@speechify/ai-sdk-provider 0.0.0-stage → 0.1.0

package/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Speechify <developers@speechify.ai> (https://speechify.ai)
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

package/README.md

@@ -1,3 +1,180 @@
-# Temporary Holding Version
+# SpeechifyAI provider for the Vercel AI SDK
 
-This version is a temporary placeholder for this package. An operational version to replace this has been submitted for review and is awaiting a staged release.
+`@speechify/ai-sdk-provider` adds [SpeechifyAI](https://speechify.ai) text to speech to the [Vercel AI SDK](https://ai-sdk.dev).
+It implements the AI SDK's speech model specification (`SpeechModelV4`), so `generateSpeech()` works with Speechify's Simba 3 models and returns word-level speech marks with every clip.
+It is maintained by Speechify and calls [`POST /v1/audio/speech`](https://docs.speechify.ai/build/api-reference/v1/audio/speech) with `fetch`, with no other runtime dependency.
+
+## Install
+
+```bash
+npm install @speechify/ai-sdk-provider ai
+```
+
+Requires AI SDK 7 (`ai@^7` with `@ai-sdk/provider@^4`), which runs on Node.js 22 or later and other runtimes with `fetch`.
+
+Set your API key, which you can get by [signing up for free](https://platform.speechify.ai/signup?utm_source=npm&utm_medium=readme&utm_campaign=vercel-ai-sdk):
+
+```bash
+export SPEECHIFY_API_KEY="your-api-key"
+```
+
+## Example
+
+```ts
+import { writeFile } from 'node:fs/promises';
+import { generateSpeech } from 'ai';
+import { speechify } from '@speechify/ai-sdk-provider';
+
+const { audio, providerMetadata } = await generateSpeech({
+  model: speechify.speech('simba-3.2'),
+  text: 'Hello from Speechify and the AI SDK.',
+  voice: 'harper_32',
+});
+
+await writeFile('hello.mp3', audio.uint8Array);
+console.log(providerMetadata.speechify?.speechMarks);
+```
+
+## Provider instance
+
+`speechify` is a default instance that reads `SPEECHIFY_API_KEY` when a request is made.
+Use `createSpeechify` to configure your own:
+
+```ts
+import { createSpeechify } from '@speechify/ai-sdk-provider';
+
+const speechify = createSpeechify({
+  apiKey: process.env.SPEECHIFY_API_KEY,
+});
+```
+
+| Setting | Default | Notes |
+| --- | --- | --- |
+| `apiKey` | `SPEECHIFY_API_KEY` | Sent as `Authorization: Bearer <key>`. |
+| `baseURL` | `https://api.speechify.ai` | The provider appends `/v1/audio/speech`. |
+| `headers` | none | Added to every request, overriding the provider's own headers. |
+| `fetch` | `globalThis.fetch` | A custom implementation, for example for a proxy or tests. |
+
+## Models and voices
+
+| Model | Languages |
+| --- | --- |
+| `simba-3.2` | English. Lowest latency and richest expressivity. Every English voice, cloned voices included. |
+| `simba-3.0` | English, German, Spanish (Spain and Mexico), French, Italian and Brazilian Portuguese. |
+
+A voice works with a model when the model is in that voice's `models` list in [`GET /v1/voices`](https://docs.speechify.ai/build/api-reference/v1/voices/get).
+`harper_32` is the default and works with both models.
+A voice the model cannot serve fails with a `400`, and an unknown voice with a `404`.
+
+## Options
+
+| `generateSpeech()` option | Sent to Speechify as | Behaviour |
+| --- | --- | --- |
+| `text` | `input` | Plain text or SSML, up to 2,000 characters per request, markup included. |
+| `voice` | `voice_id` | Defaults to `harper_32`. |
+| `outputFormat` | `audio_format` or `output_format` | Defaults to `mp3`. `mp3`, `wav`, `ogg`, `aac` and `pcm` go to `audio_format`. Codec strings (`mp3_24000_128`, `pcm_16000`, `ulaw_8000`, `wav_48000` and the rest of the [API's list](https://docs.speechify.ai/build/api-reference/v1/audio/speech)) go to `output_format`. `mulaw` and `ulaw` mean `ulaw_8000`. Anything else falls back to `mp3` with a warning. |
+| `speed` | SSML `<prosody rate>` | A multiplier from 0.5 to 100: `1.25` sends `rate="+25%"`. Plain text is escaped and wrapped in `<speak>`, and SSML input gets the prosody element inside its own `<speak>`. Billing and speech-mark offsets are unchanged. |
+| `language` | `language` | An ISO 639-1 code (`de`) or a locale (`de-DE`). `auto` sends nothing, which is the API's documented auto-detect mode. |
+| `instructions` | not sent | Speechify has no free-text instructions field, so this always produces a warning. |
+| `providerOptions.speechify.loudnessNormalization` | `options.loudness_normalization` | Normalizes loudness to -14 LUFS. Adds latency. |
+| `providerOptions.speechify.textNormalization` | `options.text_normalization` | Reads numbers and dates as words. On by default in the API. |
+| `headers` | request headers | Per-call headers, applied last. |
+| `abortSignal` | | Cancels the request. |
+
+```ts
+const { audio } = await generateSpeech({
+  model: speechify.speech('simba-3.0'),
+  text: 'Guten Tag, das ist ein kurzer Test.',
+  voice: 'anton',
+  language: 'de',
+  outputFormat: 'mp3_24000_128',
+  speed: 1.1,
+  providerOptions: { speechify: { loudnessNormalization: true } },
+});
+```
+
+`speed` adds up to 50 characters of markup to `input`, and the 2,000-character limit counts markup.
+On plain text it also escapes `&`, `<` and `>`, so each one counts as its entity (`&amp;` is five characters).
+
+## Warnings
+
+An option that Speechify cannot honour is never dropped silently.
+It comes back on `result.warnings`, and the AI SDK logs it unless you turn warning logging off.
+
+| Warning `feature` | When | What the provider does |
+| --- | --- | --- |
+| `instructions` | `instructions` is set | Does not send it. Shape delivery with SSML in `text` instead: breaks and prosody rate are applied by the Simba 3 models. |
+| `outputFormat` | The format is not one Speechify serves (for example `flac` or `opus`) | Requests `mp3`. |
+| `speed` | `speed` is below 0.5 or above 100 | Clamps it to the nearest bound. |
+| `speed` | `speed` is zero, negative or not a number | Ignores it. |
+| `providerOptions.speechify.<key>` | An unknown key under `providerOptions.speechify` | Does not send it. |
+
+Errors are thrown rather than warned about:
+
+- A missing API key throws `LoadAPIKeyError` before any request is made.
+- A `providerOptions.speechify` value of the wrong type throws `InvalidArgumentError`.
+- A non-2xx response throws `APICallError` with the API's error code, message and request id. `408`, `409`, `429`, `5xx` and network failures are marked retryable, so `generateSpeech()` retries them up to `maxRetries` times.
+
+## Speech marks and metadata
+
+Every result carries Speechify's speech marks and billing count under `providerMetadata.speechify`:
+
+| Field | Value |
+| --- | --- |
+| `speechMarks` | The [speech marks](https://docs.speechify.ai/build/guides/text-to-speech/speech-marks) for the clip: one sentence-level object with a `chunks` array of words. Times are in milliseconds. `start` and `end` index characters of your text. |
+| `billableCharactersCount` | Characters billed for the request. AI SDK telemetry also receives it as `usage.billable_characters_count`. |
+| `audioFormat` | The codec the API returned: `mp3`, `wav`, `ogg`, `aac`, `pcm` or `ulaw`. |
+| `outputFormat` | The full codec string, when you asked for one (for example `pcm_16000`). |
+| `requestId` | The `Speechify-Request-Id`, to quote to support. |
+
+```ts
+import type { SpeechifySpeechProviderMetadata } from '@speechify/ai-sdk-provider';
+
+const { speechMarks } = result.providerMetadata.speechify as SpeechifySpeechProviderMetadata;
+for (const word of speechMarks?.chunks ?? []) {
+  console.log(word.value, word.start_time, word.end_time);
+}
+```
+
+## Headless formats and `audio.mediaType`
+
+The AI SDK sets `audio.mediaType` by sniffing the audio bytes, which works for `mp3`, `wav`, `ogg` and `aac`.
+Raw PCM and u-law have no header, so the SDK falls back to the `outputFormat` you passed.
+`pcm` gives `audio/pcm` and `mulaw` gives `audio/mulaw`, but a codec string such as `pcm_16000` gives the SDK's default, `audio/mp3`.
+For headerless formats, read the encoding and sample rate from `providerMetadata.speechify.outputFormat` instead of `audio.mediaType`.
+`pcm` without a rate is 16-bit little-endian mono at 24 kHz, and `mulaw` is `ulaw_8000`.
+
+## API version
+
+Every request sends `Speechify-Version: 2026-09-30`, so the provider behaves the same whatever your workspace's default API version is.
+At this version the legacy `simba-english` and `simba-multilingual` models return `400 model_retired`, and `pcm_16000` is true 16 kHz audio.
+To pin a different version, set the header yourself:
+
+```ts
+const speechify = createSpeechify({ headers: { 'Speechify-Version': '2026-09-13' } });
+```
+
+A new release of this package moves the pin forward only with a note on what changed.
+The pinned value is exported as `SPEECHIFY_API_VERSION`.
+
+## What the provider does not do
+
+- **Streaming.** The AI SDK's speech interface returns a whole clip. For audio you play while it is generated, call [`POST /v1/audio/stream`](https://docs.speechify.ai/build/guides/text-to-speech/streaming) directly.
+- **Texts over 2,000 characters.** Split them, or use the streaming endpoint, which accepts 20,000.
+- **Browser keys.** Call it from server code. An API key shipped to a browser is readable by anyone who opens the page.
+
+## Attribution headers
+
+The provider sends `Speechify-Caller: vercel-ai-sdk` and `Speechify-Caller-Version` with this package's version, so the requests show up as this integration in your workspace's request log.
+The headers never affect access, rate limits or price.
+
+## Links
+
+- [Using Speechify with the AI SDK](https://docs.speechify.ai/build/guides/integrations/vercel-ai-sdk?utm_source=npm&utm_medium=readme&utm_campaign=vercel-ai-sdk)
+- [AI SDK speech documentation](https://ai-sdk.dev/docs/ai-sdk-core/speech)
+- [Speechify API reference](https://docs.speechify.ai/build/api-reference/v1/audio/speech)
+- [Issues](https://github.com/Speechify-AI/ai-sdk-provider/issues)
+
+## License
+
+MIT

package/dist/index.cjs

@@ -0,0 +1,336 @@
+Object.defineProperty(exports, Symbol.toStringTag, { value: "Module" });
+let _ai_sdk_provider = require("@ai-sdk/provider");
+//#region src/speechify-speech-options.ts
+/** Values of the API's `audio_format` field. */
+const SPEECHIFY_AUDIO_FORMATS = [
+	"mp3",
+	"wav",
+	"ogg",
+	"aac",
+	"pcm"
+];
+/** Values of the API's `output_format` field (`codec_sampleRate_bitrate`). */
+const SPEECHIFY_OUTPUT_FORMATS = [
+	"pcm_8000",
+	"pcm_16000",
+	"pcm_22050",
+	"pcm_24000",
+	"pcm_44100",
+	"pcm_48000",
+	"mp3_22050_32",
+	"mp3_22050_64",
+	"mp3_22050_96",
+	"mp3_22050_128",
+	"mp3_22050_160",
+	"mp3_22050_192",
+	"mp3_24000_32",
+	"mp3_24000_64",
+	"mp3_24000_96",
+	"mp3_24000_128",
+	"mp3_24000_160",
+	"mp3_24000_192",
+	"wav_24000",
+	"wav_48000",
+	"ulaw_8000",
+	"ogg_24000",
+	"aac_24000"
+];
+//#endregion
+//#region src/ssml.ts
+/** `<prosody rate>` accepts -50% to +9900%, so speed is bounded to 0.5x..100x. */
+const MIN_SPEED = .5;
+const SPEAK_OPEN_AT_START = /^<speak(\s[^>]*)?>/;
+const SPEAK_CLOSE = "</speak>";
+function isSSML(text) {
+	const trimmed = text.trim();
+	return SPEAK_OPEN_AT_START.test(trimmed) && trimmed.endsWith(SPEAK_CLOSE);
+}
+/**
+* Applies a speed multiplier as an SSML `<prosody rate>` around the input.
+* Plain text is escaped and wrapped; SSML input gets the prosody element
+* inside its own `<speak>` root. `speed` must already be within bounds.
+*/
+function withSpeechRate(text, speed) {
+	const percent = Math.round((speed - 1) * 1e4) / 100;
+	if (percent === 0) return text;
+	const rate = `${percent > 0 ? "+" : ""}${percent}%`;
+	if (isSSML(text)) {
+		const trimmed = text.trim();
+		const open = trimmed.match(SPEAK_OPEN_AT_START)[0];
+		return `${open}<prosody rate="${rate}">${trimmed.slice(open.length, trimmed.length - 8)}</prosody>${SPEAK_CLOSE}`;
+	}
+	return `<speak><prosody rate="${rate}">${escapeXmlText(text)}</prosody>${SPEAK_CLOSE}`;
+}
+function escapeXmlText(text) {
+	let out = "";
+	for (const char of text) {
+		const code = char.codePointAt(0);
+		if (char === "&") out += "&amp;";
+		else if (char === "<") out += "&lt;";
+		else if (char === ">") out += "&gt;";
+		else if (isXmlChar(code)) out += char;
+		else out += " ";
+	}
+	return out;
+}
+function isXmlChar(code) {
+	return code === 9 || code === 10 || code === 13 || code >= 32 && code <= 55295 || code >= 57344 && code <= 65533 || code >= 65536 && code <= 1114111;
+}
+//#endregion
+//#region src/speechify-speech-model.ts
+const PROVIDER_OPTION_KEYS = {
+	loudnessNormalization: "loudness_normalization",
+	textNormalization: "text_normalization"
+};
+var SpeechifySpeechModel = class {
+	modelId;
+	config;
+	specificationVersion = "v4";
+	constructor(modelId, config) {
+		this.modelId = modelId;
+		this.config = config;
+	}
+	get provider() {
+		return this.config.provider;
+	}
+	async doGenerate(options) {
+		const timestamp = /* @__PURE__ */ new Date();
+		const { body, warnings } = this.getArgs(options);
+		const url = `${this.config.baseURL}/v1/audio/speech`;
+		const headers = this.buildHeaders(options.headers);
+		const fetchFn = this.config.fetch ?? globalThis.fetch;
+		let response;
+		try {
+			response = await fetchFn(url, {
+				method: "POST",
+				headers,
+				body: JSON.stringify(body),
+				signal: options.abortSignal
+			});
+		} catch (error) {
+			if (isAbortError(error)) throw error;
+			throw new _ai_sdk_provider.APICallError({
+				message: `Cannot connect to the Speechify API: ${errorMessage(error)}`,
+				url,
+				requestBodyValues: body,
+				cause: error,
+				isRetryable: true
+			});
+		}
+		const responseHeaders = Object.fromEntries(response.headers.entries());
+		const responseBody = await response.text();
+		if (!response.ok) throw apiCallError({
+			url,
+			body,
+			response,
+			responseHeaders,
+			responseBody
+		});
+		let data;
+		try {
+			data = JSON.parse(responseBody);
+		} catch (error) {
+			throw new _ai_sdk_provider.InvalidResponseDataError({
+				data: responseBody.slice(0, 500),
+				message: `The Speechify API returned a body that is not JSON: ${errorMessage(error)}`
+			});
+		}
+		if (typeof data?.audio_data !== "string" || data.audio_data.length === 0) throw new _ai_sdk_provider.InvalidResponseDataError({
+			data: {
+				...data,
+				audio_data: void 0
+			},
+			message: "The Speechify API response has no audio_data."
+		});
+		const metadata = {
+			audioFormat: data.audio_format,
+			billableCharactersCount: data.billable_characters_count ?? null,
+			speechMarks: data.speech_marks ?? null
+		};
+		if (data.output_format != null) metadata.outputFormat = data.output_format;
+		const requestId = response.headers.get("speechify-request-id");
+		if (requestId != null) metadata.requestId = requestId;
+		return {
+			audio: data.audio_data,
+			warnings,
+			...data.billable_characters_count != null && { usage: { billable_characters_count: data.billable_characters_count } },
+			request: { body },
+			response: {
+				timestamp,
+				modelId: this.modelId,
+				headers: responseHeaders
+			},
+			providerMetadata: { speechify: metadata }
+		};
+	}
+	getArgs({ text, voice, outputFormat, instructions, speed, language, providerOptions }) {
+		const warnings = [];
+		let input = text;
+		if (speed != null) {
+			if (!Number.isFinite(speed) || speed <= 0) warnings.push({
+				type: "unsupported",
+				feature: "speed",
+				details: `speed must be a positive number; ${speed} was ignored.`
+			});
+			else {
+				const bounded = Math.min(Math.max(speed, MIN_SPEED), 100);
+				if (bounded !== speed) warnings.push({
+					type: "unsupported",
+					feature: "speed",
+					details: `Speechify supports speed from ${MIN_SPEED} to 100; ${speed} was clamped to ${bounded}.`
+				});
+				input = withSpeechRate(text, bounded);
+			}
+		}
+		const body = {
+			input,
+			voice_id: voice ?? "harper_32",
+			model: this.modelId,
+			...resolveOutputFormat(outputFormat, warnings)
+		};
+		if (language != null && language !== "" && language.toLowerCase() !== "auto") body.language = language;
+		if (instructions != null && instructions !== "") warnings.push({
+			type: "unsupported",
+			feature: "instructions",
+			details: "Speechify has no free-text instructions field. Shape delivery with SSML in the text instead (breaks and prosody rate)."
+		});
+		const apiOptions = parseProviderOptions(providerOptions?.speechify, warnings);
+		if (apiOptions != null) body.options = apiOptions;
+		return {
+			body,
+			warnings
+		};
+	}
+	buildHeaders(callHeaders) {
+		const headers = new Headers({
+			Authorization: `Bearer ${loadApiKey(this.config.apiKey)}`,
+			"Content-Type": "application/json",
+			...this.config.defaultHeaders
+		});
+		for (const source of [this.config.headers, callHeaders]) for (const [name, value] of Object.entries(source ?? {})) if (value != null) headers.set(name, value);
+		return headers;
+	}
+};
+function resolveOutputFormat(requested, warnings) {
+	if (requested == null || requested.trim() === "") return { audio_format: "mp3" };
+	const format = requested.trim().toLowerCase();
+	if (format === "mulaw" || format === "ulaw") return { output_format: "ulaw_8000" };
+	if (SPEECHIFY_AUDIO_FORMATS.includes(format)) return { audio_format: format };
+	if (SPEECHIFY_OUTPUT_FORMATS.includes(format)) return { output_format: format };
+	warnings.push({
+		type: "unsupported",
+		feature: "outputFormat",
+		details: `Speechify does not support "${requested}"; returned mp3 instead. Supported: ${[...SPEECHIFY_AUDIO_FORMATS, ...SPEECHIFY_OUTPUT_FORMATS].join(", ")}.`
+	});
+	return { audio_format: "mp3" };
+}
+function parseProviderOptions(raw, warnings) {
+	if (raw == null) return void 0;
+	if (typeof raw !== "object" || Array.isArray(raw)) throw new _ai_sdk_provider.InvalidArgumentError({
+		argument: "providerOptions.speechify",
+		message: "providerOptions.speechify must be an object."
+	});
+	const options = {};
+	for (const [key, value] of Object.entries(raw)) {
+		if (value === void 0) continue;
+		if (!Object.hasOwn(PROVIDER_OPTION_KEYS, key)) {
+			warnings.push({
+				type: "unsupported",
+				feature: `providerOptions.speechify.${key}`,
+				details: `Unknown option, not sent. Supported: ${Object.keys(PROVIDER_OPTION_KEYS).join(", ")}.`
+			});
+			continue;
+		}
+		if (typeof value !== "boolean") throw new _ai_sdk_provider.InvalidArgumentError({
+			argument: `providerOptions.speechify.${key}`,
+			message: `providerOptions.speechify.${key} must be a boolean.`
+		});
+		options[PROVIDER_OPTION_KEYS[key]] = value;
+	}
+	return Object.keys(options).length > 0 ? options : void 0;
+}
+function loadApiKey(apiKey) {
+	if (apiKey != null && apiKey !== "") return apiKey;
+	const fromEnv = typeof process !== "undefined" ? process.env?.SPEECHIFY_API_KEY : void 0;
+	if (fromEnv != null && fromEnv !== "") return fromEnv;
+	throw new _ai_sdk_provider.LoadAPIKeyError({ message: "Speechify API key is missing. Pass it as the apiKey setting of createSpeechify() or set the SPEECHIFY_API_KEY environment variable." });
+}
+function apiCallError({ url, body, response, responseHeaders, responseBody }) {
+	let data;
+	try {
+		data = JSON.parse(responseBody);
+	} catch {
+		data = void 0;
+	}
+	const code = data?.error?.code;
+	const detail = data?.error?.message ?? (responseBody.slice(0, 200) || response.statusText);
+	const requestId = data?.request_id ?? response.headers.get("speechify-request-id");
+	return new _ai_sdk_provider.APICallError({
+		message: `Speechify API error ${response.status}${code ? ` ${code}` : ""}: ${detail}` + (requestId ? ` (request id ${requestId})` : ""),
+		url,
+		requestBodyValues: body,
+		statusCode: response.status,
+		responseHeaders,
+		responseBody,
+		data
+	});
+}
+function isAbortError(error) {
+	return error instanceof Error && (error.name === "AbortError" || error.name === "TimeoutError");
+}
+function errorMessage(error) {
+	return error instanceof Error ? error.message : String(error);
+}
+//#endregion
+//#region src/version.ts
+/** This package's version, injected from package.json at build time. */
+const VERSION = "0.1.0";
+//#endregion
+//#region src/speechify-provider.ts
+/**
+* The dated Speechify API version every request pins via `Speechify-Version`,
+* so behaviour never depends on the workspace's default version.
+*/
+const SPEECHIFY_API_VERSION = "2026-09-30";
+/** Identifies this integration's traffic to Speechify (`Speechify-Caller`). */
+const SPEECHIFY_CALLER = "vercel-ai-sdk";
+const DEFAULT_BASE_URL = "https://api.speechify.ai";
+/** Creates a Speechify provider instance. */
+function createSpeechify(settings = {}) {
+	const baseURL = (settings.baseURL ?? DEFAULT_BASE_URL).replace(/\/+$/, "");
+	const createSpeechModel = (modelId) => new SpeechifySpeechModel(modelId, {
+		provider: "speechify.speech",
+		baseURL,
+		apiKey: settings.apiKey,
+		defaultHeaders: {
+			"Speechify-Caller": SPEECHIFY_CALLER,
+			"Speechify-Caller-Version": VERSION,
+			"Speechify-Version": SPEECHIFY_API_VERSION
+		},
+		headers: settings.headers,
+		fetch: settings.fetch
+	});
+	const noSuchModel = (modelType) => (modelId) => {
+		throw new _ai_sdk_provider.NoSuchModelError({
+			modelId,
+			modelType,
+			message: `Speechify provides speech models only; use speechify.speech("${modelId}") with generateSpeech().`
+		});
+	};
+	return {
+		specificationVersion: "v4",
+		speech: createSpeechModel,
+		speechModel: createSpeechModel,
+		languageModel: noSuchModel("languageModel"),
+		embeddingModel: noSuchModel("embeddingModel"),
+		imageModel: noSuchModel("imageModel")
+	};
+}
+/** Default provider instance. Reads `SPEECHIFY_API_KEY` from the environment. */
+const speechify = createSpeechify();
+//#endregion
+exports.SPEECHIFY_API_VERSION = SPEECHIFY_API_VERSION;
+exports.SPEECHIFY_CALLER = SPEECHIFY_CALLER;
+exports.VERSION = VERSION;
+exports.createSpeechify = createSpeechify;
+exports.speechify = speechify;

package/dist/index.d.cts

@@ -0,0 +1,98 @@
+import { ProviderV4, SpeechModelV4 } from "@ai-sdk/provider";
+//#region src/speechify-speech-options.d.ts
+/**
+ * Speech models served by `POST /v1/audio/speech`.
+ *
+ * - `simba-3.2`: lowest latency and richest expressivity, English only.
+ * - `simba-3.0`: English plus de-DE, es-ES, es-MX, fr-FR, it-IT and pt-BR.
+ */
+type SpeechifySpeechModelId = 'simba-3.2' | 'simba-3.0' | (string & {});
+/** Values of the API's `audio_format` field. */
+declare const SPEECHIFY_AUDIO_FORMATS: readonly ["mp3", "wav", "ogg", "aac", "pcm"];
+/** Values of the API's `output_format` field (`codec_sampleRate_bitrate`). */
+declare const SPEECHIFY_OUTPUT_FORMATS: readonly ["pcm_8000", "pcm_16000", "pcm_22050", "pcm_24000", "pcm_44100", "pcm_48000", "mp3_22050_32", "mp3_22050_64", "mp3_22050_96", "mp3_22050_128", "mp3_22050_160", "mp3_22050_192", "mp3_24000_32", "mp3_24000_64", "mp3_24000_96", "mp3_24000_128", "mp3_24000_160", "mp3_24000_192", "wav_24000", "wav_48000", "ulaw_8000", "ogg_24000", "aac_24000"];
+type SpeechifyAudioFormat = (typeof SPEECHIFY_AUDIO_FORMATS)[number];
+type SpeechifyCodecOutputFormat = (typeof SPEECHIFY_OUTPUT_FORMATS)[number];
+/** Every value the `outputFormat` option of `generateSpeech()` accepts. */
+type SpeechifyOutputFormat = SpeechifyAudioFormat | SpeechifyCodecOutputFormat | 'mulaw' | 'ulaw';
+/** Options read from `providerOptions.speechify`. */
+interface SpeechifySpeechModelOptions {
+  /** Normalize loudness to -14 LUFS. Adds latency. API default: false. */
+  loudnessNormalization?: boolean;
+  /** Read numbers, dates and the like as words ("55" as "fifty five"). API default: true. */
+  textNormalization?: boolean;
+}
+//#endregion
+//#region src/speechify-provider.d.ts
+/**
+ * The dated Speechify API version every request pins via `Speechify-Version`,
+ * so behaviour never depends on the workspace's default version.
+ */
+export declare const SPEECHIFY_API_VERSION = "2026-09-30";
+/** Identifies this integration's traffic to Speechify (`Speechify-Caller`). */
+export declare const SPEECHIFY_CALLER = "vercel-ai-sdk";
+interface SpeechifyProviderSettings {
+  /**
+   * Speechify API key, sent as a Bearer token. Defaults to the
+   * `SPEECHIFY_API_KEY` environment variable, read when a request is made.
+   */
+  apiKey?: string;
+  /** API base URL. Defaults to `https://api.speechify.ai`. */
+  baseURL?: string;
+  /**
+   * Headers added to every request. They override the provider's own
+   * headers, so `Speechify-Version` here replaces the pinned version.
+   */
+  headers?: Record<string, string>;
+  /** Custom fetch implementation, for example for proxies or tests. */
+  fetch?: typeof globalThis.fetch;
+}
+interface SpeechifyProvider extends ProviderV4 {
+  /** Creates a speech model for `generateSpeech()`. */
+  speech(modelId: SpeechifySpeechModelId): SpeechModelV4;
+  /** Creates a speech model for `generateSpeech()`. */
+  speechModel(modelId: SpeechifySpeechModelId): SpeechModelV4;
+}
+/** Creates a Speechify provider instance. */
+export declare function createSpeechify(settings?: SpeechifyProviderSettings): SpeechifyProvider;
+/** Default provider instance. Reads `SPEECHIFY_API_KEY` from the environment. */
+export declare const speechify: SpeechifyProvider;
+//#endregion
+//#region src/speechify-api-types.d.ts
+/** One timed segment of the synthesized speech. */
+type SpeechifySpeechMark = {
+  /** Segment kind, for example `word` or `sentence`. */
+  type: string;
+  /** Start offset in the input text, in characters. */
+  start: number;
+  /** End offset in the input text, in characters. */
+  end: number;
+  /** Start time in the audio, in milliseconds. */
+  start_time: number;
+  /** End time in the audio, in milliseconds. */
+  end_time: number;
+  /** The text this segment speaks. */
+  value: string;
+};
+/** Speech marks for a clip: the whole text, with one chunk per word. */
+type SpeechifySpeechMarks = SpeechifySpeechMark & {
+  chunks: SpeechifySpeechMark[];
+};
+/** Shape of `providerMetadata.speechify` on a `generateSpeech()` result. */
+type SpeechifySpeechProviderMetadata = {
+  /** Codec of the returned audio: mp3, wav, ogg, aac, pcm or ulaw. */
+  audioFormat: string;
+  /** Full `codec_sampleRate_bitrate` string, when one was requested. */
+  outputFormat?: string;
+  /** Characters billed for the request. */
+  billableCharactersCount: number | null;
+  speechMarks: SpeechifySpeechMarks | null;
+  /** `Speechify-Request-Id` of the response. */
+  requestId?: string;
+};
+//#endregion
+//#region src/version.d.ts
+/** This package's version, injected from package.json at build time. */
+export declare const VERSION: string;
+//#endregion
+export type { SpeechifyAudioFormat, SpeechifyCodecOutputFormat, SpeechifyOutputFormat, SpeechifyProvider, SpeechifyProviderSettings, SpeechifySpeechMark, SpeechifySpeechMarks, SpeechifySpeechModelId, SpeechifySpeechModelOptions, SpeechifySpeechProviderMetadata };

package/dist/index.d.ts

@@ -0,0 +1,98 @@
+import { ProviderV4, SpeechModelV4 } from "@ai-sdk/provider";
+//#region src/speechify-speech-options.d.ts
+/**
+ * Speech models served by `POST /v1/audio/speech`.
+ *
+ * - `simba-3.2`: lowest latency and richest expressivity, English only.
+ * - `simba-3.0`: English plus de-DE, es-ES, es-MX, fr-FR, it-IT and pt-BR.
+ */
+type SpeechifySpeechModelId = 'simba-3.2' | 'simba-3.0' | (string & {});
+/** Values of the API's `audio_format` field. */
+declare const SPEECHIFY_AUDIO_FORMATS: readonly ["mp3", "wav", "ogg", "aac", "pcm"];
+/** Values of the API's `output_format` field (`codec_sampleRate_bitrate`). */
+declare const SPEECHIFY_OUTPUT_FORMATS: readonly ["pcm_8000", "pcm_16000", "pcm_22050", "pcm_24000", "pcm_44100", "pcm_48000", "mp3_22050_32", "mp3_22050_64", "mp3_22050_96", "mp3_22050_128", "mp3_22050_160", "mp3_22050_192", "mp3_24000_32", "mp3_24000_64", "mp3_24000_96", "mp3_24000_128", "mp3_24000_160", "mp3_24000_192", "wav_24000", "wav_48000", "ulaw_8000", "ogg_24000", "aac_24000"];
+type SpeechifyAudioFormat = (typeof SPEECHIFY_AUDIO_FORMATS)[number];
+type SpeechifyCodecOutputFormat = (typeof SPEECHIFY_OUTPUT_FORMATS)[number];
+/** Every value the `outputFormat` option of `generateSpeech()` accepts. */
+type SpeechifyOutputFormat = SpeechifyAudioFormat | SpeechifyCodecOutputFormat | 'mulaw' | 'ulaw';
+/** Options read from `providerOptions.speechify`. */
+interface SpeechifySpeechModelOptions {
+  /** Normalize loudness to -14 LUFS. Adds latency. API default: false. */
+  loudnessNormalization?: boolean;
+  /** Read numbers, dates and the like as words ("55" as "fifty five"). API default: true. */
+  textNormalization?: boolean;
+}
+//#endregion
+//#region src/speechify-provider.d.ts
+/**
+ * The dated Speechify API version every request pins via `Speechify-Version`,
+ * so behaviour never depends on the workspace's default version.
+ */
+export declare const SPEECHIFY_API_VERSION = "2026-09-30";
+/** Identifies this integration's traffic to Speechify (`Speechify-Caller`). */
+export declare const SPEECHIFY_CALLER = "vercel-ai-sdk";
+interface SpeechifyProviderSettings {
+  /**
+   * Speechify API key, sent as a Bearer token. Defaults to the
+   * `SPEECHIFY_API_KEY` environment variable, read when a request is made.
+   */
+  apiKey?: string;
+  /** API base URL. Defaults to `https://api.speechify.ai`. */
+  baseURL?: string;
+  /**
+   * Headers added to every request. They override the provider's own
+   * headers, so `Speechify-Version` here replaces the pinned version.
+   */
+  headers?: Record<string, string>;
+  /** Custom fetch implementation, for example for proxies or tests. */
+  fetch?: typeof globalThis.fetch;
+}
+interface SpeechifyProvider extends ProviderV4 {
+  /** Creates a speech model for `generateSpeech()`. */
+  speech(modelId: SpeechifySpeechModelId): SpeechModelV4;
+  /** Creates a speech model for `generateSpeech()`. */
+  speechModel(modelId: SpeechifySpeechModelId): SpeechModelV4;
+}
+/** Creates a Speechify provider instance. */
+export declare function createSpeechify(settings?: SpeechifyProviderSettings): SpeechifyProvider;
+/** Default provider instance. Reads `SPEECHIFY_API_KEY` from the environment. */
+export declare const speechify: SpeechifyProvider;
+//#endregion
+//#region src/speechify-api-types.d.ts
+/** One timed segment of the synthesized speech. */
+type SpeechifySpeechMark = {
+  /** Segment kind, for example `word` or `sentence`. */
+  type: string;
+  /** Start offset in the input text, in characters. */
+  start: number;
+  /** End offset in the input text, in characters. */
+  end: number;
+  /** Start time in the audio, in milliseconds. */
+  start_time: number;
+  /** End time in the audio, in milliseconds. */
+  end_time: number;
+  /** The text this segment speaks. */
+  value: string;
+};
+/** Speech marks for a clip: the whole text, with one chunk per word. */
+type SpeechifySpeechMarks = SpeechifySpeechMark & {
+  chunks: SpeechifySpeechMark[];
+};
+/** Shape of `providerMetadata.speechify` on a `generateSpeech()` result. */
+type SpeechifySpeechProviderMetadata = {
+  /** Codec of the returned audio: mp3, wav, ogg, aac, pcm or ulaw. */
+  audioFormat: string;
+  /** Full `codec_sampleRate_bitrate` string, when one was requested. */
+  outputFormat?: string;
+  /** Characters billed for the request. */
+  billableCharactersCount: number | null;
+  speechMarks: SpeechifySpeechMarks | null;
+  /** `Speechify-Request-Id` of the response. */
+  requestId?: string;
+};
+//#endregion
+//#region src/version.d.ts
+/** This package's version, injected from package.json at build time. */
+export declare const VERSION: string;
+//#endregion
+export type { SpeechifyAudioFormat, SpeechifyCodecOutputFormat, SpeechifyOutputFormat, SpeechifyProvider, SpeechifyProviderSettings, SpeechifySpeechMark, SpeechifySpeechMarks, SpeechifySpeechModelId, SpeechifySpeechModelOptions, SpeechifySpeechProviderMetadata };

package/dist/index.js

@@ -0,0 +1,331 @@
+import { APICallError, InvalidArgumentError, InvalidResponseDataError, LoadAPIKeyError, NoSuchModelError } from "@ai-sdk/provider";
+//#region src/speechify-speech-options.ts
+/** Values of the API's `audio_format` field. */
+const SPEECHIFY_AUDIO_FORMATS = [
+	"mp3",
+	"wav",
+	"ogg",
+	"aac",
+	"pcm"
+];
+/** Values of the API's `output_format` field (`codec_sampleRate_bitrate`). */
+const SPEECHIFY_OUTPUT_FORMATS = [
+	"pcm_8000",
+	"pcm_16000",
+	"pcm_22050",
+	"pcm_24000",
+	"pcm_44100",
+	"pcm_48000",
+	"mp3_22050_32",
+	"mp3_22050_64",
+	"mp3_22050_96",
+	"mp3_22050_128",
+	"mp3_22050_160",
+	"mp3_22050_192",
+	"mp3_24000_32",
+	"mp3_24000_64",
+	"mp3_24000_96",
+	"mp3_24000_128",
+	"mp3_24000_160",
+	"mp3_24000_192",
+	"wav_24000",
+	"wav_48000",
+	"ulaw_8000",
+	"ogg_24000",
+	"aac_24000"
+];
+//#endregion
+//#region src/ssml.ts
+/** `<prosody rate>` accepts -50% to +9900%, so speed is bounded to 0.5x..100x. */
+const MIN_SPEED = .5;
+const SPEAK_OPEN_AT_START = /^<speak(\s[^>]*)?>/;
+const SPEAK_CLOSE = "</speak>";
+function isSSML(text) {
+	const trimmed = text.trim();
+	return SPEAK_OPEN_AT_START.test(trimmed) && trimmed.endsWith(SPEAK_CLOSE);
+}
+/**
+* Applies a speed multiplier as an SSML `<prosody rate>` around the input.
+* Plain text is escaped and wrapped; SSML input gets the prosody element
+* inside its own `<speak>` root. `speed` must already be within bounds.
+*/
+function withSpeechRate(text, speed) {
+	const percent = Math.round((speed - 1) * 1e4) / 100;
+	if (percent === 0) return text;
+	const rate = `${percent > 0 ? "+" : ""}${percent}%`;
+	if (isSSML(text)) {
+		const trimmed = text.trim();
+		const open = trimmed.match(SPEAK_OPEN_AT_START)[0];
+		return `${open}<prosody rate="${rate}">${trimmed.slice(open.length, trimmed.length - 8)}</prosody>${SPEAK_CLOSE}`;
+	}
+	return `<speak><prosody rate="${rate}">${escapeXmlText(text)}</prosody>${SPEAK_CLOSE}`;
+}
+function escapeXmlText(text) {
+	let out = "";
+	for (const char of text) {
+		const code = char.codePointAt(0);
+		if (char === "&") out += "&amp;";
+		else if (char === "<") out += "&lt;";
+		else if (char === ">") out += "&gt;";
+		else if (isXmlChar(code)) out += char;
+		else out += " ";
+	}
+	return out;
+}
+function isXmlChar(code) {
+	return code === 9 || code === 10 || code === 13 || code >= 32 && code <= 55295 || code >= 57344 && code <= 65533 || code >= 65536 && code <= 1114111;
+}
+//#endregion
+//#region src/speechify-speech-model.ts
+const PROVIDER_OPTION_KEYS = {
+	loudnessNormalization: "loudness_normalization",
+	textNormalization: "text_normalization"
+};
+var SpeechifySpeechModel = class {
+	modelId;
+	config;
+	specificationVersion = "v4";
+	constructor(modelId, config) {
+		this.modelId = modelId;
+		this.config = config;
+	}
+	get provider() {
+		return this.config.provider;
+	}
+	async doGenerate(options) {
+		const timestamp = /* @__PURE__ */ new Date();
+		const { body, warnings } = this.getArgs(options);
+		const url = `${this.config.baseURL}/v1/audio/speech`;
+		const headers = this.buildHeaders(options.headers);
+		const fetchFn = this.config.fetch ?? globalThis.fetch;
+		let response;
+		try {
+			response = await fetchFn(url, {
+				method: "POST",
+				headers,
+				body: JSON.stringify(body),
+				signal: options.abortSignal
+			});
+		} catch (error) {
+			if (isAbortError(error)) throw error;
+			throw new APICallError({
+				message: `Cannot connect to the Speechify API: ${errorMessage(error)}`,
+				url,
+				requestBodyValues: body,
+				cause: error,
+				isRetryable: true
+			});
+		}
+		const responseHeaders = Object.fromEntries(response.headers.entries());
+		const responseBody = await response.text();
+		if (!response.ok) throw apiCallError({
+			url,
+			body,
+			response,
+			responseHeaders,
+			responseBody
+		});
+		let data;
+		try {
+			data = JSON.parse(responseBody);
+		} catch (error) {
+			throw new InvalidResponseDataError({
+				data: responseBody.slice(0, 500),
+				message: `The Speechify API returned a body that is not JSON: ${errorMessage(error)}`
+			});
+		}
+		if (typeof data?.audio_data !== "string" || data.audio_data.length === 0) throw new InvalidResponseDataError({
+			data: {
+				...data,
+				audio_data: void 0
+			},
+			message: "The Speechify API response has no audio_data."
+		});
+		const metadata = {
+			audioFormat: data.audio_format,
+			billableCharactersCount: data.billable_characters_count ?? null,
+			speechMarks: data.speech_marks ?? null
+		};
+		if (data.output_format != null) metadata.outputFormat = data.output_format;
+		const requestId = response.headers.get("speechify-request-id");
+		if (requestId != null) metadata.requestId = requestId;
+		return {
+			audio: data.audio_data,
+			warnings,
+			...data.billable_characters_count != null && { usage: { billable_characters_count: data.billable_characters_count } },
+			request: { body },
+			response: {
+				timestamp,
+				modelId: this.modelId,
+				headers: responseHeaders
+			},
+			providerMetadata: { speechify: metadata }
+		};
+	}
+	getArgs({ text, voice, outputFormat, instructions, speed, language, providerOptions }) {
+		const warnings = [];
+		let input = text;
+		if (speed != null) {
+			if (!Number.isFinite(speed) || speed <= 0) warnings.push({
+				type: "unsupported",
+				feature: "speed",
+				details: `speed must be a positive number; ${speed} was ignored.`
+			});
+			else {
+				const bounded = Math.min(Math.max(speed, MIN_SPEED), 100);
+				if (bounded !== speed) warnings.push({
+					type: "unsupported",
+					feature: "speed",
+					details: `Speechify supports speed from ${MIN_SPEED} to 100; ${speed} was clamped to ${bounded}.`
+				});
+				input = withSpeechRate(text, bounded);
+			}
+		}
+		const body = {
+			input,
+			voice_id: voice ?? "harper_32",
+			model: this.modelId,
+			...resolveOutputFormat(outputFormat, warnings)
+		};
+		if (language != null && language !== "" && language.toLowerCase() !== "auto") body.language = language;
+		if (instructions != null && instructions !== "") warnings.push({
+			type: "unsupported",
+			feature: "instructions",
+			details: "Speechify has no free-text instructions field. Shape delivery with SSML in the text instead (breaks and prosody rate)."
+		});
+		const apiOptions = parseProviderOptions(providerOptions?.speechify, warnings);
+		if (apiOptions != null) body.options = apiOptions;
+		return {
+			body,
+			warnings
+		};
+	}
+	buildHeaders(callHeaders) {
+		const headers = new Headers({
+			Authorization: `Bearer ${loadApiKey(this.config.apiKey)}`,
+			"Content-Type": "application/json",
+			...this.config.defaultHeaders
+		});
+		for (const source of [this.config.headers, callHeaders]) for (const [name, value] of Object.entries(source ?? {})) if (value != null) headers.set(name, value);
+		return headers;
+	}
+};
+function resolveOutputFormat(requested, warnings) {
+	if (requested == null || requested.trim() === "") return { audio_format: "mp3" };
+	const format = requested.trim().toLowerCase();
+	if (format === "mulaw" || format === "ulaw") return { output_format: "ulaw_8000" };
+	if (SPEECHIFY_AUDIO_FORMATS.includes(format)) return { audio_format: format };
+	if (SPEECHIFY_OUTPUT_FORMATS.includes(format)) return { output_format: format };
+	warnings.push({
+		type: "unsupported",
+		feature: "outputFormat",
+		details: `Speechify does not support "${requested}"; returned mp3 instead. Supported: ${[...SPEECHIFY_AUDIO_FORMATS, ...SPEECHIFY_OUTPUT_FORMATS].join(", ")}.`
+	});
+	return { audio_format: "mp3" };
+}
+function parseProviderOptions(raw, warnings) {
+	if (raw == null) return void 0;
+	if (typeof raw !== "object" || Array.isArray(raw)) throw new InvalidArgumentError({
+		argument: "providerOptions.speechify",
+		message: "providerOptions.speechify must be an object."
+	});
+	const options = {};
+	for (const [key, value] of Object.entries(raw)) {
+		if (value === void 0) continue;
+		if (!Object.hasOwn(PROVIDER_OPTION_KEYS, key)) {
+			warnings.push({
+				type: "unsupported",
+				feature: `providerOptions.speechify.${key}`,
+				details: `Unknown option, not sent. Supported: ${Object.keys(PROVIDER_OPTION_KEYS).join(", ")}.`
+			});
+			continue;
+		}
+		if (typeof value !== "boolean") throw new InvalidArgumentError({
+			argument: `providerOptions.speechify.${key}`,
+			message: `providerOptions.speechify.${key} must be a boolean.`
+		});
+		options[PROVIDER_OPTION_KEYS[key]] = value;
+	}
+	return Object.keys(options).length > 0 ? options : void 0;
+}
+function loadApiKey(apiKey) {
+	if (apiKey != null && apiKey !== "") return apiKey;
+	const fromEnv = typeof process !== "undefined" ? process.env?.SPEECHIFY_API_KEY : void 0;
+	if (fromEnv != null && fromEnv !== "") return fromEnv;
+	throw new LoadAPIKeyError({ message: "Speechify API key is missing. Pass it as the apiKey setting of createSpeechify() or set the SPEECHIFY_API_KEY environment variable." });
+}
+function apiCallError({ url, body, response, responseHeaders, responseBody }) {
+	let data;
+	try {
+		data = JSON.parse(responseBody);
+	} catch {
+		data = void 0;
+	}
+	const code = data?.error?.code;
+	const detail = data?.error?.message ?? (responseBody.slice(0, 200) || response.statusText);
+	const requestId = data?.request_id ?? response.headers.get("speechify-request-id");
+	return new APICallError({
+		message: `Speechify API error ${response.status}${code ? ` ${code}` : ""}: ${detail}` + (requestId ? ` (request id ${requestId})` : ""),
+		url,
+		requestBodyValues: body,
+		statusCode: response.status,
+		responseHeaders,
+		responseBody,
+		data
+	});
+}
+function isAbortError(error) {
+	return error instanceof Error && (error.name === "AbortError" || error.name === "TimeoutError");
+}
+function errorMessage(error) {
+	return error instanceof Error ? error.message : String(error);
+}
+//#endregion
+//#region src/version.ts
+/** This package's version, injected from package.json at build time. */
+const VERSION = "0.1.0";
+//#endregion
+//#region src/speechify-provider.ts
+/**
+* The dated Speechify API version every request pins via `Speechify-Version`,
+* so behaviour never depends on the workspace's default version.
+*/
+const SPEECHIFY_API_VERSION = "2026-09-30";
+/** Identifies this integration's traffic to Speechify (`Speechify-Caller`). */
+const SPEECHIFY_CALLER = "vercel-ai-sdk";
+const DEFAULT_BASE_URL = "https://api.speechify.ai";
+/** Creates a Speechify provider instance. */
+function createSpeechify(settings = {}) {
+	const baseURL = (settings.baseURL ?? DEFAULT_BASE_URL).replace(/\/+$/, "");
+	const createSpeechModel = (modelId) => new SpeechifySpeechModel(modelId, {
+		provider: "speechify.speech",
+		baseURL,
+		apiKey: settings.apiKey,
+		defaultHeaders: {
+			"Speechify-Caller": SPEECHIFY_CALLER,
+			"Speechify-Caller-Version": VERSION,
+			"Speechify-Version": SPEECHIFY_API_VERSION
+		},
+		headers: settings.headers,
+		fetch: settings.fetch
+	});
+	const noSuchModel = (modelType) => (modelId) => {
+		throw new NoSuchModelError({
+			modelId,
+			modelType,
+			message: `Speechify provides speech models only; use speechify.speech("${modelId}") with generateSpeech().`
+		});
+	};
+	return {
+		specificationVersion: "v4",
+		speech: createSpeechModel,
+		speechModel: createSpeechModel,
+		languageModel: noSuchModel("languageModel"),
+		embeddingModel: noSuchModel("embeddingModel"),
+		imageModel: noSuchModel("imageModel")
+	};
+}
+/** Default provider instance. Reads `SPEECHIFY_API_KEY` from the environment. */
+const speechify = createSpeechify();
+//#endregion
+export { SPEECHIFY_API_VERSION, SPEECHIFY_CALLER, VERSION, createSpeechify, speechify };

package/package.json

@@ -1,6 +1,80 @@
 {
   "name": "@speechify/ai-sdk-provider",
-  "version": "0.0.0-stage",
-  "stub": true,
-  "description": "Temporary package placeholder for staged publishing"
-}
+  "version": "0.1.0",
+  "description": "SpeechifyAI text to speech for the Vercel AI SDK: generateSpeech() with Simba 3 models, speech marks included.",
+  "license": "MIT",
+  "author": "Speechify <developers@speechify.ai> (https://speechify.ai)",
+  "homepage": "https://docs.speechify.ai/build/guides/integrations/vercel-ai-sdk",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/Speechify-AI/ai-sdk-provider.git"
+  },
+  "bugs": {
+    "url": "https://github.com/Speechify-AI/ai-sdk-provider/issues"
+  },
+  "keywords": [
+    "ai",
+    "ai-sdk",
+    "vercel",
+    "speechify",
+    "text-to-speech",
+    "tts",
+    "speech",
+    "generateSpeech"
+  ],
+  "type": "module",
+  "sideEffects": false,
+  "main": "./dist/index.cjs",
+  "module": "./dist/index.js",
+  "types": "./dist/index.d.cts",
+  "exports": {
+    ".": {
+      "import": {
+        "types": "./dist/index.d.ts",
+        "default": "./dist/index.js"
+      },
+      "require": {
+        "types": "./dist/index.d.cts",
+        "default": "./dist/index.cjs"
+      }
+    },
+    "./package.json": "./package.json"
+  },
+  "files": [
+    "dist"
+  ],
+  "engines": {
+    "node": ">=22"
+  },
+  "scripts": {
+    "build": "tsdown",
+    "typecheck": "tsc --noEmit",
+    "test": "vitest run --maxWorkers=2 --dir src",
+    "test:live": "vitest run --maxWorkers=2 --dir test",
+    "check:dist": "node scripts/check-dist.mjs",
+    "prepublishOnly": "npm run typecheck && npm test && npm run build && npm run check:dist"
+  },
+  "peerDependencies": {
+    "@ai-sdk/provider": "^4.0.0",
+    "ai": "^7.0.0"
+  },
+  "peerDependenciesMeta": {
+    "ai": {
+      "optional": true
+    }
+  },
+  "devDependencies": {
+    "@ai-sdk/provider": "4.0.21",
+    "@arethetypeswrong/core": "0.18.5",
+    "@types/node": "22.20.4",
+    "ai": "7.0.126",
+    "publint": "0.3.24",
+    "tsdown": "0.23.0",
+    "typescript": "5.9.3",
+    "vitest": "5.0.3"
+  },
+  "publishConfig": {
+    "access": "public",
+    "provenance": true
+  }
+}