@r16t/multimodal-mcp 1.2.3 → 1.3.0

package/README.md

@@ -1,12 +1,14 @@
 # multimodal-mcp
 
-Multi-provider media generation MCP server. Generate images, videos, and audio from text prompts using OpenAI, xAI, and Gemini through a single unified interface.
+Multi-provider media generation MCP server. Generate images, videos, audio, and transcriptions from text prompts using OpenAI, xAI, Gemini, ElevenLabs, and BFL (FLUX) through a single unified interface.
 
 ## Features
 
-- 🎨 **Image Generation** — Generate images via OpenAI (gpt-image-1), xAI (grok-imagine-image), or Gemini (imagen-4)
+- 🎨 **Image Generation** — Generate images via OpenAI (gpt-image-1), xAI (grok-imagine-image), Gemini (imagen-4), or BFL (FLUX Pro 1.1)
+- ✏️ **Image Editing** — Edit images via OpenAI, xAI, Gemini, or BFL (FLUX Kontext)
 - 🎬 **Video Generation** — Generate videos via OpenAI (sora-2), xAI (grok-imagine-video), or Gemini (veo-3.1)
-- 🔊 **Audio Generation** — Text-to-speech via OpenAI (tts-1) or Gemini (gemini-2.5-flash-preview-tts)
+- 🔊 **Audio Generation** — Text-to-speech via OpenAI (tts-1), Gemini, or ElevenLabs (Flash v2.5). Sound effects via ElevenLabs
+- 🎙️ **Audio Transcription** — Speech-to-text via OpenAI (Whisper) or ElevenLabs (Scribe)
 - 🔄 **Auto-Discovery** — Automatically detects configured providers from environment variables
 - 🎯 **Provider Selection** — Auto-selects or explicitly choose a provider per request
 - 📁 **File Output** — Saves all generated media to disk with descriptive filenames
@@ -24,6 +26,12 @@ claude mcp add multimodal-mcp -e OPENAI_API_KEY=sk-... -- npx @r16t/multimodal-m
 
 # Or using Gemini
 # claude mcp add multimodal-mcp -e GEMINI_API_KEY=AIza... -- npx @r16t/multimodal-mcp@latest
+
+# Or using ElevenLabs (audio + transcription)
+# claude mcp add multimodal-mcp -e ELEVENLABS_API_KEY=xi-... -- npx @r16t/multimodal-mcp@latest
+
+# Or using BFL/FLUX (images)
+# claude mcp add multimodal-mcp -e BFL_API_KEY=... -- npx @r16t/multimodal-mcp@latest
 ```
 
 Using a different editor? See [setup instructions](#editor-setup) for Claude Desktop, Cursor, VS Code, Windsurf, and Cline.
@@ -32,10 +40,12 @@ Using a different editor? See [setup instructions](#editor-setup) for Claude Des
 
 | Variable | Required | Description |
 |----------|----------|-------------|
-| `OPENAI_API_KEY` | At least one provider key | OpenAI API key — enables image, video, and audio generation via gpt-image-1, sora-2, and tts-1 |
+| `OPENAI_API_KEY` | At least one provider key | OpenAI API key — enables image, video, audio generation, and transcription via gpt-image-1, sora-2, tts-1, and whisper-1 |
 | `XAI_API_KEY` | At least one provider key | xAI API key — enables image and video generation via grok-imagine-image and grok-imagine-video |
 | `GEMINI_API_KEY` | At least one provider key | Gemini API key — enables image, video, and audio generation via imagen-4, veo-3.1, and gemini-2.5-flash-preview-tts |
 | `GOOGLE_API_KEY` | — | Alias for `GEMINI_API_KEY`; either name is accepted |
+| `ELEVENLABS_API_KEY` | At least one provider key | ElevenLabs API key — enables audio generation (TTS, sound effects) and transcription via Flash v2.5 and Scribe v1 |
+| `BFL_API_KEY` | At least one provider key | BFL API key — enables image generation and editing via FLUX Pro 1.1 and FLUX Kontext |
 | `MEDIA_OUTPUT_DIR` | No | Directory for saved media files. Defaults to the current working directory |
 
 ## Available Tools
@@ -47,7 +57,7 @@ Generate an image from a text prompt.
 | Parameter | Type | Required | Description |
 |-----------|------|----------|-------------|
 | `prompt` | string | Yes | Text description of the image to generate |
-| `provider` | string | No | Provider to use: `openai`, `xai`, `google`. Auto-selects if omitted |
+| `provider` | string | No | Provider to use: `openai`, `xai`, `google`, `bfl`. Auto-selects if omitted |
 | `aspectRatio` | string | No | Aspect ratio: `1:1`, `16:9`, `9:16`, `4:3`, `3:4` |
 | `quality` | string | No | Quality level: `low`, `standard`, `high` |
 | `outputDirectory` | string | No | Directory to save the generated file. Absolute or relative path. Defaults to `MEDIA_OUTPUT_DIR` or cwd |
@@ -69,16 +79,27 @@ Generate a video from a text prompt. Video generation is asynchronous and may ta
 
 ### `generate_audio`
 
-Generate audio (text-to-speech) from text. Audio generation is synchronous.
+Generate audio from text. Supports text-to-speech and sound effects. Audio generation is synchronous.
 
 | Parameter | Type | Required | Description |
 |-----------|------|----------|-------------|
-| `text` | string | Yes | Text to convert to speech |
-| `provider` | string | No | Provider to use: `openai`, `google`. Auto-selects if omitted |
-| `voice` | string | No | Voice name (provider-specific). OpenAI: `alloy`, `ash`, `coral`, `echo`, `fable`, `nova`, `onyx`, `sage`, `shimmer`. Google: `Kore`, `Charon`, `Fenrir`, `Aoede`, `Puck`, etc. |
+| `text` | string | Yes | Text to convert to speech, or a description of the sound effect to generate |
+| `provider` | string | No | Provider to use: `openai`, `google`, `elevenlabs`. Auto-selects if omitted |
+| `voice` | string | No | Voice name (provider-specific). OpenAI: `alloy`, `ash`, `coral`, `echo`, `fable`, `nova`, `onyx`, `sage`, `shimmer`. Google: `Kore`, `Charon`, `Fenrir`, `Aoede`, `Puck`, etc. ElevenLabs: voice ID |
 | `speed` | number | No | Speech speed multiplier (OpenAI only): `0.25` to `4.0` |
 | `format` | string | No | Output format (OpenAI only): `mp3`, `opus`, `aac`, `flac`, `wav`, `pcm` |
 | `outputDirectory` | string | No | Directory to save the generated file. Absolute or relative path. Defaults to `MEDIA_OUTPUT_DIR` or cwd |
+| `providerOptions` | object | No | Provider-specific parameters passed through directly. ElevenLabs: set `mode: "sound-effect"` for sound effects, `model` for TTS model selection |
+
+### `transcribe_audio`
+
+Transcribe audio to text (speech-to-text).
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `audioPath` | string | Yes | Absolute path to the audio file to transcribe |
+| `provider` | string | No | Provider to use: `openai`, `elevenlabs`. Auto-selects if omitted |
+| `language` | string | No | Language code (e.g., `en`, `fr`, `es`) to hint the transcription language |
 | `providerOptions` | object | No | Provider-specific parameters passed through directly |
 
 ### `list_providers`
@@ -87,11 +108,13 @@ List all configured media generation providers and their capabilities. Takes no
 
 ## Provider Capabilities
 
-| Provider | Image | Video | Audio | Image Model | Video Model | Audio Model |
-|----------|:-----:|:-----:|:-----:|-------------|-------------|-------------|
-| OpenAI | ✅ | ✅ | ✅ | gpt-image-1 | sora-2 | tts-1 |
-| xAI | ✅ | ✅ | — | grok-imagine-image | grok-imagine-video | — |
-| Gemini | ✅ | ✅ | ✅ | imagen-4 | veo-3.1 | gemini-2.5-flash-preview-tts |
+| Provider | Image | Image Editing | Video | Audio | Transcription | Key Models |
+|----------|:-----:|:------------:|:-----:|:-----:|:------------:|------------|
+| OpenAI | ✅ | ✅ | ✅ | ✅ | ✅ | gpt-image-1, sora-2, tts-1, whisper-1 |
+| xAI | ✅ | ✅ | ✅ | — | — | grok-imagine-image, grok-imagine-video |
+| Gemini | ✅ | ✅ | ✅ | ✅ | — | imagen-4, veo-3.1, gemini-2.5-flash-preview-tts |
+| ElevenLabs | — | — | — | ✅ | ✅ | eleven_flash_v2_5, scribe_v1 |
+| BFL | ✅ | ✅ | — | — | — | flux-pro-1.1, flux-kontext-pro |
 
 ### Image Aspect Ratios
 
@@ -100,6 +123,7 @@ List all configured media generation providers and their capabilities. Takes no
 | OpenAI | ✅ | ✅ | ✅ | ✅ | ✅ |
 | xAI | ✅ | ✅ | ✅ | ✅ | ✅ |
 | Gemini | ✅ | ✅ | ✅ | ✅ | ✅ |
+| BFL | ✅ | ✅ | ✅ | ✅ | ✅ |
 
 ### Video Aspect Ratios & Resolutions
 
@@ -115,6 +139,7 @@ List all configured media generation providers and their capabilities. Takes no
 |----------|:---:|:----:|:---:|:----:|:---:|:---:|
 | OpenAI | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
 | Gemini | — | — | — | — | ✅ | — |
+| ElevenLabs | ✅ | ✅ | — | — | — | ✅ |
 
 ## Troubleshooting
 
@@ -124,11 +149,11 @@ List all configured media generation providers and their capabilities. Takes no
 [config] No provider API keys detected
 ```
 
-Set at least one of `OPENAI_API_KEY`, `XAI_API_KEY`, or `GEMINI_API_KEY` in the MCP server's `env` block.
+Set at least one of `OPENAI_API_KEY`, `XAI_API_KEY`, `GEMINI_API_KEY`, `ELEVENLABS_API_KEY`, or `BFL_API_KEY` in the MCP server's `env` block.
 
 ### Provider not available for requested media type
 
-All three providers support image and video generation. Audio generation (text-to-speech) is supported by OpenAI and Gemini. xAI does not currently offer a standalone TTS API. If you specify a `provider` that isn't configured (no API key) or doesn't support the requested media type, you'll receive an error. Omit the `provider` parameter to auto-select from configured providers.
+Each provider supports different media types (see [Provider Capabilities](#provider-capabilities)). If you specify a `provider` that isn't configured (no API key) or doesn't support the requested media type, you'll receive an error. Omit the `provider` parameter to auto-select from configured providers.
 
 ### Video generation timeout
 
@@ -154,7 +179,7 @@ npm run dev        # Watch mode for TypeScript compilation
 
 ## Editor Setup
 
-Replace `OPENAI_API_KEY` with your provider of choice (`XAI_API_KEY`, `GEMINI_API_KEY`). You can set multiple keys to enable multiple providers.
+Replace `OPENAI_API_KEY` with your provider of choice (`XAI_API_KEY`, `GEMINI_API_KEY`, `ELEVENLABS_API_KEY`, `BFL_API_KEY`). You can set multiple keys to enable multiple providers.
 
 ### Claude Desktop
 

package/build/config.d.ts

@@ -3,6 +3,8 @@ declare const configSchema: z.ZodObject<{
     openaiApiKey: z.ZodOptional<z.ZodString>;
     xaiApiKey: z.ZodOptional<z.ZodString>;
     googleApiKey: z.ZodOptional<z.ZodString>;
+    elevenlabsApiKey: z.ZodOptional<z.ZodString>;
+    bflApiKey: z.ZodOptional<z.ZodString>;
     outputDirectory: z.ZodString;
 }, z.core.$strip>;
 export type Config = z.infer<typeof configSchema>;

package/build/config.js

@@ -3,6 +3,8 @@ const configSchema = z.object({
     openaiApiKey: z.string().optional(),
     xaiApiKey: z.string().optional(),
     googleApiKey: z.string().optional(),
+    elevenlabsApiKey: z.string().optional(),
+    bflApiKey: z.string().optional(),
     outputDirectory: z.string(),
 });
 function resolveGeminiKey() {
@@ -13,6 +15,8 @@ export function loadConfig() {
         openaiApiKey: process.env.OPENAI_API_KEY || undefined,
         xaiApiKey: process.env.XAI_API_KEY || undefined,
         googleApiKey: resolveGeminiKey(),
+        elevenlabsApiKey: process.env.ELEVENLABS_API_KEY || undefined,
+        bflApiKey: process.env.BFL_API_KEY || undefined,
         outputDirectory: process.env.MEDIA_OUTPUT_DIR || process.cwd(),
     });
     const detected = [];
@@ -22,6 +26,10 @@ export function loadConfig() {
         detected.push("xAI");
     if (config.googleApiKey)
         detected.push("Gemini");
+    if (config.elevenlabsApiKey)
+        detected.push("ElevenLabs");
+    if (config.bflApiKey)
+        detected.push("BFL");
     if (detected.length > 0) {
         console.error(`[config] Detected providers: ${detected.join(", ")}`);
     }

package/build/errors.js

@@ -3,6 +3,7 @@ const API_KEY_PATTERNS = [
     /xai-[a-zA-Z0-9_-]{10,}/g,
     /AIzaSy[a-zA-Z0-9_-]{10,}/g,
     /key=[a-zA-Z0-9_-]{20,}/g,
+    /xi-[a-zA-Z0-9_-]{10,}/g,
 ];
 export function sanitizeError(error) {
     let message;

package/build/providers/bfl.d.ts

@@ -0,0 +1,15 @@
+import type { MediaProvider, ProviderCapabilities, ImageParams, EditImageParams, VideoParams, AudioParams, GeneratedMedia } from "./types.js";
+export declare class BFLProvider implements MediaProvider {
+    readonly name = "bfl";
+    readonly capabilities: ProviderCapabilities;
+    private apiKey;
+    constructor(apiKey: string);
+    generateImage(params: ImageParams): Promise<GeneratedMedia>;
+    editImage(params: EditImageParams): Promise<GeneratedMedia>;
+    generateVideo(_params: VideoParams): Promise<GeneratedMedia>;
+    generateAudio(_params: AudioParams): Promise<GeneratedMedia>;
+    private submitTask;
+    private pollTask;
+    private downloadResult;
+    private mapAspectRatio;
+}

package/build/providers/bfl.js

@@ -0,0 +1,87 @@
+import { pollForCompletion } from "./polling.js";
+const BFL_BASE_URL = "https://api.bfl.ml/v1";
+const IMAGE_MODEL = "flux-pro-1.1";
+const EDIT_MODEL = "flux-kontext-pro";
+const ASPECT_RATIO_MAP = {
+    "1:1": { width: 1024, height: 1024 },
+    "16:9": { width: 1344, height: 768 },
+    "9:16": { width: 768, height: 1344 },
+    "4:3": { width: 1152, height: 896 },
+    "3:4": { width: 896, height: 1152 },
+};
+export class BFLProvider {
+    name = "bfl";
+    capabilities = {
+        supportsImageGeneration: true,
+        supportsImageEditing: true,
+        supportsVideoGeneration: false,
+        supportsAudioGeneration: false,
+        supportsTranscription: false,
+        supportedImageAspectRatios: ["1:1", "16:9", "9:16", "4:3", "3:4"],
+        supportedVideoAspectRatios: [],
+        supportedVideoResolutions: [],
+        supportedAudioFormats: [],
+        maxVideoDurationSeconds: 0,
+    };
+    apiKey;
+    constructor(apiKey) {
+        this.apiKey = apiKey;
+    }
+    async generateImage(params) {
+        const { model, ...options } = params.providerOptions ?? {};
+        const modelName = model ?? IMAGE_MODEL;
+        const { width, height } = this.mapAspectRatio(params.aspectRatio);
+        const task = await this.submitTask(modelName, { prompt: params.prompt, width, height, ...options });
+        const result = await this.pollTask(task.id);
+        return this.downloadResult(result.result.sample, modelName);
+    }
+    async editImage(params) {
+        const { model, ...options } = params.providerOptions ?? {};
+        const modelName = model ?? EDIT_MODEL;
+        const input_image = params.imageData.toString("base64");
+        const task = await this.submitTask(modelName, { prompt: params.prompt, input_image, ...options });
+        const result = await this.pollTask(task.id);
+        return this.downloadResult(result.result.sample, modelName);
+    }
+    async generateVideo(_params) {
+        throw new Error("BFL does not support video generation");
+    }
+    async generateAudio(_params) {
+        throw new Error("BFL does not support audio generation");
+    }
+    async submitTask(model, body) {
+        const response = await fetch(`${BFL_BASE_URL}/${model}`, {
+            method: "POST",
+            headers: { "Content-Type": "application/json", "X-Key": this.apiKey },
+            body: JSON.stringify(body),
+        });
+        if (!response.ok) {
+            throw new Error(`BFL task submission failed: ${response.status}`);
+        }
+        return response.json();
+    }
+    async pollTask(taskId) {
+        return pollForCompletion(async () => {
+            const response = await fetch(`${BFL_BASE_URL}/get_result?id=${taskId}`, {
+                headers: { "X-Key": this.apiKey },
+            });
+            return response.json();
+        }, (result) => result.status === "Ready", { timeoutMs: 300_000, intervalMs: 3_000 });
+    }
+    async downloadResult(url, model) {
+        const response = await fetch(url);
+        if (!response.ok) {
+            throw new Error(`BFL image download failed: ${response.status}`);
+        }
+        const mimeType = response.headers.get("content-type") ?? "image/png";
+        const data = Buffer.from(await response.arrayBuffer());
+        return { data, mimeType, metadata: { model, provider: "bfl" } };
+    }
+    mapAspectRatio(ratio) {
+        const dimensions = ASPECT_RATIO_MAP[ratio];
+        if (!dimensions) {
+            throw new Error(`BFL does not support aspect ratio: ${ratio}`);
+        }
+        return dimensions;
+    }
+}

package/build/providers/elevenlabs.d.ts

@@ -0,0 +1,14 @@
+import type { MediaProvider, ProviderCapabilities, ImageParams, EditImageParams, VideoParams, AudioParams, GeneratedMedia, TranscribeParams, TranscribedText } from "./types.js";
+export declare class ElevenLabsProvider implements MediaProvider {
+    readonly name = "elevenlabs";
+    readonly capabilities: ProviderCapabilities;
+    private apiKey;
+    constructor(apiKey: string);
+    generateImage(_params: ImageParams): Promise<GeneratedMedia>;
+    editImage(_params: EditImageParams): Promise<GeneratedMedia>;
+    generateVideo(_params: VideoParams): Promise<GeneratedMedia>;
+    generateAudio(params: AudioParams): Promise<GeneratedMedia>;
+    transcribeAudio(params: TranscribeParams): Promise<TranscribedText>;
+    private generateSpeech;
+    private generateSoundEffect;
+}

package/build/providers/elevenlabs.js

@@ -0,0 +1,96 @@
+const BASE_URL = "https://api.elevenlabs.io/v1";
+const DEFAULT_VOICE_ID = "JBFqnCBsd6RMkjVDRZzb";
+const DEFAULT_TTS_MODEL = "eleven_flash_v2_5";
+const TRANSCRIPTION_MODEL = "scribe_v1";
+export class ElevenLabsProvider {
+    name = "elevenlabs";
+    capabilities = {
+        supportsImageGeneration: false,
+        supportsImageEditing: false,
+        supportsVideoGeneration: false,
+        supportsAudioGeneration: true,
+        supportsTranscription: true,
+        supportedImageAspectRatios: [],
+        supportedVideoAspectRatios: [],
+        supportedVideoResolutions: [],
+        supportedAudioFormats: ["mp3", "pcm", "ulaw", "opus"],
+        maxVideoDurationSeconds: 0,
+    };
+    apiKey;
+    constructor(apiKey) {
+        this.apiKey = apiKey;
+    }
+    async generateImage(_params) {
+        throw new Error("ElevenLabs does not support image generation");
+    }
+    async editImage(_params) {
+        throw new Error("ElevenLabs does not support image editing");
+    }
+    async generateVideo(_params) {
+        throw new Error("ElevenLabs does not support video generation");
+    }
+    async generateAudio(params) {
+        const mode = params.providerOptions?.mode;
+        if (mode === "sound-effect") {
+            return this.generateSoundEffect(params);
+        }
+        return this.generateSpeech(params);
+    }
+    async transcribeAudio(params) {
+        const formData = new FormData();
+        const blob = new Blob([new Uint8Array(params.audioData)], { type: params.audioMimeType });
+        formData.append("file", blob, "audio");
+        formData.append("model_id", TRANSCRIPTION_MODEL);
+        if (params.language) {
+            formData.append("language_code", params.language);
+        }
+        const response = await fetch(`${BASE_URL}/speech-to-text`, {
+            method: "POST",
+            headers: { "xi-api-key": this.apiKey },
+            body: formData,
+        });
+        if (!response.ok) {
+            throw new Error(`ElevenLabs transcription failed: ${response.status}`);
+        }
+        const result = (await response.json());
+        return {
+            text: result.text,
+            metadata: { model: TRANSCRIPTION_MODEL, provider: "elevenlabs" },
+        };
+    }
+    async generateSpeech(params) {
+        const voiceId = params.voice ?? DEFAULT_VOICE_ID;
+        const options = params.providerOptions ?? {};
+        const modelId = options.model ?? DEFAULT_TTS_MODEL;
+        const filtered = Object.fromEntries(Object.entries(options).filter(([k]) => k !== "mode" && k !== "model"));
+        const response = await fetch(`${BASE_URL}/text-to-speech/${voiceId}`, {
+            method: "POST",
+            headers: { "Content-Type": "application/json", "xi-api-key": this.apiKey },
+            body: JSON.stringify({ text: params.text, model_id: modelId, ...filtered }),
+        });
+        if (!response.ok) {
+            throw new Error(`ElevenLabs TTS failed: ${response.status}`);
+        }
+        return {
+            data: Buffer.from(await response.arrayBuffer()),
+            mimeType: "audio/mpeg",
+            metadata: { model: modelId, provider: "elevenlabs", voice: voiceId },
+        };
+    }
+    async generateSoundEffect(params) {
+        const filtered = Object.fromEntries(Object.entries(params.providerOptions ?? {}).filter(([k]) => k !== "mode"));
+        const response = await fetch(`${BASE_URL}/text-to-sound-effects`, {
+            method: "POST",
+            headers: { "Content-Type": "application/json", "xi-api-key": this.apiKey },
+            body: JSON.stringify({ text: params.text, ...filtered }),
+        });
+        if (!response.ok) {
+            throw new Error(`ElevenLabs sound effect generation failed: ${response.status}`);
+        }
+        return {
+            data: Buffer.from(await response.arrayBuffer()),
+            mimeType: "audio/mpeg",
+            metadata: { provider: "elevenlabs" },
+        };
+    }
+}

package/build/providers/google.js

@@ -7,6 +7,7 @@ export class GoogleProvider {
         supportsImageEditing: true,
         supportsVideoGeneration: true,
         supportsAudioGeneration: true,
+        supportsTranscription: false,
         supportedImageAspectRatios: ["1:1", "16:9", "9:16", "4:3", "3:4"],
         supportedVideoAspectRatios: ["16:9", "9:16"],
         supportedVideoResolutions: ["720p", "1080p"],

package/build/providers/openai.d.ts

@@ -1,4 +1,4 @@
-import type { MediaProvider, ProviderCapabilities, ImageParams, EditImageParams, VideoParams, AudioParams, GeneratedMedia } from "./types.js";
+import type { MediaProvider, ProviderCapabilities, ImageParams, EditImageParams, VideoParams, AudioParams, GeneratedMedia, TranscribeParams, TranscribedText } from "./types.js";
 export declare class OpenAIProvider implements MediaProvider {
     readonly name = "openai";
     readonly capabilities: ProviderCapabilities;
@@ -8,6 +8,7 @@ export declare class OpenAIProvider implements MediaProvider {
     editImage(params: EditImageParams): Promise<GeneratedMedia>;
     generateVideo(params: VideoParams): Promise<GeneratedMedia>;
     generateAudio(params: AudioParams): Promise<GeneratedMedia>;
+    transcribeAudio(params: TranscribeParams): Promise<TranscribedText>;
     private audioFormatToMimeType;
     private mapAspectRatioToSize;
 }

package/build/providers/openai.js

@@ -14,6 +14,7 @@ export class OpenAIProvider {
         supportsImageEditing: true,
         supportsVideoGeneration: true,
         supportsAudioGeneration: true,
+        supportsTranscription: true,
         supportedImageAspectRatios: ["1:1", "16:9", "9:16", "4:3", "3:4"],
         supportedVideoAspectRatios: ["16:9", "9:16", "1:1"],
         supportedVideoResolutions: ["480p", "720p", "1080p"],
@@ -96,6 +97,19 @@ export class OpenAIProvider {
             metadata: { model: "tts-1", provider: "openai", voice, format },
         };
     }
+    async transcribeAudio(params) {
+        const audioFile = new File([new Uint8Array(params.audioData)], "audio.wav", { type: params.audioMimeType });
+        const response = await this.client.audio.transcriptions.create({
+            model: "whisper-1",
+            file: audioFile,
+            language: params.language,
+            ...params.providerOptions,
+        });
+        return {
+            text: response.text,
+            metadata: { model: "whisper-1", provider: "openai" },
+        };
+    }
     audioFormatToMimeType(format) {
         const mimeTypes = {
             mp3: "audio/mpeg",

package/build/providers/registry.d.ts

@@ -7,5 +7,6 @@ export declare class ProviderRegistry {
     getImageEditProviders(): MediaProvider[];
     getVideoProviders(): MediaProvider[];
     getAudioProviders(): MediaProvider[];
+    getTranscriptionProviders(): MediaProvider[];
     listCapabilities(): ProviderInfo[];
 }

package/build/providers/registry.js

@@ -22,6 +22,9 @@ export class ProviderRegistry {
     getAudioProviders() {
         return [...this.providers.values()].filter((p) => p.capabilities.supportsAudioGeneration);
     }
+    getTranscriptionProviders() {
+        return [...this.providers.values()].filter((p) => p.capabilities.supportsTranscription);
+    }
     listCapabilities() {
         return [...this.providers.values()].map((p) => ({
             name: p.name,

package/build/providers/types.d.ts

@@ -5,12 +5,14 @@ export interface MediaProvider {
     editImage(params: EditImageParams): Promise<GeneratedMedia>;
     generateVideo(params: VideoParams): Promise<GeneratedMedia>;
     generateAudio(params: AudioParams): Promise<GeneratedMedia>;
+    transcribeAudio?(params: TranscribeParams): Promise<TranscribedText>;
 }
 export interface ProviderCapabilities {
     supportsImageGeneration: boolean;
     supportsImageEditing: boolean;
     supportsVideoGeneration: boolean;
     supportsAudioGeneration: boolean;
+    supportsTranscription: boolean;
     supportedImageAspectRatios: string[];
     supportedVideoAspectRatios: string[];
     supportedVideoResolutions: string[];
@@ -50,6 +52,16 @@ export interface GeneratedMedia {
     mimeType: string;
     metadata: Record<string, unknown>;
 }
+export interface TranscribeParams {
+    audioData: Buffer;
+    audioMimeType: string;
+    language?: string;
+    providerOptions?: Record<string, unknown>;
+}
+export interface TranscribedText {
+    text: string;
+    metadata: Record<string, unknown>;
+}
 export interface ProviderInfo {
     name: string;
     capabilities: ProviderCapabilities;

package/build/providers/xai.js

@@ -10,6 +10,7 @@ export class XAIProvider {
         supportsImageEditing: true,
         supportsVideoGeneration: true,
         supportsAudioGeneration: false,
+        supportsTranscription: false,
         supportedImageAspectRatios: ["1:1", "16:9", "9:16", "4:3", "3:4"],
         supportedVideoAspectRatios: ["16:9", "9:16", "1:1"],
         supportedVideoResolutions: ["720p", "1080p"],

package/build/read-media-file.js

@@ -7,6 +7,14 @@ const EXTENSION_TO_MIME = {
     ".webp": "image/webp",
     ".gif": "image/gif",
     ".mp4": "video/mp4",
+    ".mp3": "audio/mpeg",
+    ".wav": "audio/wav",
+    ".flac": "audio/flac",
+    ".ogg": "audio/ogg",
+    ".m4a": "audio/mp4",
+    ".aac": "audio/aac",
+    ".opus": "audio/opus",
+    ".webm": "audio/webm",
 };
 export async function readMediaFile(filePath) {
     const absolutePath = resolve(filePath);

package/build/server.js

@@ -4,11 +4,14 @@ import { ProviderRegistry } from "./providers/registry.js";
 import { OpenAIProvider } from "./providers/openai.js";
 import { XAIProvider } from "./providers/xai.js";
 import { GoogleProvider } from "./providers/google.js";
+import { ElevenLabsProvider } from "./providers/elevenlabs.js";
+import { BFLProvider } from "./providers/bfl.js";
 import { FileManager } from "./file-manager.js";
 import { buildGenerateImageHandler } from "./tools/generate-image.js";
 import { buildEditImageHandler } from "./tools/edit-image.js";
 import { buildGenerateVideoHandler } from "./tools/generate-video.js";
 import { buildGenerateAudioHandler } from "./tools/generate-audio.js";
+import { buildTranscribeAudioHandler } from "./tools/transcribe-audio.js";
 import { buildListProvidersHandler } from "./tools/list-providers.js";
 export function createServer(config) {
     const registry = new ProviderRegistry();
@@ -25,25 +28,34 @@ export function createServer(config) {
         registry.register(new GoogleProvider(config.googleApiKey));
         console.error("[server] Registered Google provider");
     }
+    if (config.elevenlabsApiKey) {
+        registry.register(new ElevenLabsProvider(config.elevenlabsApiKey));
+        console.error("[server] Registered ElevenLabs provider");
+    }
+    if (config.bflApiKey) {
+        registry.register(new BFLProvider(config.bflApiKey));
+        console.error("[server] Registered BFL provider");
+    }
     const generateImageHandler = buildGenerateImageHandler(registry, fileManager);
     const editImageHandler = buildEditImageHandler(registry, fileManager);
     const generateVideoHandler = buildGenerateVideoHandler(registry, fileManager);
     const generateAudioHandler = buildGenerateAudioHandler(registry, fileManager);
+    const transcribeAudioHandler = buildTranscribeAudioHandler(registry);
     const listProvidersHandler = buildListProvidersHandler(registry);
     const providerNames = registry.listCapabilities().map((p) => p.name).join(", ") || "none configured";
     const server = new McpServer({ name: "multimodal-mcp", version: "1.0.0" });
-    server.tool("generate_image", `Generate an image from a text prompt using AI. Available providers: ${providerNames}`, {
+    server.tool("generate_image", `Generate an image from a text prompt using AI. Providers: openai (DALL-E), xai (Aurora), google (Imagen), bfl (FLUX). Available: ${providerNames}`, {
         prompt: z.string().describe("Text description of the image to generate"),
-        provider: z.string().optional().describe("Provider to use: openai, xai, google. Auto-selects if omitted."),
+        provider: z.string().optional().describe("Provider to use: openai, xai, google, bfl. Auto-selects if omitted."),
         aspectRatio: z.string().optional().describe("Aspect ratio: 1:1, 16:9, 9:16, 4:3, 3:4"),
         quality: z.string().optional().describe("Quality level: low, standard, high"),
         outputDirectory: z.string().optional().describe("Directory to save the generated file. Supports absolute or relative paths (resolved from cwd). Defaults to MEDIA_OUTPUT_DIR env var or cwd."),
         providerOptions: z.record(z.string(), z.unknown()).optional().describe("Provider-specific parameters passed through directly"),
     }, async (params) => generateImageHandler(params));
-    server.tool("edit_image", `Edit an existing image using AI. Provide the path to an image and a text prompt describing the desired edits. Available providers: ${providerNames}`, {
+    server.tool("edit_image", `Edit an existing image using AI. Provide the path to an image and a text prompt describing the desired edits. Providers: openai, xai, google, bfl (FLUX Kontext). Available: ${providerNames}`, {
         imagePath: z.string().describe("Absolute path to the source image file to edit"),
         prompt: z.string().describe("Text description of the edits to apply to the image"),
-        provider: z.string().optional().describe("Provider to use: openai, xai, google. Auto-selects if omitted."),
+        provider: z.string().optional().describe("Provider to use: openai, xai, google, bfl. Auto-selects if omitted."),
         outputDirectory: z.string().optional().describe("Directory to save the edited file. Supports absolute or relative paths (resolved from cwd). Defaults to MEDIA_OUTPUT_DIR env var or cwd."),
         providerOptions: z.record(z.string(), z.unknown()).optional().describe("Provider-specific parameters passed through directly"),
     }, async (params) => editImageHandler(params));
@@ -57,15 +69,21 @@ export function createServer(config) {
         outputDirectory: z.string().optional().describe("Directory to save the generated file. Supports absolute or relative paths (resolved from cwd). Defaults to MEDIA_OUTPUT_DIR env var or cwd."),
         providerOptions: z.record(z.string(), z.unknown()).optional().describe("Provider-specific parameters passed through directly"),
     }, async (params) => generateVideoHandler(params));
-    server.tool("generate_audio", `Generate audio (text-to-speech) from text using AI. Available providers: ${providerNames}`, {
-        text: z.string().describe("Text to convert to speech"),
-        provider: z.string().optional().describe("Provider to use: openai, google. Auto-selects if omitted."),
-        voice: z.string().optional().describe("Voice name (provider-specific). OpenAI: alloy, ash, coral, echo, fable, nova, onyx, sage, shimmer. Google: Kore, Charon, Fenrir, Aoede, Puck, etc."),
+    server.tool("generate_audio", `Generate audio from text using AI. Supports text-to-speech and sound effects. Providers: openai, google, elevenlabs. ElevenLabs: use providerOptions.mode = "sound-effect" for sound effects. Available: ${providerNames}`, {
+        text: z.string().describe("Text to convert to speech, or a description of the sound effect to generate"),
+        provider: z.string().optional().describe("Provider to use: openai, google, elevenlabs. Auto-selects if omitted."),
+        voice: z.string().optional().describe("Voice name (provider-specific). OpenAI: alloy, ash, coral, echo, fable, nova, onyx, sage, shimmer. Google: Kore, Charon, Fenrir, Aoede, Puck, etc. ElevenLabs: voice ID."),
         speed: z.number().optional().describe("Speech speed multiplier (OpenAI only): 0.25 to 4.0"),
         format: z.string().optional().describe("Output format (OpenAI only): mp3, opus, aac, flac, wav, pcm"),
         outputDirectory: z.string().optional().describe("Directory to save the generated file. Supports absolute or relative paths (resolved from cwd). Defaults to MEDIA_OUTPUT_DIR env var or cwd."),
         providerOptions: z.record(z.string(), z.unknown()).optional().describe("Provider-specific parameters passed through directly"),
     }, async (params) => generateAudioHandler(params));
+    server.tool("transcribe_audio", `Transcribe audio to text using AI (speech-to-text). Providers: openai (Whisper), elevenlabs (Scribe). Available: ${providerNames}`, {
+        audioPath: z.string().describe("Absolute path to the audio file to transcribe"),
+        provider: z.string().optional().describe("Provider to use: openai, elevenlabs. Auto-selects if omitted."),
+        language: z.string().optional().describe("Language code (e.g., 'en', 'fr', 'es') to hint the transcription language"),
+        providerOptions: z.record(z.string(), z.unknown()).optional().describe("Provider-specific parameters passed through directly"),
+    }, async (params) => transcribeAudioHandler(params));
     server.tool("list_providers", "List all configured media generation providers and their capabilities", async () => listProvidersHandler());
     return server;
 }

package/build/tools/list-providers.js

@@ -5,7 +5,7 @@ export function buildListProvidersHandler(registry) {
             return {
                 content: [{
                         type: "text",
-                        text: "No providers configured. Set one or more API keys: OPENAI_API_KEY, XAI_API_KEY, GEMINI_API_KEY",
+                        text: "No providers configured. Set one or more API keys: OPENAI_API_KEY, XAI_API_KEY, GEMINI_API_KEY, ELEVENLABS_API_KEY, BFL_API_KEY",
                     }],
             };
         }
@@ -19,6 +19,8 @@ export function buildListProvidersHandler(registry) {
                 caps.push("video");
             if (p.capabilities.supportsAudioGeneration)
                 caps.push("audio");
+            if (p.capabilities.supportsTranscription)
+                caps.push("transcription");
             return `- ${p.name}: ${caps.join(", ")}`;
         });
         return {

package/build/tools/transcribe-audio.d.ts

@@ -0,0 +1,19 @@
+import type { ProviderRegistry } from "../providers/registry.js";
+export declare function buildTranscribeAudioHandler(registry: ProviderRegistry): (params: {
+    audioPath: string;
+    provider?: string;
+    language?: string;
+    providerOptions?: Record<string, unknown>;
+}) => Promise<{
+    isError: true;
+    content: {
+        type: "text";
+        text: string;
+    }[];
+} | {
+    content: {
+        type: "text";
+        text: string;
+    }[];
+    isError?: undefined;
+}>;

package/build/tools/transcribe-audio.js

@@ -0,0 +1,48 @@
+import { readMediaFile } from "../read-media-file.js";
+import { sanitizeError } from "../errors.js";
+export function buildTranscribeAudioHandler(registry) {
+    return async (params) => {
+        const provider = params.provider
+            ? registry.getProvider(params.provider)
+            : registry.getTranscriptionProviders()[0];
+        if (!provider) {
+            const available = registry.getTranscriptionProviders().map((p) => p.name).join(", ") || "none";
+            const text = params.provider
+                ? `Provider "${params.provider}" is not configured or does not support transcription. Available transcription providers: ${available}`
+                : `No transcription provider available. Available transcription providers: ${available}`;
+            return {
+                isError: true,
+                content: [{ type: "text", text }],
+            };
+        }
+        if (!provider.capabilities.supportsTranscription || !provider.transcribeAudio) {
+            const available = registry.getTranscriptionProviders().map((p) => p.name).join(", ") || "none";
+            return {
+                isError: true,
+                content: [{
+                        type: "text",
+                        text: `Provider "${provider.name}" does not support transcription. Available transcription providers: ${available}`,
+                    }],
+            };
+        }
+        try {
+            const { data, mimeType } = await readMediaFile(params.audioPath);
+            const result = await provider.transcribeAudio({
+                audioData: data,
+                audioMimeType: mimeType,
+                language: params.language,
+                providerOptions: params.providerOptions,
+            });
+            return {
+                content: [{ type: "text", text: result.text }],
+            };
+        }
+        catch (error) {
+            const message = sanitizeError(error);
+            return {
+                isError: true,
+                content: [{ type: "text", text: `Transcription failed: ${message}` }],
+            };
+        }
+    };
+}

package/package.json

@@ -1,6 +1,7 @@
 {
   "name": "@r16t/multimodal-mcp",
-  "version": "1.2.3",
+  "version": "1.3.0",
+  "mcpName": "io.github.rsmdt/multimodal",
   "description": "Multi-provider media generation MCP server",
   "type": "module",
   "main": "build/index.js",