@byte_fluffy/nexra-sdk 0.1.0-alpha.52 → 0.1.0-alpha.53

package/README.md

@@ -4,6 +4,21 @@ TypeScript SDK for the Nexra Task API. It includes task execution, model discove
 asset upload/download, webhook verification, authoritative catalog quotes, and the
 browser-safe public model catalog.
 
+## Speech recognition
+
+Standard file recognition uses `run("bytedance/doubao-asr-standard-v2", input)`.
+Live recognition uses `transcription.stream({ model: "bytedance/doubao-asr-stream-v2",
+audio, configuration, signal })`, where `audio` is an `AsyncIterable<Uint8Array>`.
+The SDK owns WebSocket framing and decoding; applications own audio capture.
+Each event contains `{ final, response }`; `response.result.text` is a cumulative
+snapshot, not an append-only delta. End the audio iterator to finish normally;
+abort the signal to cancel. Node/Bun and browser builds use separate transports.
+
+See the [ASR integration guide](https://github.com/starrank-soft/nexra-monorepo/blob/refactor/typescript-restate-scaffold/docs/asr-sdk-integration.md)
+for VibePaper/StarCut deployment, authentication and stopping semantics. This ASR
+addition must be built/packaged or published before use; the previously published
+`0.1.0-alpha.50` does not include the streaming client.
+
 ```bash
 npm install @byte_fluffy/nexra-sdk@next
 ```
@@ -120,30 +135,6 @@ const result = await nexra.tasks.wait(task.id);
 Seedance 2.0 supports 4–15 seconds and Seedance 2.5 supports 4–30 seconds.
 The existing ByteDance model IDs retain their own supplies and prices.
 
-## MiniMax H3 Max
-
-`0.1.0-alpha.49` adds the official `minimax/MiniMax-H3-Max` model. It supports
-480P/768P output, 5–15 seconds, and image, video and audio references.
-
-```ts
-const model = "minimax/MiniMax-H3-Max";
-const state = await nexra.catalog.model(model, "video.generate");
-// The selected environment owns availability and current sale prices.
-console.log(state.available, state.prices);
-
-const task = await nexra.tasks.create(model, {
-  content: [{ type: "text", role: "prompt", text: "A paper boat drifts across a rain puddle." }],
-  duration: 5,
-  resolution: "480P",
-  aspect_ratio: "16:9",
-});
-const result = await nexra.tasks.wait(task.id);
-```
-
-Use the selected environment's published prices for estimates. The SDK's bundled
-catalog describes the model contract; channel costs and sale prices remain in
-the live catalog.
-
 ## Banana 2.1
 
 Use `google/gemini-nano-banana-2.1` for Banana 2.1. The model supports
@@ -463,92 +454,6 @@ const gpt6Prices = prices.filter(({ modelId }) =>
 );
 ```
 
-## Ark web search (Responses)
-
-Available since SDK `0.1.0-alpha.47` (`npm install @byte_fluffy/nexra-sdk@next`).
-
-DeepSeek V4.1 Flash (`deepseek/deepseek-v4-1-flash`), GLM 5.3 Flash
-(`z-ai/glm-5-3-flash`), Doubao Seed 2.1 Lite
-(`bytedance/doubao-seed-2-1-lite-260915`), and Kimi K3.1 Pro
-(`moonshot-ai/kimi-k3-1-pro`) support the Ark online content plugin through
-`/v1/responses`. The default SDK binding selects this endpoint. All four retain
-explicit Chat Completions bindings; DeepSeek also retains Messages.
-Search is a provider-executed tool, rather than a Chat `web_search_options` flag.
-
-```ts
-import { generateText } from "ai";
-import { openai } from "@ai-sdk/openai";
-import { createNexraLanguageModel } from "@byte_fluffy/nexra-sdk/language";
-
-const result = await generateText({
-  model: createNexraLanguageModel("deepseek/deepseek-v4-1-flash", {
-    apiKey: process.env.NEXRA_API_KEY!,
-    baseUrl: "https://vip-api.nexra-ai.com/v1",
-  }),
-  prompt: "Search for the official DeepSeek website and cite its URL.",
-  tools: { web_search: openai.tools.webSearch() },
-  providerOptions: {
-    openai: { maxToolCalls: 1 },
-    nexra: { web_search: { sources: ["search_engine"], max_keyword: 1, limit: 3 } },
-  },
-  maxOutputTokens: 512,
-  maxRetries: 0,
-});
-console.log(result.text, result.sources);
-```
-
-`providerOptions.nexra.web_search` preserves native tool fields such as `sources`,
-`max_keyword`, `limit`, and `user_location`; it requires the `web_search` tool.
-The same options work with `streamText`. Unpositioned native citations become
-URL sources; original Native bodies, raw stream events, and
-`finalStep.usage.raw.tool_usage_details.web_search` remain available.
-
-VIP configured search prices (CNY, checked 2026-11-01):
-
-| Content source | Channel cost / 1,000 uses | Nexra sale / 1,000 uses |
-| --- | ---: | ---: |
-| `search_engine` (default) | ¥4 | **¥4.4** |
-| `toutiao`, `douyin`, `moji` (each additional source) | ¥6 | ¥6.6 |
-
-A use is an actual upstream content-source search, **not an HTTP request or a
-returned result**. Multiple rounds, keywords, or content sources can incur
-multiple uses. Token charges are additional, including retrieved context.
-Declaring a tool does not itself incur a search fee if the model does not use
-it. Preauthorization reserves the configured search ceiling and settles the
-actual evidenced usage; set `maxToolCalls` and `max_keyword` to control that
-ceiling. Missing search evidence is not treated as free search.
-
-Current VIP token sale prices per million tokens:
-
-| Model | Input | Cached input | Output |
-| --- | ---: | ---: | ---: |
-| DeepSeek V4.1 Flash | ¥2.2 | ¥0.044 | ¥8.8 |
-| GLM 5.3 Flash | ¥0.88 | ¥0.253 | ¥3.08 |
-| Kimi K3.1 Pro | ¥14.3 | ¥1.43 | ¥74.8 |
-| Doubao Seed 2.1 Lite (non-audio input) | ¥0.88 | ¥0.176 | ¥2.97 |
-
-Seed audio input is ¥13.2/million tokens; cached audio input is ¥2.64/million.
-For Ark audio/video prompts in the AI SDK adapter, select
-`protocol: "openai-chat-completions"`; its native media parts retain their order. Kimi media requires bytes or Base64
-data URLs; the Chat binding derives URL support from the Native schema.
-The Responses search example above uses text. Native Responses media fields
-remain documented by each model's selected endpoint schema.
-
-GLM and Kimi K3.1 Pro thinking is always on. Use `reasoning: "low"` for minimum effort;
-`reasoning: "none"` fails locally. Native `none`/`minimal` effort aliases do not
-mean that these models can turn thinking off. Kimi does not use a `thinking`
-parameter. Its Responses endpoint permits `toolChoice: "auto"` (default) or
-`"none"`; forcing a particular tool or requiring a tool is rejected before
-fetch. With auto selection, search is billed only when actually used.
-
-These are the configured channel prices;
-the SDK does not dynamically apply upstream off-peak discounts. Provider account
-free quotas do not automatically make Nexra requests free. The selected plugin
-is separate from Doubao Search Custom; no Custom search service is used here.
-Always read the selected environment's live catalog prices before estimating
-charges. Official references: [online content plugin pricing](https://ark.volcengine.com/region:cn-beijing/docs/online-content-plugin-pricing)
-and [model pricing](https://console.volcengine.com/ark/region:cn-beijing/docs/model-pricing).
-
 ## Directory layout
 
 ```

package/dist/catalog.d.ts

@@ -1,6 +1,6 @@
-import { a as JsonObject } from './json-Cz0MkWQn.js';
-import { H as HttpTransport, N as NexraCatalogChangeParams, a as NexraCatalogChangePage, b as NexraCatalogModelState, c as NexraSalePriceList, C as CreateNexraQuoteRequest, d as NexraQuote, e as CreateNexraDisplayQuoteBatchRequest, f as NexraDisplayQuoteBatch, g as NexraCatalogRevision, h as NexraModelSpec, i as NexraModelEndpointSpec, j as NexraModelSpecFilter } from './media-geometry-COln1N_2.js';
-export { M as MediaGeometryField, k as MediaGeometryProjection, l as NexraBillingCurrency, m as NexraCatalogModelIdentity, n as NexraModelOperation, o as NexraSalePrice, p as NexraSettlement, U as UnifiedMediaGeometry, q as applyMediaGeometry, r as decodeMediaGeometry, s as encodeMediaGeometry, t as projectMediaGeometry } from './media-geometry-COln1N_2.js';
+import { J as JsonObject } from './json-dnsDzk-s.js';
+import { H as HttpTransport, A as NexraCatalogChangeParams, B as NexraCatalogChangePage, D as NexraCatalogModelState, t as NexraSalePriceList, a as CreateNexraQuoteRequest, r as NexraQuote, C as CreateNexraDisplayQuoteBatchRequest, m as NexraDisplayQuoteBatch, l as NexraCatalogRevision, p as NexraModelSpec, E as NexraModelEndpointSpec, q as NexraModelSpecFilter } from './media-geometry-B92BvuQL.js';
+export { M as MediaGeometryField, b as MediaGeometryProjection, k as NexraBillingCurrency, G as NexraCatalogModelIdentity, o as NexraModelOperation, s as NexraSalePrice, u as NexraSettlement, U as UnifiedMediaGeometry, w as applyMediaGeometry, x as decodeMediaGeometry, y as encodeMediaGeometry, z as projectMediaGeometry } from './media-geometry-B92BvuQL.js';
 
 declare function formatModelDisplayName(displayName: string, identity?: {
     modelId: string;

package/dist/catalog.js

@@ -9,8 +9,8 @@ import {
   listModelSpecs,
   projectMediaGeometry,
   resolveNexraLanguageReasoning
-} from "./chunk-V3KBU3J5.js";
-import "./chunk-LEZWVFQH.js";
+} from "./chunk-LWJWWD7Z.js";
+import "./chunk-V3F6VPMP.js";
 export {
   CatalogClient,
   applyMediaGeometry,