@mux/ai 0.3.0 → 0.4.0

package/README.md

@@ -83,12 +83,12 @@ S3_SECRET_ACCESS_KEY=your-secret-key
 
 | Workflow                                                                 | Description                                                       | Providers                 | Default Models                                                     | Mux Asset Requirements | Cloud Infrastructure Requirements |
 | ------------------------------------------------------------------------ | ----------------------------------------------------------------- | ------------------------- | ------------------------------------------------------------------ | ---------------------- | --------------------------------- |
-| [`getSummaryAndTags`](./docs/WORKFLOWS.md#video-summarization)<br/>[API](./docs/API.md#getsummaryandtagsassetid-options) · [Source](./src/workflows/summarization.ts) | Generate titles, descriptions, and tags for an asset              | OpenAI, Anthropic, Google | `gpt-5.1` (OpenAI), `claude-sonnet-4-5` (Anthropic), `gemini-2.5-flash` (Google) | Video (required), Captions (optional) | None |
+| [`getSummaryAndTags`](./docs/WORKFLOWS.md#video-summarization)<br/>[API](./docs/API.md#getsummaryandtagsassetid-options) · [Source](./src/workflows/summarization.ts) | Generate titles, descriptions, and tags for an asset              | OpenAI, Anthropic, Google | `gpt-5.1` (OpenAI), `claude-sonnet-4-5` (Anthropic), `gemini-3-flash-preview` (Google) | Video (required), Captions (optional) | None |
 | [`getModerationScores`](./docs/WORKFLOWS.md#content-moderation)<br/>[API](./docs/API.md#getmoderationscoresassetid-options) · [Source](./src/workflows/moderation.ts) | Detect inappropriate (sexual or violent) content in an asset      | OpenAI, Hive              | `omni-moderation-latest` (OpenAI) or Hive visual moderation task   | Video (required) | None |
-| [`hasBurnedInCaptions`](./docs/WORKFLOWS.md#burned-in-caption-detection)<br/>[API](./docs/API.md#hasburnedincaptionsassetid-options) · [Source](./src/workflows/burned-in-captions.ts) | Detect burned-in captions (hardcoded subtitles) in an asset       | OpenAI, Anthropic, Google | `gpt-5.1` (OpenAI), `claude-sonnet-4-5` (Anthropic), `gemini-2.5-flash` (Google) | Video (required) | None |
-| [`generateChapters`](./docs/WORKFLOWS.md#chapter-generation)<br/>[API](./docs/API.md#generatechaptersassetid-languagecode-options) · [Source](./src/workflows/chapters.ts) | Generate chapter markers for an asset using the transcript        | OpenAI, Anthropic, Google | `gpt-5.1` (OpenAI), `claude-sonnet-4-5` (Anthropic), `gemini-2.5-flash` (Google) | Video (required), Captions (required) | None |
+| [`hasBurnedInCaptions`](./docs/WORKFLOWS.md#burned-in-caption-detection)<br/>[API](./docs/API.md#hasburnedincaptionsassetid-options) · [Source](./src/workflows/burned-in-captions.ts) | Detect burned-in captions (hardcoded subtitles) in an asset       | OpenAI, Anthropic, Google | `gpt-5.1` (OpenAI), `claude-sonnet-4-5` (Anthropic), `gemini-3-flash-preview` (Google) | Video (required) | None |
+| [`generateChapters`](./docs/WORKFLOWS.md#chapter-generation)<br/>[API](./docs/API.md#generatechaptersassetid-languagecode-options) · [Source](./src/workflows/chapters.ts) | Generate chapter markers for an asset using the transcript        | OpenAI, Anthropic, Google | `gpt-5.1` (OpenAI), `claude-sonnet-4-5` (Anthropic), `gemini-3-flash-preview` (Google) | Video (required), Captions (required) | None |
 | [`generateVideoEmbeddings`](./docs/WORKFLOWS.md#video-embeddings)<br/>[API](./docs/API.md#generatevideoembeddingsassetid-options) · [Source](./src/workflows/embeddings.ts) | Generate vector embeddings for an asset's transcript chunks       | OpenAI, Google            | `text-embedding-3-small` (OpenAI), `gemini-embedding-001` (Google) | Video (required), Captions (required) | None |
-| [`translateCaptions`](./docs/WORKFLOWS.md#caption-translation)<br/>[API](./docs/API.md#translatecaptionsassetid-fromlanguagecode-tolanguagecode-options) · [Source](./src/workflows/translate-captions.ts) | Translate an asset's captions into different languages            | OpenAI, Anthropic, Google | `gpt-5.1` (OpenAI), `claude-sonnet-4-5` (Anthropic), `gemini-2.5-flash` (Google) | Video (required), Captions (required) | AWS S3 (if `uploadToMux=true`) |
+| [`translateCaptions`](./docs/WORKFLOWS.md#caption-translation)<br/>[API](./docs/API.md#translatecaptionsassetid-fromlanguagecode-tolanguagecode-options) · [Source](./src/workflows/translate-captions.ts) | Translate an asset's captions into different languages            | OpenAI, Anthropic, Google | `gpt-5.1` (OpenAI), `claude-sonnet-4-5` (Anthropic), `gemini-3-flash-preview` (Google) | Video (required), Captions (required) | AWS S3 (if `uploadToMux=true`) |
 | [`translateAudio`](./docs/WORKFLOWS.md#audio-dubbing)<br/>[API](./docs/API.md#translateaudioassetid-tolanguagecode-options) · [Source](./src/workflows/translate-audio.ts) | Create AI-dubbed audio tracks in different languages for an asset | ElevenLabs only           | ElevenLabs Dubbing API                                             | Video (required), Audio (required) | AWS S3 (if `uploadToMux=true`) |
 
 ## Compatability with Workflow DevKit
@@ -233,7 +233,7 @@ for (const chunk of result.chunks) {
 
 # Key Features
 
-- **Cost-Effective by Default**: Uses affordable frontier models like `gpt-5.1`, `claude-sonnet-4-5`, and `gemini-2.5-flash` to keep analysis costs low while maintaining high quality results
+- **Cost-Effective by Default**: Uses affordable frontier models like `gpt-5.1`, `claude-sonnet-4-5`, and `gemini-3-flash-preview` to keep analysis costs low while maintaining high quality results
 - **Multi-modal Analysis**: Combines storyboard images with video transcripts for richer understanding
 - **Tone Control**: Choose between neutral, playful, or professional analysis styles for summarization
 - **Prompt Customization**: Override specific prompt sections to tune workflows to your exact use case

package/dist/index.js

@@ -404,7 +404,7 @@ import { createOpenAI } from "@ai-sdk/openai";
 var DEFAULT_LANGUAGE_MODELS = {
   openai: "gpt-5.1",
   anthropic: "claude-sonnet-4-5",
-  google: "gemini-2.5-flash"
+  google: "gemini-3-flash-preview"
 };
 var DEFAULT_EMBEDDING_MODELS = {
   openai: "text-embedding-3-small",
@@ -1526,6 +1526,7 @@ var summarySchema = z4.object({
   title: z4.string(),
   description: z4.string()
 });
+var VALID_TONES = ["neutral", "playful", "professional"];
 var TONE_INSTRUCTIONS = {
   neutral: "Provide a clear, straightforward analysis.",
   playful: "Channel your inner diva! Answer with maximum sass, wit, and playful attitude. Don't hold back - be cheeky, clever, and delightfully snarky. Make it pop!",
@@ -1711,6 +1712,11 @@ async function getSummaryAndTags(assetId, options) {
     abortSignal: _abortSignal,
     promptOverrides
   } = options ?? {};
+  if (!VALID_TONES.includes(tone)) {
+    throw new Error(
+      `Invalid tone "${tone}". Valid tones are: ${VALID_TONES.join(", ")}`
+    );
+  }
   const config = await createWorkflowConfig(
     { ...options, model },
     provider