s 768p clip in **4.8s** vs **57s** (measured) |
+| | `minimax-h3` | `minimax-h3-max` | `minimax-h3-max-turbo` |
+|---|---|---|---|
+| Resolution | 480p / 768p / **2K / 4K** | 480p / 768p / 1080p | 480p / 768p / 1080p |
+| References | 9 images + 3 video + 3 audio (12 files) | 9 images + 3 video + 3 audio (12 files) | **none** (no reference endpoint) |
+| Frames | start and/or end | start and/or end | start and/or end |
+| Price at 768p | **$0.060/s** | $0.080/s | $0.040/s |
+| Why pick it | resolution, references, and the cheaper second | **speed** — a 5s 768p clip in **4.8s** vs **57s** (measured) | **price** — half Max's rate at every tier |
 
 **Max is the premium seat, not the budget one.** It is 33% dearer at the one tier they share and it
 tops out lower. Route there when a fast turnaround on a text-to-video or start-frame shot is worth
 paying for; route to base H3 for anything needing resolution, references, or the same tier cheaper.
 
+**Turbo is the budget seat.** Same grammar and Max's ladder at half Max's rate, with no reference
+endpoint: attach a reference and Slates refuses the call rather than dropping it. Route there for
+drafts, volume and start-frame coverage, then re-run the keeper on Max or base H3 when it needs
+references.
+
+**1080p on Max and Turbo is a refinement, not a native render.** fal's schema, verbatim: *"1080P
+latent refinement from a native 768P source."* It is a different stage from base H3's 2K/4K
+upscaler, and it costs double the 768p second. Judge a 1080p take against the same shot at 768p
+before paying for it across a batch.
+
 **The speed is measured, not claimed** (2026-08-27, same prompt and params on both rows): a 5-second
 768p text-to-video finished in **4.8 seconds** on Max against **57 seconds** on base H3 — roughly
 **12x**, queue to finished file. fal advertises "under 3 seconds"; the literal claim did not hold at
@@ -192,8 +202,8 @@ original wording preserved exactly: *A red neon sign reading "Open Late" glows a
 
 ## References — H3's real differentiator is the declared RELATIONSHIP
 
-*(BOTH rows. `minimax-h3-max` gained the reference set on 2026-09-09; its free allowance is
-FOUR images rather than the base row's five.)*
+*(`minimax-h3` and `minimax-h3-max`. Max gained the reference set on 2026-09-09; its free allowance
+is FOUR images rather than the base row's five. `minimax-h3-max-turbo` takes no references.)*
 
 <!-- @inject:references-read-literally -->
 > **The general law: the model reads a reference literally.**
@@ -213,7 +223,7 @@ Every reference rule below is a corollary of that one sentence, which is why "pr
 Identity = a few flat-lit neutral angles; one reference per role, named inline; 2-4 refs not 12; describe environments instead of feeding a grid.
 
 1. **2-4 strong references beat both extremes.** Not 1 (warps toward itself), not 12 (averages worse). Start with 2-3 focused refs — each one adds context AND another variable to balance.
-2. **One reference per ROLE, named in the prompt** — identity / style-grade / environment. The model does **not** infer a reference's role from its position in the list; the inline name carries it. Same-role competitors drift (two "identity" refs of different people blend into a third face). Slates composes the naming for you from your `@mentions` / `#tags` — you never hand-write role labels.
+2. **One reference per ROLE, named in the prompt** — identity / style-grade / environment. The model does **not** infer a reference's role from its position in the list; the inline name carries it. Same-role competitors drift (two "identity" refs of different people blend into a third face). Slates resolves `@mentions` / `#tags` into numbered citations. You can also bind references directly in scene prose, naming what each image supplies.
 3. **One identity sheet per character, named inline.** A character's identity is a single asset (dominant portrait + body panels), so attach that one asset rather than a pile of views: **fewer competing renderings of a face is better, because the model cannot tell which one is authoritative and averages them.** Slates cites it as `Marcus (image 1)`. **Do NOT hand-write a "Reference Image Instructions" block or role essays** ("use for identity, ignore the outfit, render a neutral expression") — that drags the sheet's studio lighting and wardrobe into a scene that asked for neither. The prompt leads; the user's words own wardrobe, expression, lighting, and action.
 4. **Flat-light identity refs.** Prep identity references with flat, even, shadowless lighting on a plain neutral background. A studio-lit or scene-lit character sheet bleeds its lighting into every generation — the failure looks like the subject was green-screen-pasted in front of the location. Reference prep beats prompting here.
 5. **Environment: describe it, don't feed a grid.** Default to describing the location in words and let the model build a space that fits the shot. Reserve an environment reference for a mandatory exact-match, and then use ONE clean establishing image with natural ambient light that reads as the location's real light — never a multi-panel grid fed whole.
@@ -260,7 +270,7 @@ exactly and say so.
 **An audio reference cannot travel alone** — H3 refuses a reference set that is audio only. Pair it
 with at least one image or video reference.
 
-### 💸 Reference images past the free allowance are billed — and the two rows differ
+### 💸 Reference images past the free allowance are billed — and the two reference rows differ
 
 On `minimax-h3` the first **5** are free and each additional image adds **4 credits**.
 Max pools image pixels, reference-video seconds and reference-audio seconds into one token
@@ -279,14 +289,14 @@ reference-heavy job — a quote that omits it under-reports the bill.
 
 ## Frames
 
-`minimax-h3` and `minimax-h3-max` both take a **start frame**, an **end frame**, or both. With an
+All three rows take a **start frame**, an **end frame**, or both. With an
 end frame, land it explicitly: describe the final pose, spacing and composition as the thing the
 shot **settles into** at the end, rather than hoping the model finds it.
 
 > *"…she rotates the handle into the final angle and settles into the pose, spacing and composition
 > of image 2 at the end of the shot."*
 
-**Frames and references are mutually exclusive** on both rows — they are different endpoints, and
+**Frames and references are mutually exclusive** on the two reference rows — they are different endpoints, and
 the reference endpoint has no frame slots at all. Slates refuses the combination rather than
 dropping one side.
 
@@ -301,6 +311,9 @@ dropping one side.
 | `minimax-h3` · 2K · 10s | 65 |
 | `minimax-h3` · 4K · 10s | 80 |
 | `minimax-h3-max` · 768p · 10s | 40 |
+| `minimax-h3-max` · 1080p · 10s | 80 |
+| `minimax-h3-max-turbo` · 768p · 10s | 20 |
+| `minimax-h3-max-turbo` · 1080p · 10s | 40 |
 | `minimax-h3` — every reference image past the **fifth** | **+4** |
 
 **768p is the default for a reason.** It is the tier the model natively generates.

package/skills/slates-prompting-motion-transfer.md

@@ -64,7 +64,7 @@ movement from video 1. Preserve the character's identity, appearance, and outfit
 That is the same endpoint the old `motionModel=seedance-2` branch called — it just wrote that sentence for you, invisibly. Add style/setting/camera direction freely; Seedance re-generates the whole shot.
 
 - **Driving clip must be 2–15s** (all providers cap reference video at 15s). Longer clips: trim first, or use Kling MC (`characterOrientation: 'video'` takes up to 30s).
-- **Billing = combined input+output seconds** (the vref keys). The server probes the clip and corrects an understated key — quote via the confirm gate before spending.
+- **Billing = combined input+output seconds** (the vref keys). The server probes the clip and corrects an understated key — quote via the confirm gate before spending. On Seedance 2.5's AI-face route (EvoLink) the input side counts as at least the output's length: max(input, output) + output.
 - **Faces route through the face cascade**: `seedanceFace` for a character, `[REAL_FACE_DETECTED]` → confirm consent → `seedanceRealFace=true, realFaceConsent=true` (premium realface vref pricing).
 - `characterOrientation` has no Seedance equivalent; framing follows the prompt + `aspectRatio`.