0.7.6

.serena/.gitignore

@@ -0,0 +1 @@
+/cache

.serena/project.yml

@@ -0,0 +1,67 @@
+# language of the project (csharp, python, rust, java, typescript, go, cpp, or ruby)
+#  * For C, use cpp
+#  * For JavaScript, use typescript
+# Special requirements:
+#  * csharp: Requires the presence of a .sln file in the project folder.
+language: typescript
+
+# whether to use the project's gitignore file to ignore files
+# Added on 2025-04-07
+ignore_all_files_in_gitignore: true
+# list of additional paths to ignore
+# same syntax as gitignore, so you can use * and **
+# Was previously called `ignored_dirs`, please update your config if you are using that.
+# Added (renamed) on 2025-04-07
+ignored_paths: []
+
+# whether the project is in read-only mode
+# If set to true, all editing tools will be disabled and attempts to use them will result in an error
+# Added on 2025-04-18
+read_only: false
+
+# list of tool names to exclude. We recommend not excluding any tools, see the readme for more details.
+# Below is the complete list of tools for convenience.
+# To make sure you have the latest list of tools, and to view their descriptions, 
+# execute `uv run scripts/print_tool_overview.py`.
+#
+#  * `activate_project`: Activates a project by name.
+#  * `check_onboarding_performed`: Checks whether project onboarding was already performed.
+#  * `create_text_file`: Creates/overwrites a file in the project directory.
+#  * `delete_lines`: Deletes a range of lines within a file.
+#  * `delete_memory`: Deletes a memory from Serena's project-specific memory store.
+#  * `execute_shell_command`: Executes a shell command.
+#  * `find_referencing_code_snippets`: Finds code snippets in which the symbol at the given location is referenced.
+#  * `find_referencing_symbols`: Finds symbols that reference the symbol at the given location (optionally filtered by type).
+#  * `find_symbol`: Performs a global (or local) search for symbols with/containing a given name/substring (optionally filtered by type).
+#  * `get_current_config`: Prints the current configuration of the agent, including the active and available projects, tools, contexts, and modes.
+#  * `get_symbols_overview`: Gets an overview of the top-level symbols defined in a given file.
+#  * `initial_instructions`: Gets the initial instructions for the current project.
+#     Should only be used in settings where the system prompt cannot be set,
+#     e.g. in clients you have no control over, like Claude Desktop.
+#  * `insert_after_symbol`: Inserts content after the end of the definition of a given symbol.
+#  * `insert_at_line`: Inserts content at a given line in a file.
+#  * `insert_before_symbol`: Inserts content before the beginning of the definition of a given symbol.
+#  * `list_dir`: Lists files and directories in the given directory (optionally with recursion).
+#  * `list_memories`: Lists memories in Serena's project-specific memory store.
+#  * `onboarding`: Performs onboarding (identifying the project structure and essential tasks, e.g. for testing or building).
+#  * `prepare_for_new_conversation`: Provides instructions for preparing for a new conversation (in order to continue with the necessary context).
+#  * `read_file`: Reads a file within the project directory.
+#  * `read_memory`: Reads the memory with the given name from Serena's project-specific memory store.
+#  * `remove_project`: Removes a project from the Serena configuration.
+#  * `replace_lines`: Replaces a range of lines within a file with new content.
+#  * `replace_symbol_body`: Replaces the full definition of a symbol.
+#  * `restart_language_server`: Restarts the language server, may be necessary when edits not through Serena happen.
+#  * `search_for_pattern`: Performs a search for a pattern in the project.
+#  * `summarize_changes`: Provides instructions for summarizing the changes made to the codebase.
+#  * `switch_modes`: Activates modes by providing a list of their names
+#  * `think_about_collected_information`: Thinking tool for pondering the completeness of collected information.
+#  * `think_about_task_adherence`: Thinking tool for determining whether the agent is still on track with the current task.
+#  * `think_about_whether_you_are_done`: Thinking tool for determining whether the task is truly completed.
+#  * `write_memory`: Writes a named memory (for future reference) to Serena's project-specific memory store.
+excluded_tools: []
+
+# initial prompt for the project. It will always be given to the LLM upon activating the project
+# (contrary to the memories, which are loaded on demand).
+initial_prompt: ""
+
+project_name: "smartai"

changelog.md

@@ -1,5 +1,47 @@
 # Changelog
 
+## 2025-10-09 - 0.7.6 - fix(provider.elevenlabs)
+Provide default ElevenLabs TTS voice fallback and add local tool/project configs
+
+- ElevenLabsProvider: fallback to Samara voice id ('19STyYD15bswVz51nqLf') when no voiceId or defaultVoiceId is provided — avoids throwing an error on TTS calls.
+- ElevenLabsProvider: continue to use 'eleven_v3' as the default model for TTS.
+- Add .claude/settings.local.json with expanded allowed permissions for local tooling and web search.
+- Add .serena/project.yml and .serena/.gitignore to include Serena project configuration and ignore cache.
+
+## 2025-10-08 - 0.7.5 - fix(provider.elevenlabs)
+Update ElevenLabs default TTS model to eleven_v3 and add local Claude permissions file
+
+- Changed default ElevenLabs modelId from 'eleven_multilingual_v2' to 'eleven_v3' in ts/provider.elevenlabs.ts to use the newer/default TTS model.
+- Added .claude/settings.local.json with a permissions allow-list for local Claude tooling and CI tasks.
+
+## 2025-10-03 - 0.7.4 - fix(provider.anthropic)
+Use image/png for embedded PDF images in Anthropic provider and add local Claude settings for development permissions
+
+- AnthropicProvider: change media_type from 'image/jpeg' to 'image/png' when embedding images extracted from PDFs to ensure correct format in Anthropic requests.
+- Add .claude/settings.local.json with development/testing permissions for local Claude usage (shell commands, webfetch, websearch, test/run tasks).
+
+## 2025-10-03 - 0.7.3 - fix(tests)
+Add extensive provider/feature tests and local Claude CI permissions
+
+- Add many focused test files covering providers and features: OpenAI, Anthropic, Perplexity, Groq, Ollama, Exo, XAI (chat, audio, vision, document, research, image generation, stubs, interfaces, basic)
+- Introduce .claude/settings.local.json to declare allowed permissions for local Claude/CI actions
+- Replace older aggregated test files with modular per-feature tests (removed legacy combined tests and split into smaller suites)
+- No changes to library runtime code — this change adds tests and CI/local agent configuration only
+
+## 2025-10-03 - 0.7.2 - fix(anthropic)
+Update Anthropic provider branding to Claude Sonnet 4.5 and add local Claude permissions
+
+- Docs: Replace 'Claude 3 Opus' with 'Claude Sonnet 4.5' in README provider capabilities matrix.
+- Config: Add .claude/settings.local.json to define local Claude permissions for tests and development commands.
+
+## 2025-10-03 - 0.7.1 - fix(docs)
+Add README image generation docs and .claude local settings
+
+- Add .claude/settings.local.json with permission allow-list for local assistant tooling and web search
+- Update README provider capabilities table to include an Images column and reference gpt-image-1
+- Add Image Generation & Editing section with examples, options, and gpt-image-1 advantages
+- Mark image generation support as implemented in the roadmap and remove duplicate entry
+
 ## 2025-10-03 - 0.7.0 - feat(providers)
 Add research API and image generation/editing support; extend providers and tests
 

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@push.rocks/smartai",
-  "version": "0.7.0",
+  "version": "0.7.6",
   "private": false,
   "description": "SmartAi is a versatile TypeScript library designed to facilitate integration and interaction with various AI models, offering functionalities for chat, audio generation, document processing, and vision tasks.",
   "main": "dist_ts/index.js",
@@ -15,22 +15,23 @@
     "buildDocs": "(tsdoc)"
   },
   "devDependencies": {
-    "@git.zone/tsbuild": "^2.6.4",
+    "@git.zone/tsbuild": "^2.6.8",
     "@git.zone/tsbundle": "^2.5.1",
     "@git.zone/tsrun": "^1.3.3",
-    "@git.zone/tstest": "^2.3.2",
-    "@push.rocks/qenv": "^6.1.0",
+    "@git.zone/tstest": "^2.3.8",
+    "@push.rocks/qenv": "^6.1.3",
     "@push.rocks/tapbundle": "^6.0.3",
-    "@types/node": "^22.15.17"
+    "@types/node": "^22.15.17",
+    "typescript": "^5.9.3"
   },
   "dependencies": {
-    "@anthropic-ai/sdk": "^0.59.0",
+    "@anthropic-ai/sdk": "^0.65.0",
     "@push.rocks/smartarray": "^1.1.0",
-    "@push.rocks/smartfile": "^11.2.5",
+    "@push.rocks/smartfile": "^11.2.7",
     "@push.rocks/smartpath": "^6.0.0",
     "@push.rocks/smartpdf": "^4.1.1",
     "@push.rocks/smartpromise": "^4.2.3",
-    "@push.rocks/smartrequest": "^4.2.1",
+    "@push.rocks/smartrequest": "^4.3.1",
     "@push.rocks/webstream": "^1.0.10",
     "openai": "^5.12.2"
   },

readme.md

@@ -5,7 +5,7 @@
 [![TypeScript](https://img.shields.io/badge/TypeScript-5.x-blue.svg)](https://www.typescriptlang.org/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
-SmartAI unifies the world's leading AI providers - OpenAI, Anthropic, Perplexity, Ollama, Groq, XAI, and Exo - under a single, elegant TypeScript interface. Build AI applications at lightning speed without vendor lock-in. 
+SmartAI unifies the world's leading AI providers - OpenAI, Anthropic, Perplexity, Ollama, Groq, XAI, Exo, and ElevenLabs - under a single, elegant TypeScript interface. Build AI applications at lightning speed without vendor lock-in. 
 
 ## 🎯 Why SmartAI?
 
@@ -28,7 +28,11 @@ import { SmartAi } from '@push.rocks/smartai';
 // Initialize with your favorite providers
 const ai = new SmartAi({
   openaiToken: 'sk-...',
-  anthropicToken: 'sk-ant-...'
+  anthropicToken: 'sk-ant-...',
+  elevenlabsToken: 'sk-...',
+  elevenlabs: {
+    defaultVoiceId: '19STyYD15bswVz51nqLf' // Optional: Samara voice
+  }
 });
 
 await ai.start();
@@ -45,15 +49,16 @@ const response = await ai.openaiProvider.chat({
 
 Choose the right provider for your use case:
 
-| Provider | Chat | Streaming | TTS | Vision | Documents | Research | Highlights |
-|----------|:----:|:---------:|:---:|:------:|:---------:|:--------:|------------|
-| **OpenAI** | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | • GPT-4, DALL-E 3<br>• Industry standard<br>• Deep research API |
-| **Anthropic** | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | • Claude 3 Opus<br>• Superior reasoning<br>• Web search API |
-| **Ollama** | ✅ | ✅ | ❌ | ✅ | ✅ | ❌ | • 100% local<br>• Privacy-first<br>• No API costs |
-| **XAI** | ✅ | ✅ | ❌ | ❌ | ✅ | ❌ | • Grok models<br>• Real-time data<br>• Uncensored |
-| **Perplexity** | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | • Web-aware<br>• Research-focused<br>• Sonar Pro models |
-| **Groq** | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | • 10x faster<br>• LPU inference<br>• Low latency |
-| **Exo** | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | • Distributed<br>• P2P compute<br>• Decentralized |
+| Provider | Chat | Streaming | TTS | Vision | Documents | Research | Images | Highlights |
+|----------|:----:|:---------:|:---:|:------:|:---------:|:--------:|:------:|------------|
+| **OpenAI** | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | • gpt-image-1<br>• DALL-E 3<br>• Deep research API |
+| **Anthropic** | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | • Claude Sonnet 4.5<br>• Superior reasoning<br>• Web search API |
+| **ElevenLabs** | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | • Premium TTS<br>• 70+ languages<br>• Natural voices |
+| **Ollama** | ✅ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | • 100% local<br>• Privacy-first<br>• No API costs |
+| **XAI** | ✅ | ✅ | ❌ | ❌ | ✅ | ❌ | ❌ | • Grok models<br>• Real-time data<br>• Uncensored |
+| **Perplexity** | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ❌ | • Web-aware<br>• Research-focused<br>• Sonar Pro models |
+| **Groq** | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | • 10x faster<br>• LPU inference<br>• Low latency |
+| **Exo** | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | • Distributed<br>• P2P compute<br>• Decentralized |
 
 ## 🎮 Core Features
 
@@ -105,13 +110,27 @@ while (true) {
 
 ### 🎙️ Text-to-Speech
 
-Generate natural voices with OpenAI:
+Generate natural voices with OpenAI or ElevenLabs:
 
 ```typescript
+// OpenAI TTS
 const audioStream = await ai.openaiProvider.audio({
   message: 'Welcome to the future of AI development!'
 });
 
+// ElevenLabs TTS - Premium quality, natural voices (uses v3 by default)
+const elevenLabsAudio = await ai.elevenlabsProvider.audio({
+  message: 'Experience the most lifelike text to speech technology.',
+  voiceId: '19STyYD15bswVz51nqLf', // Optional: Samara voice
+  modelId: 'eleven_v3', // Optional: defaults to eleven_v3 (70+ languages, most expressive)
+  voiceSettings: { // Optional: fine-tune voice characteristics
+    stability: 0.5,        // 0-1: Speech consistency
+    similarity_boost: 0.8, // 0-1: Voice similarity to original
+    style: 0.0,            // 0-1: Expressiveness (higher = more expressive)
+    use_speaker_boost: true // Enhanced clarity
+  }
+});
+
 // Stream directly to speakers
 audioStream.pipe(speakerOutput);
 
@@ -216,6 +235,87 @@ const perplexityResearch = await ai.perplexityProvider.research({
 - **Anthropic**: Web Search API with domain filtering
 - **Perplexity**: Sonar and Sonar Pro models with built-in citations
 
+### 🎨 Image Generation & Editing
+
+Generate and edit images with OpenAI's cutting-edge models:
+
+```typescript
+// Basic image generation with gpt-image-1
+const image = await ai.openaiProvider.imageGenerate({
+  prompt: 'A futuristic robot assistant in a modern office, digital art',
+  model: 'gpt-image-1',
+  quality: 'high',
+  size: '1024x1024'
+});
+
+// Save the generated image
+const imageBuffer = Buffer.from(image.images[0].b64_json!, 'base64');
+fs.writeFileSync('robot.png', imageBuffer);
+
+// Advanced: Transparent background with custom format
+const logo = await ai.openaiProvider.imageGenerate({
+  prompt: 'Minimalist mountain peak logo, geometric design',
+  model: 'gpt-image-1',
+  quality: 'high',
+  size: '1024x1024',
+  background: 'transparent',
+  outputFormat: 'png'
+});
+
+// WebP with compression for web use
+const webImage = await ai.openaiProvider.imageGenerate({
+  prompt: 'Product showcase: sleek smartphone on marble surface',
+  model: 'gpt-image-1',
+  quality: 'high',
+  size: '1536x1024',
+  outputFormat: 'webp',
+  outputCompression: 85
+});
+
+// Superior text rendering (gpt-image-1's strength)
+const signage = await ai.openaiProvider.imageGenerate({
+  prompt: 'Vintage cafe sign saying "COFFEE & CODE" in hand-lettered typography',
+  model: 'gpt-image-1',
+  quality: 'high',
+  size: '1024x1024'
+});
+
+// Generate multiple variations at once
+const variations = await ai.openaiProvider.imageGenerate({
+  prompt: 'Abstract geometric pattern, colorful minimalist art',
+  model: 'gpt-image-1',
+  n: 3,
+  quality: 'medium',
+  size: '1024x1024'
+});
+
+// Edit an existing image
+const editedImage = await ai.openaiProvider.imageEdit({
+  image: originalImageBuffer,
+  prompt: 'Add sunglasses and change the background to a beach sunset',
+  model: 'gpt-image-1',
+  quality: 'high'
+});
+```
+
+**Image Generation Options:**
+- `model`: 'gpt-image-1' | 'dall-e-3' | 'dall-e-2'
+- `quality`: 'low' | 'medium' | 'high' | 'auto'
+- `size`: Multiple aspect ratios up to 4096×4096
+- `background`: 'transparent' | 'opaque' | 'auto'
+- `outputFormat`: 'png' | 'jpeg' | 'webp'
+- `outputCompression`: 0-100 for webp/jpeg
+- `moderation`: 'low' | 'auto'
+- `n`: Number of images (1-10)
+
+**gpt-image-1 Advantages:**
+- Superior text rendering in images
+- Up to 4096×4096 resolution
+- Transparent background support
+- Advanced output formats (WebP with compression)
+- Better prompt understanding
+- Streaming support for progressive rendering
+
 ### 🔄 Persistent Conversations
 
 Maintain context across interactions:
@@ -467,6 +567,7 @@ npm install @push.rocks/smartai
 export OPENAI_API_KEY=sk-...
 export ANTHROPIC_API_KEY=sk-ant-...
 export PERPLEXITY_API_KEY=pplx-...
+export ELEVENLABS_API_KEY=sk-...
 # ... etc
 ```
 
@@ -493,6 +594,7 @@ export PERPLEXITY_API_KEY=pplx-...
 | **Complex Reasoning** | Anthropic | Superior logical thinking, safer outputs |
 | **Research & Facts** | Perplexity | Web-aware, provides citations |
 | **Deep Research** | OpenAI | Deep Research API with comprehensive analysis |
+| **Premium TTS** | ElevenLabs | Most natural voices, 70+ languages, superior quality (v3) |
 | **Speed Critical** | Groq | 10x faster inference, sub-second responses |
 | **Privacy Critical** | Ollama | 100% local, no data leaves your servers |
 | **Real-time Data** | XAI | Access to current information |
@@ -501,8 +603,8 @@ export PERPLEXITY_API_KEY=pplx-...
 ## 📈 Roadmap
 
 - [x] Research & Web Search API
+- [x] Image generation support (gpt-image-1, DALL-E 3, DALL-E 2)
 - [ ] Streaming function calls
-- [ ] Image generation support
 - [ ] Voice input processing
 - [ ] Fine-tuning integration
 - [ ] Embedding support

test/test.anthropic.ts

@@ -1,216 +0,0 @@
-import { expect, tap } from '@push.rocks/tapbundle';
-import * as qenv from '@push.rocks/qenv';
-import * as smartrequest from '@push.rocks/smartrequest';
-import * as smartfile from '@push.rocks/smartfile';
-
-const testQenv = new qenv.Qenv('./', './.nogit/');
-
-import * as smartai from '../ts/index.js';
-
-let anthropicProvider: smartai.AnthropicProvider;
-
-tap.test('Anthropic: should create and start Anthropic provider', async () => {
-  anthropicProvider = new smartai.AnthropicProvider({
-    anthropicToken: await testQenv.getEnvVarOnDemand('ANTHROPIC_TOKEN'),
-  });
-  await anthropicProvider.start();
-  expect(anthropicProvider).toBeInstanceOf(smartai.AnthropicProvider);
-});
-
-tap.test('Anthropic: should create chat response', async () => {
-  const userMessage = 'What is the capital of France? Answer in one word.';
-  const response = await anthropicProvider.chat({
-    systemMessage: 'You are a helpful assistant. Be concise.',
-    userMessage: userMessage,
-    messageHistory: [],
-  });
-  console.log(`Anthropic Chat - User: ${userMessage}`);
-  console.log(`Anthropic Chat - Response: ${response.message}`);
-
-  expect(response.role).toEqual('assistant');
-  expect(response.message).toBeTruthy();
-  expect(response.message.toLowerCase()).toInclude('paris');
-});
-
-tap.test('Anthropic: should handle message history', async () => {
-  const messageHistory: smartai.ChatMessage[] = [
-    { role: 'user', content: 'My name is Claude Test' },
-    { role: 'assistant', content: 'Nice to meet you, Claude Test!' }
-  ];
-
-  const response = await anthropicProvider.chat({
-    systemMessage: 'You are a helpful assistant with good memory.',
-    userMessage: 'What is my name?',
-    messageHistory: messageHistory,
-  });
-
-  console.log(`Anthropic Memory Test - Response: ${response.message}`);
-  expect(response.message.toLowerCase()).toInclude('claude test');
-});
-
-tap.test('Anthropic: should analyze coffee image with latte art', async () => {
-  // Test 1: Coffee image from Unsplash by Dani
-  const imagePath = './test/testimages/coffee-dani/coffee.jpg';
-  console.log(`Loading coffee image from: ${imagePath}`);
-
-  const imageBuffer = await smartfile.fs.toBuffer(imagePath);
-  console.log(`Image loaded, size: ${imageBuffer.length} bytes`);
-
-  const result = await anthropicProvider.vision({
-    image: imageBuffer,
-    prompt: 'Describe this coffee image. What do you see in terms of the cup, foam pattern, and overall composition?'
-  });
-
-  console.log(`Anthropic Vision (Coffee) - Result: ${result}`);
-  expect(result).toBeTruthy();
-  expect(typeof result).toEqual('string');
-  expect(result.toLowerCase()).toInclude('coffee');
-  // The image has a heart pattern in the latte art
-  const mentionsLatte = result.toLowerCase().includes('heart') ||
-                        result.toLowerCase().includes('latte') ||
-                        result.toLowerCase().includes('foam');
-  expect(mentionsLatte).toBeTrue();
-});
-
-tap.test('Anthropic: should analyze laptop/workspace image', async () => {
-  // Test 2: Laptop image from Unsplash by Nicolas Bichon
-  const imagePath = './test/testimages/laptop-nicolas/laptop.jpg';
-  console.log(`Loading laptop image from: ${imagePath}`);
-
-  const imageBuffer = await smartfile.fs.toBuffer(imagePath);
-  console.log(`Image loaded, size: ${imageBuffer.length} bytes`);
-
-  const result = await anthropicProvider.vision({
-    image: imageBuffer,
-    prompt: 'Describe the technology and workspace setup in this image. What devices and equipment can you see?'
-  });
-
-  console.log(`Anthropic Vision (Laptop) - Result: ${result}`);
-  expect(result).toBeTruthy();
-  expect(typeof result).toEqual('string');
-  // Should mention laptop, computer, keyboard, or desk
-  const mentionsTech = result.toLowerCase().includes('laptop') ||
-                       result.toLowerCase().includes('computer') ||
-                       result.toLowerCase().includes('keyboard') ||
-                       result.toLowerCase().includes('desk');
-  expect(mentionsTech).toBeTrue();
-});
-
-tap.test('Anthropic: should analyze receipt/document image', async () => {
-  // Test 3: Receipt image from Unsplash by Annie Spratt
-  const imagePath = './test/testimages/receipt-annie/receipt.jpg';
-  console.log(`Loading receipt image from: ${imagePath}`);
-
-  const imageBuffer = await smartfile.fs.toBuffer(imagePath);
-  console.log(`Image loaded, size: ${imageBuffer.length} bytes`);
-
-  const result = await anthropicProvider.vision({
-    image: imageBuffer,
-    prompt: 'What type of document is this? Can you identify any text or numbers visible in the image?'
-  });
-
-  console.log(`Anthropic Vision (Receipt) - Result: ${result}`);
-  expect(result).toBeTruthy();
-  expect(typeof result).toEqual('string');
-  // Should mention receipt, document, text, or paper
-  const mentionsDocument = result.toLowerCase().includes('receipt') ||
-                          result.toLowerCase().includes('document') ||
-                          result.toLowerCase().includes('text') ||
-                          result.toLowerCase().includes('paper');
-  expect(mentionsDocument).toBeTrue();
-});
-
-tap.test('Anthropic: should document a PDF', async () => {
-  const pdfUrl = 'https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf';
-  const pdfResponse = await smartrequest.SmartRequest.create()
-    .url(pdfUrl)
-    .get();
-
-  const result = await anthropicProvider.document({
-    systemMessage: 'Classify the document. Only the following answers are allowed: "invoice", "bank account statement", "contract", "test document", "other". The answer should only contain the keyword for machine use.',
-    userMessage: 'Classify this document.',
-    messageHistory: [],
-    pdfDocuments: [Buffer.from(await pdfResponse.arrayBuffer())],
-  });
-
-  console.log(`Anthropic Document - Result:`, result);
-  expect(result).toBeTruthy();
-  expect(result.message).toBeTruthy();
-});
-
-tap.test('Anthropic: should handle complex document analysis', async () => {
-  // Test with the demo PDF if it exists
-  const pdfPath = './.nogit/demo_without_textlayer.pdf';
-  let pdfBuffer: Uint8Array;
-
-  try {
-    pdfBuffer = await smartfile.fs.toBuffer(pdfPath);
-  } catch (error) {
-    // If the file doesn't exist, use the dummy PDF
-    console.log('Demo PDF not found, using dummy PDF instead');
-    const pdfUrl = 'https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf';
-    const pdfResponse = await smartrequest.SmartRequest.create()
-      .url(pdfUrl)
-      .get();
-    pdfBuffer = Buffer.from(await pdfResponse.arrayBuffer());
-  }
-
-  const result = await anthropicProvider.document({
-    systemMessage: `
-      Analyze this document and provide a JSON response with the following structure:
-      {
-        "documentType": "string",
-        "hasText": boolean,
-        "summary": "string"
-      }
-    `,
-    userMessage: 'Analyze this document.',
-    messageHistory: [],
-    pdfDocuments: [pdfBuffer],
-  });
-
-  console.log(`Anthropic Complex Document Analysis:`, result);
-  expect(result).toBeTruthy();
-  expect(result.message).toBeTruthy();
-});
-
-tap.test('Anthropic: should handle errors gracefully', async () => {
-  // Test with invalid message (empty)
-  let errorCaught = false;
-
-  try {
-    await anthropicProvider.chat({
-      systemMessage: '',
-      userMessage: '',
-      messageHistory: [],
-    });
-  } catch (error) {
-    errorCaught = true;
-    console.log('Expected error caught:', error.message);
-  }
-
-  // Anthropic might handle empty messages, so we don't assert error
-  console.log(`Error handling test - Error caught: ${errorCaught}`);
-});
-
-tap.test('Anthropic: audio should throw not supported error', async () => {
-  let errorCaught = false;
-
-  try {
-    await anthropicProvider.audio({
-      message: 'This should fail'
-    });
-  } catch (error) {
-    errorCaught = true;
-    expect(error.message).toInclude('not yet supported');
-  }
-
-  expect(errorCaught).toBeTrue();
-});
-
-tap.test('Anthropic: should stop the provider', async () => {
-  await anthropicProvider.stop();
-  console.log('Anthropic provider stopped successfully');
-});
-
-export default tap.start();

test/test.audio.elevenlabs.ts

@@ -0,0 +1,54 @@
+import { expect, tap } from '@push.rocks/tapbundle';
+import * as qenv from '@push.rocks/qenv';
+import * as smartfile from '@push.rocks/smartfile';
+
+const testQenv = new qenv.Qenv('./', './.nogit/');
+
+import * as smartai from '../ts/index.js';
+
+let testSmartai: smartai.SmartAi;
+
+tap.test('ElevenLabs Audio: should create a smartai instance with ElevenLabs provider', async () => {
+  testSmartai = new smartai.SmartAi({
+    elevenlabsToken: await testQenv.getEnvVarOnDemand('ELEVENLABS_TOKEN'),
+    elevenlabs: {
+      defaultVoiceId: '19STyYD15bswVz51nqLf',
+    },
+  });
+  await testSmartai.start();
+});
+
+tap.test('ElevenLabs Audio: should create audio response', async () => {
+  const audioStream = await testSmartai.elevenlabsProvider.audio({
+    message: 'Welcome to SmartAI, the unified interface for the world\'s leading artificial intelligence providers. SmartAI brings together OpenAI, Anthropic, Perplexity, and ElevenLabs under a single elegant TypeScript API. Whether you need text generation, vision analysis, document processing, or premium text-to-speech capabilities, SmartAI provides a consistent and powerful interface for all your AI needs. Build intelligent applications at lightning speed without vendor lock-in.',
+  });
+  const chunks: Uint8Array[] = [];
+  for await (const chunk of audioStream) {
+    chunks.push(chunk as Uint8Array);
+  }
+  const audioBuffer = Buffer.concat(chunks);
+  await smartfile.fs.toFs(audioBuffer, './.nogit/testoutput_elevenlabs.mp3');
+  console.log(`Audio Buffer length: ${audioBuffer.length}`);
+  expect(audioBuffer.length).toBeGreaterThan(0);
+});
+
+tap.test('ElevenLabs Audio: should create audio with custom voice', async () => {
+  const audioStream = await testSmartai.elevenlabsProvider.audio({
+    message: 'Testing with a different voice.',
+    voiceId: 'JBFqnCBsd6RMkjVDRZzb',
+  });
+  const chunks: Uint8Array[] = [];
+  for await (const chunk of audioStream) {
+    chunks.push(chunk as Uint8Array);
+  }
+  const audioBuffer = Buffer.concat(chunks);
+  await smartfile.fs.toFs(audioBuffer, './.nogit/testoutput_elevenlabs_custom.mp3');
+  console.log(`Audio Buffer length (custom voice): ${audioBuffer.length}`);
+  expect(audioBuffer.length).toBeGreaterThan(0);
+});
+
+tap.test('ElevenLabs Audio: should stop the smartai instance', async () => {
+  await testSmartai.stop();
+});
+
+export default tap.start();

test/test.audio.openai.ts

@@ -0,0 +1,39 @@
+import { expect, tap } from '@push.rocks/tapbundle';
+import * as qenv from '@push.rocks/qenv';
+import * as smartfile from '@push.rocks/smartfile';
+
+const testQenv = new qenv.Qenv('./', './.nogit/');
+
+import * as smartai from '../ts/index.js';
+
+let testSmartai: smartai.SmartAi;
+
+tap.test('OpenAI Audio: should create a smartai instance with OpenAI provider', async () => {
+  testSmartai = new smartai.SmartAi({
+    openaiToken: await testQenv.getEnvVarOnDemand('OPENAI_TOKEN'),
+  });
+  await testSmartai.start();
+});
+
+tap.test('OpenAI Audio: should create audio response', async () => {
+  // Call the audio method with a sample message.
+  const audioStream = await testSmartai.openaiProvider.audio({
+    message: 'This is a test of audio generation.',
+  });
+  // Read all chunks from the stream.
+  const chunks: Uint8Array[] = [];
+  for await (const chunk of audioStream) {
+    chunks.push(chunk as Uint8Array);
+  }
+  const audioBuffer = Buffer.concat(chunks);
+  await smartfile.fs.toFs(audioBuffer, './.nogit/testoutput.mp3');
+  console.log(`Audio Buffer length: ${audioBuffer.length}`);
+  // Assert that the resulting buffer is not empty.
+  expect(audioBuffer.length).toBeGreaterThan(0);
+});
+
+tap.test('OpenAI Audio: should stop the smartai instance', async () => {
+  await testSmartai.stop();
+});
+
+export default tap.start();

test/test.audio.stubs.ts

@@ -0,0 +1,36 @@
+import { expect, tap } from '@push.rocks/tapbundle';
+import * as qenv from '@push.rocks/qenv';
+
+const testQenv = new qenv.Qenv('./', './.nogit/');
+
+import * as smartai from '../ts/index.js';
+
+let anthropicProvider: smartai.AnthropicProvider;
+
+tap.test('Audio Stubs: should create Anthropic provider', async () => {
+  anthropicProvider = new smartai.AnthropicProvider({
+    anthropicToken: await testQenv.getEnvVarOnDemand('ANTHROPIC_TOKEN'),
+  });
+  await anthropicProvider.start();
+});
+
+tap.test('Audio Stubs: Anthropic audio should throw not supported error', async () => {
+  let errorCaught = false;
+
+  try {
+    await anthropicProvider.audio({
+      message: 'This should fail'
+    });
+  } catch (error) {
+    errorCaught = true;
+    expect(error.message).toInclude('not yet supported');
+  }
+
+  expect(errorCaught).toBeTrue();
+});
+
+tap.test('Audio Stubs: should stop Anthropic provider', async () => {
+  await anthropicProvider.stop();
+});
+
+export default tap.start();

test/test.chat.anthropic.ts

@@ -0,0 +1,72 @@
+import { expect, tap } from '@push.rocks/tapbundle';
+import * as qenv from '@push.rocks/qenv';
+
+const testQenv = new qenv.Qenv('./', './.nogit/');
+
+import * as smartai from '../ts/index.js';
+
+let anthropicProvider: smartai.AnthropicProvider;
+
+tap.test('Anthropic Chat: should create and start Anthropic provider', async () => {
+  anthropicProvider = new smartai.AnthropicProvider({
+    anthropicToken: await testQenv.getEnvVarOnDemand('ANTHROPIC_TOKEN'),
+  });
+  await anthropicProvider.start();
+  expect(anthropicProvider).toBeInstanceOf(smartai.AnthropicProvider);
+});
+
+tap.test('Anthropic Chat: should create chat response', async () => {
+  const userMessage = 'What is the capital of France? Answer in one word.';
+  const response = await anthropicProvider.chat({
+    systemMessage: 'You are a helpful assistant. Be concise.',
+    userMessage: userMessage,
+    messageHistory: [],
+  });
+  console.log(`Anthropic Chat - User: ${userMessage}`);
+  console.log(`Anthropic Chat - Response: ${response.message}`);
+
+  expect(response.role).toEqual('assistant');
+  expect(response.message).toBeTruthy();
+  expect(response.message.toLowerCase()).toInclude('paris');
+});
+
+tap.test('Anthropic Chat: should handle message history', async () => {
+  const messageHistory: smartai.ChatMessage[] = [
+    { role: 'user', content: 'My name is Claude Test' },
+    { role: 'assistant', content: 'Nice to meet you, Claude Test!' }
+  ];
+
+  const response = await anthropicProvider.chat({
+    systemMessage: 'You are a helpful assistant with good memory.',
+    userMessage: 'What is my name?',
+    messageHistory: messageHistory,
+  });
+
+  console.log(`Anthropic Memory Test - Response: ${response.message}`);
+  expect(response.message.toLowerCase()).toInclude('claude test');
+});
+
+tap.test('Anthropic Chat: should handle errors gracefully', async () => {
+  // Test with invalid message (empty)
+  let errorCaught = false;
+
+  try {
+    await anthropicProvider.chat({
+      systemMessage: '',
+      userMessage: '',
+      messageHistory: [],
+    });
+  } catch (error) {
+    errorCaught = true;
+    console.log('Expected error caught:', error.message);
+  }
+
+  // Anthropic might handle empty messages, so we don't assert error
+  console.log(`Error handling test - Error caught: ${errorCaught}`);
+});
+
+tap.test('Anthropic Chat: should stop the provider', async () => {
+  await anthropicProvider.stop();
+});
+
+export default tap.start();

test/test.chat.openai.ts

@@ -0,0 +1,34 @@
+import { expect, tap } from '@push.rocks/tapbundle';
+import * as qenv from '@push.rocks/qenv';
+
+const testQenv = new qenv.Qenv('./', './.nogit/');
+
+import * as smartai from '../ts/index.js';
+
+let testSmartai: smartai.SmartAi;
+
+tap.test('OpenAI Chat: should create a smartai instance with OpenAI provider', async () => {
+  testSmartai = new smartai.SmartAi({
+    openaiToken: await testQenv.getEnvVarOnDemand('OPENAI_TOKEN'),
+  });
+  await testSmartai.start();
+});
+
+tap.test('OpenAI Chat: should create chat response', async () => {
+  const userMessage = 'How are you?';
+  const response = await testSmartai.openaiProvider.chat({
+    systemMessage: 'Hello',
+    userMessage: userMessage,
+    messageHistory: [],
+  });
+  console.log(`userMessage: ${userMessage}`);
+  console.log(response.message);
+  expect(response.role).toEqual('assistant');
+  expect(response.message).toBeTruthy();
+});
+
+tap.test('OpenAI Chat: should stop the smartai instance', async () => {
+  await testSmartai.stop();
+});
+
+export default tap.start();

test/test.document.anthropic.ts

@@ -0,0 +1,78 @@
+import { expect, tap } from '@push.rocks/tapbundle';
+import * as qenv from '@push.rocks/qenv';
+import * as smartrequest from '@push.rocks/smartrequest';
+import * as smartfile from '@push.rocks/smartfile';
+
+const testQenv = new qenv.Qenv('./', './.nogit/');
+
+import * as smartai from '../ts/index.js';
+
+let anthropicProvider: smartai.AnthropicProvider;
+
+tap.test('Anthropic Document: should create and start Anthropic provider', async () => {
+  anthropicProvider = new smartai.AnthropicProvider({
+    anthropicToken: await testQenv.getEnvVarOnDemand('ANTHROPIC_TOKEN'),
+  });
+  await anthropicProvider.start();
+  expect(anthropicProvider).toBeInstanceOf(smartai.AnthropicProvider);
+});
+
+tap.test('Anthropic Document: should document a PDF', async () => {
+  const pdfUrl = 'https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf';
+  const pdfResponse = await smartrequest.SmartRequest.create()
+    .url(pdfUrl)
+    .get();
+
+  const result = await anthropicProvider.document({
+    systemMessage: 'Classify the document. Only the following answers are allowed: "invoice", "bank account statement", "contract", "test document", "other". The answer should only contain the keyword for machine use.',
+    userMessage: 'Classify this document.',
+    messageHistory: [],
+    pdfDocuments: [Buffer.from(await pdfResponse.arrayBuffer())],
+  });
+
+  console.log(`Anthropic Document - Result:`, result);
+  expect(result).toBeTruthy();
+  expect(result.message).toBeTruthy();
+});
+
+tap.test('Anthropic Document: should handle complex document analysis', async () => {
+  // Test with the demo PDF if it exists
+  const pdfPath = './.nogit/demo_without_textlayer.pdf';
+  let pdfBuffer: Uint8Array;
+
+  try {
+    pdfBuffer = await smartfile.fs.toBuffer(pdfPath);
+  } catch (error) {
+    // If the file doesn't exist, use the dummy PDF
+    console.log('Demo PDF not found, using dummy PDF instead');
+    const pdfUrl = 'https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf';
+    const pdfResponse = await smartrequest.SmartRequest.create()
+      .url(pdfUrl)
+      .get();
+    pdfBuffer = Buffer.from(await pdfResponse.arrayBuffer());
+  }
+
+  const result = await anthropicProvider.document({
+    systemMessage: `
+      Analyze this document and provide a JSON response with the following structure:
+      {
+        "documentType": "string",
+        "hasText": boolean,
+        "summary": "string"
+      }
+    `,
+    userMessage: 'Analyze this document.',
+    messageHistory: [],
+    pdfDocuments: [pdfBuffer],
+  });
+
+  console.log(`Anthropic Complex Document Analysis:`, result);
+  expect(result).toBeTruthy();
+  expect(result.message).toBeTruthy();
+});
+
+tap.test('Anthropic Document: should stop the provider', async () => {
+  await anthropicProvider.stop();
+});
+
+export default tap.start();

test/test.document.openai.ts

@@ -9,25 +9,14 @@ import * as smartai from '../ts/index.js';
 
 let testSmartai: smartai.SmartAi;
 
-tap.test('OpenAI: should create a smartai instance with OpenAI provider', async () => {
+tap.test('OpenAI Document: should create a smartai instance with OpenAI provider', async () => {
   testSmartai = new smartai.SmartAi({
     openaiToken: await testQenv.getEnvVarOnDemand('OPENAI_TOKEN'),
   });
   await testSmartai.start();
 });
 
-tap.test('OpenAI: should create chat response', async () => {
-  const userMessage = 'How are you?';
-  const response = await testSmartai.openaiProvider.chat({
-    systemMessage: 'Hello',
-    userMessage: userMessage,
-    messageHistory: [],
-  });
-  console.log(`userMessage: ${userMessage}`);
-  console.log(response.message);
-});
-
-tap.test('OpenAI: should document a pdf', async () => {
+tap.test('OpenAI Document: should document a pdf', async () => {
   const pdfUrl = 'https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf';
   const pdfResponse = await smartrequest.SmartRequest.create()
     .url(pdfUrl)
@@ -39,9 +28,10 @@ tap.test('OpenAI: should document a pdf', async () => {
     pdfDocuments: [Buffer.from(await pdfResponse.arrayBuffer())],
   });
   console.log(result);
+  expect(result.message).toBeTruthy();
 });
 
-tap.test('OpenAI: should recognize companies in a pdf', async () => {
+tap.test('OpenAI Document: should recognize companies in a pdf', async () => {
   const pdfBuffer = await smartfile.fs.toBuffer('./.nogit/demo_without_textlayer.pdf');
   const result = await testSmartai.openaiProvider.document({
     systemMessage: `
@@ -76,27 +66,11 @@ tap.test('OpenAI: should recognize companies in a pdf', async () => {
     pdfDocuments: [pdfBuffer],
   });
   console.log(result);
+  expect(result.message).toBeTruthy();
 });
 
-tap.test('OpenAI: should create audio response', async () => {
-  // Call the audio method with a sample message.
-  const audioStream = await testSmartai.openaiProvider.audio({
-    message: 'This is a test of audio generation.',
-  });
-  // Read all chunks from the stream.
-  const chunks: Uint8Array[] = [];
-  for await (const chunk of audioStream) {
-    chunks.push(chunk as Uint8Array);
-  }
-  const audioBuffer = Buffer.concat(chunks);
-  await smartfile.fs.toFs(audioBuffer, './.nogit/testoutput.mp3');
-  console.log(`Audio Buffer length: ${audioBuffer.length}`);
-  // Assert that the resulting buffer is not empty.
-  expect(audioBuffer.length).toBeGreaterThan(0);
-});
-
-tap.test('OpenAI: should stop the smartai instance', async () => {
+tap.test('OpenAI Document: should stop the smartai instance', async () => {
   await testSmartai.stop();
 });
 
-export default tap.start();
+export default tap.start();

test/test.vision.anthropic.ts

@@ -0,0 +1,95 @@
+import { expect, tap } from '@push.rocks/tapbundle';
+import * as qenv from '@push.rocks/qenv';
+import * as smartfile from '@push.rocks/smartfile';
+
+const testQenv = new qenv.Qenv('./', './.nogit/');
+
+import * as smartai from '../ts/index.js';
+
+let anthropicProvider: smartai.AnthropicProvider;
+
+tap.test('Anthropic Vision: should create and start Anthropic provider', async () => {
+  anthropicProvider = new smartai.AnthropicProvider({
+    anthropicToken: await testQenv.getEnvVarOnDemand('ANTHROPIC_TOKEN'),
+  });
+  await anthropicProvider.start();
+  expect(anthropicProvider).toBeInstanceOf(smartai.AnthropicProvider);
+});
+
+tap.test('Anthropic Vision: should analyze coffee image with latte art', async () => {
+  // Test 1: Coffee image from Unsplash by Dani
+  const imagePath = './test/testimages/coffee-dani/coffee.jpg';
+  console.log(`Loading coffee image from: ${imagePath}`);
+
+  const imageBuffer = await smartfile.fs.toBuffer(imagePath);
+  console.log(`Image loaded, size: ${imageBuffer.length} bytes`);
+
+  const result = await anthropicProvider.vision({
+    image: imageBuffer,
+    prompt: 'Describe this coffee image. What do you see in terms of the cup, foam pattern, and overall composition?'
+  });
+
+  console.log(`Anthropic Vision (Coffee) - Result: ${result}`);
+  expect(result).toBeTruthy();
+  expect(typeof result).toEqual('string');
+  expect(result.toLowerCase()).toInclude('coffee');
+  // The image has a heart pattern in the latte art
+  const mentionsLatte = result.toLowerCase().includes('heart') ||
+                        result.toLowerCase().includes('latte') ||
+                        result.toLowerCase().includes('foam');
+  expect(mentionsLatte).toBeTrue();
+});
+
+tap.test('Anthropic Vision: should analyze laptop/workspace image', async () => {
+  // Test 2: Laptop image from Unsplash by Nicolas Bichon
+  const imagePath = './test/testimages/laptop-nicolas/laptop.jpg';
+  console.log(`Loading laptop image from: ${imagePath}`);
+
+  const imageBuffer = await smartfile.fs.toBuffer(imagePath);
+  console.log(`Image loaded, size: ${imageBuffer.length} bytes`);
+
+  const result = await anthropicProvider.vision({
+    image: imageBuffer,
+    prompt: 'Describe the technology and workspace setup in this image. What devices and equipment can you see?'
+  });
+
+  console.log(`Anthropic Vision (Laptop) - Result: ${result}`);
+  expect(result).toBeTruthy();
+  expect(typeof result).toEqual('string');
+  // Should mention laptop, computer, keyboard, or desk
+  const mentionsTech = result.toLowerCase().includes('laptop') ||
+                       result.toLowerCase().includes('computer') ||
+                       result.toLowerCase().includes('keyboard') ||
+                       result.toLowerCase().includes('desk');
+  expect(mentionsTech).toBeTrue();
+});
+
+tap.test('Anthropic Vision: should analyze receipt/document image', async () => {
+  // Test 3: Receipt image from Unsplash by Annie Spratt
+  const imagePath = './test/testimages/receipt-annie/receipt.jpg';
+  console.log(`Loading receipt image from: ${imagePath}`);
+
+  const imageBuffer = await smartfile.fs.toBuffer(imagePath);
+  console.log(`Image loaded, size: ${imageBuffer.length} bytes`);
+
+  const result = await anthropicProvider.vision({
+    image: imageBuffer,
+    prompt: 'What type of document is this? Can you identify any text or numbers visible in the image?'
+  });
+
+  console.log(`Anthropic Vision (Receipt) - Result: ${result}`);
+  expect(result).toBeTruthy();
+  expect(typeof result).toEqual('string');
+  // Should mention receipt, document, text, or paper
+  const mentionsDocument = result.toLowerCase().includes('receipt') ||
+                          result.toLowerCase().includes('document') ||
+                          result.toLowerCase().includes('text') ||
+                          result.toLowerCase().includes('paper');
+  expect(mentionsDocument).toBeTrue();
+});
+
+tap.test('Anthropic Vision: should stop the provider', async () => {
+  await anthropicProvider.stop();
+});
+
+export default tap.start();

ts/00_commitinfo_data.ts

@@ -3,6 +3,6 @@
  */
 export const commitinfo = {
   name: '@push.rocks/smartai',
-  version: '0.7.0',
+  version: '0.7.6',
   description: 'SmartAi is a versatile TypeScript library designed to facilitate integration and interaction with various AI models, offering functionalities for chat, audio generation, document processing, and vision tasks.'
 }

ts/classes.conversation.ts

@@ -96,6 +96,18 @@ export class Conversation {
     return conversation;
   }
 
+  public static async createWithElevenlabs(smartaiRefArg: SmartAi) {
+    if (!smartaiRefArg.elevenlabsProvider) {
+      throw new Error('ElevenLabs provider not available');
+    }
+    const conversation = new Conversation(smartaiRefArg, {
+      processFunction: async (input) => {
+        return '' // TODO implement proper streaming
+      }
+    });
+    return conversation;
+  }
+
   // INSTANCE
   smartaiRef: SmartAi
   private systemMessage: string;

ts/classes.smartai.ts

@@ -1,6 +1,7 @@
 import { Conversation } from './classes.conversation.js';
 import * as plugins from './plugins.js';
 import { AnthropicProvider } from './provider.anthropic.js';
+import { ElevenLabsProvider } from './provider.elevenlabs.js';
 import { OllamaProvider } from './provider.ollama.js';
 import { OpenAiProvider } from './provider.openai.js';
 import { PerplexityProvider } from './provider.perplexity.js';
@@ -15,6 +16,7 @@ export interface ISmartAiOptions {
   perplexityToken?: string;
   groqToken?: string;
   xaiToken?: string;
+  elevenlabsToken?: string;
   exo?: {
     baseUrl?: string;
     apiKey?: string;
@@ -24,9 +26,13 @@ export interface ISmartAiOptions {
     model?: string;
     visionModel?: string;
   };
+  elevenlabs?: {
+    defaultVoiceId?: string;
+    defaultModelId?: string;
+  };
 }
 
-export type TProvider = 'openai' | 'anthropic' | 'perplexity' | 'ollama' | 'exo' | 'groq' | 'xai';
+export type TProvider = 'openai' | 'anthropic' | 'perplexity' | 'ollama' | 'exo' | 'groq' | 'xai' | 'elevenlabs';
 
 export class SmartAi {
   public options: ISmartAiOptions;
@@ -38,6 +44,7 @@ export class SmartAi {
   public exoProvider: ExoProvider;
   public groqProvider: GroqProvider;
   public xaiProvider: XAIProvider;
+  public elevenlabsProvider: ElevenLabsProvider;
 
   constructor(optionsArg: ISmartAiOptions) {
     this.options = optionsArg;
@@ -74,6 +81,14 @@ export class SmartAi {
       });
       await this.xaiProvider.start();
     }
+    if (this.options.elevenlabsToken) {
+      this.elevenlabsProvider = new ElevenLabsProvider({
+        elevenlabsToken: this.options.elevenlabsToken,
+        defaultVoiceId: this.options.elevenlabs?.defaultVoiceId,
+        defaultModelId: this.options.elevenlabs?.defaultModelId,
+      });
+      await this.elevenlabsProvider.start();
+    }
     if (this.options.ollama) {
       this.ollamaProvider = new OllamaProvider({
         baseUrl: this.options.ollama.baseUrl,
@@ -107,6 +122,9 @@ export class SmartAi {
     if (this.xaiProvider) {
       await this.xaiProvider.stop();
     }
+    if (this.elevenlabsProvider) {
+      await this.elevenlabsProvider.stop();
+    }
     if (this.ollamaProvider) {
       await this.ollamaProvider.stop();
     }
@@ -134,6 +152,8 @@ export class SmartAi {
         return Conversation.createWithGroq(this);
       case 'xai':
         return Conversation.createWithXai(this);
+      case 'elevenlabs':
+        return Conversation.createWithElevenlabs(this);
       default:
         throw new Error('Provider not available');
     }

ts/index.ts

@@ -7,3 +7,4 @@ export * from './provider.groq.js';
 export * from './provider.ollama.js';
 export * from './provider.xai.js';
 export * from './provider.exo.js';
+export * from './provider.elevenlabs.js';

ts/provider.anthropic.ts

@@ -220,7 +220,7 @@ export class AnthropicProvider extends MultiModalModel {
         type: 'image',
         source: {
           type: 'base64',
-          media_type: 'image/jpeg',
+          media_type: 'image/png',
           data: Buffer.from(imageBytes).toString('base64')
         }
       });

ts/provider.elevenlabs.ts

@@ -0,0 +1,114 @@
+import * as plugins from './plugins.js';
+
+import { MultiModalModel } from './abstract.classes.multimodal.js';
+import type {
+  ChatOptions,
+  ChatResponse,
+  ResearchOptions,
+  ResearchResponse,
+  ImageGenerateOptions,
+  ImageEditOptions,
+  ImageResponse
+} from './abstract.classes.multimodal.js';
+
+export interface IElevenLabsProviderOptions {
+  elevenlabsToken: string;
+  defaultVoiceId?: string;
+  defaultModelId?: string;
+}
+
+export interface IElevenLabsVoiceSettings {
+  stability?: number;
+  similarity_boost?: number;
+  style?: number;
+  use_speaker_boost?: boolean;
+}
+
+export class ElevenLabsProvider extends MultiModalModel {
+  private options: IElevenLabsProviderOptions;
+  private baseUrl: string = 'https://api.elevenlabs.io/v1';
+
+  constructor(optionsArg: IElevenLabsProviderOptions) {
+    super();
+    this.options = optionsArg;
+  }
+
+  public async start() {
+    await super.start();
+  }
+
+  public async stop() {
+    await super.stop();
+  }
+
+  public async chat(optionsArg: ChatOptions): Promise<ChatResponse> {
+    throw new Error('ElevenLabs does not support chat functionality. This provider is specialized for text-to-speech only.');
+  }
+
+  public async chatStream(input: ReadableStream<Uint8Array>): Promise<ReadableStream<string>> {
+    throw new Error('ElevenLabs does not support chat streaming functionality. This provider is specialized for text-to-speech only.');
+  }
+
+  public async audio(optionsArg: { 
+    message: string; 
+    voiceId?: string; 
+    modelId?: string;
+    voiceSettings?: IElevenLabsVoiceSettings;
+  }): Promise<NodeJS.ReadableStream> {
+    // Use Samara voice as default fallback
+    const voiceId = optionsArg.voiceId || this.options.defaultVoiceId || '19STyYD15bswVz51nqLf';
+
+    const modelId = optionsArg.modelId || this.options.defaultModelId || 'eleven_v3';
+
+    const url = `${this.baseUrl}/text-to-speech/${voiceId}`;
+    
+    const requestBody: any = {
+      text: optionsArg.message,
+      model_id: modelId,
+    };
+
+    if (optionsArg.voiceSettings) {
+      requestBody.voice_settings = optionsArg.voiceSettings;
+    }
+
+    const response = await plugins.smartrequest.SmartRequest.create()
+      .url(url)
+      .header('xi-api-key', this.options.elevenlabsToken)
+      .json(requestBody)
+      .autoDrain(false)
+      .post();
+
+    if (!response.ok) {
+      const errorText = await response.text();
+      throw new Error(`ElevenLabs API error: ${response.status} ${response.statusText} - ${errorText}`);
+    }
+
+    const nodeStream = response.streamNode();
+    return nodeStream;
+  }
+
+  public async vision(optionsArg: { image: Buffer; prompt: string }): Promise<string> {
+    throw new Error('ElevenLabs does not support vision functionality. This provider is specialized for text-to-speech only.');
+  }
+
+  public async document(optionsArg: {
+    systemMessage: string;
+    userMessage: string;
+    pdfDocuments: Uint8Array[];
+    messageHistory: any[];
+  }): Promise<{ message: any }> {
+    throw new Error('ElevenLabs does not support document processing. This provider is specialized for text-to-speech only.');
+  }
+
+  public async research(optionsArg: ResearchOptions): Promise<ResearchResponse> {
+    throw new Error('ElevenLabs does not support research capabilities. This provider is specialized for text-to-speech only.');
+  }
+
+  public async imageGenerate(optionsArg: ImageGenerateOptions): Promise<ImageResponse> {
+    throw new Error('ElevenLabs does not support image generation. This provider is specialized for text-to-speech only.');
+  }
+
+  public async imageEdit(optionsArg: ImageEditOptions): Promise<ImageResponse> {
+    throw new Error('ElevenLabs does not support image editing. This provider is specialized for text-to-speech only.');
+  }
+}