@zhoujinandrew/fish-audio-mcp-server 0.7.0

package/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Daichi Okazaki
+
+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

@@ -0,0 +1,430 @@
+# Fish Audio MCP Server
+
+<div align="center">
+  <img src="./dcos/icon_fish-audio.webp" alt="Fish Audio Logo" width="300" height="300" />
+</div>
+
+[![npm version](https://badge.fury.io/js/@zhoujinandrew%2Ffish-audio-mcp-server.svg)](https://badge.fury.io/js/@zhoujinandrew%2Ffish-audio-mcp-server) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+
+An MCP (Model Context Protocol) server that provides seamless integration between Fish Audio's Text-to-Speech API and LLMs like Claude, enabling natural language-driven speech synthesis.
+
+## What is Fish Audio?
+
+[Fish Audio](https://fish.audio/) is a cutting-edge Text-to-Speech platform that offers:
+
+- 🌊 **State-of-the-art voice synthesis** with natural-sounding output
+- 🎯 **Voice cloning capabilities** to create custom voice models
+- 🌍 **Multilingual support** including English, Japanese, Chinese, and more
+- ⚡ **Low-latency streaming** for real-time applications
+- 🎨 **Fine-grained control** over speech prosody and emotions
+
+This MCP server brings Fish Audio's powerful capabilities directly to your LLM workflows.
+
+## Features
+
+- 🎙️ **High-Quality TTS**: Leverage Fish Audio's state-of-the-art TTS models
+- 🌊 **Streaming Support**: Real-time audio streaming for low-latency applications
+- 🎨 **Multiple Voices**: Support for custom voice models via reference IDs
+- 🎯 **Smart Voice Selection**: Select voices by ID, name, or tags
+- 📚 **Voice Library Management**: Configure and manage multiple voice references
+- 🔧 **Flexible Configuration**: Environment variable-based configuration
+- 📦 **Multiple Audio Formats**: Support for MP3, WAV, PCM, and Opus
+- 🚀 **Easy Integration**: Simple setup with any MCP-compatible client
+
+## Quick Start
+
+### Installation
+
+You can run this MCP server directly using npx:
+
+```bash
+npx @zhoujinandrew/fish-audio-mcp-server
+```
+
+Or install it globally:
+
+```bash
+npm install -g @zhoujinandrew/fish-audio-mcp-server
+```
+
+### Configuration
+
+1. Get your Fish Audio API key from [Fish Audio](https://fish.audio/)
+
+2. Set up environment variables:
+
+```bash
+export FISH_API_KEY=your_fish_audio_api_key_here
+```
+
+3. Add to your MCP settings configuration:
+
+#### Single Voice Mode (Simple)
+```json
+{
+  "mcpServers": {
+    "fish-audio": {
+      "command": "npx",
+      "args": ["-y", "@zhoujinandrew/fish-audio-mcp-server"],
+      "env": {
+        "FISH_API_KEY": "your_fish_audio_api_key_here",
+        "FISH_MODEL_ID": "speech-1.6",
+        "FISH_REFERENCE_ID": "your_voice_reference_id_here",
+        "FISH_OUTPUT_FORMAT": "mp3",
+        "FISH_STREAMING": "false",
+        "FISH_LATENCY": "balanced",
+        "FISH_MP3_BITRATE": "128",
+        "FISH_AUTO_PLAY": "false",
+        "AUDIO_OUTPUT_DIR": "~/.fish-audio-mcp/audio_output"
+      }
+    }
+  }
+}
+```
+
+#### Multiple Voice Mode (Advanced)
+```json
+{
+  "mcpServers": {
+    "fish-audio": {
+      "command": "npx",
+      "args": ["-y", "@zhoujinandrew/fish-audio-mcp-server"],
+      "env": {
+        "FISH_API_KEY": "your_fish_audio_api_key_here",
+        "FISH_MODEL_ID": "speech-1.6",
+        "FISH_REFERENCES": "[{'reference_id':'id1','name':'Alice','tags':['female','english']},{'reference_id':'id2','name':'Bob','tags':['male','japanese']},{'reference_id':'id3','name':'Carol','tags':['female','japanese','anime']}]",
+        "FISH_DEFAULT_REFERENCE": "id1",
+        "FISH_OUTPUT_FORMAT": "mp3",
+        "FISH_STREAMING": "false",
+        "FISH_LATENCY": "balanced",
+        "FISH_MP3_BITRATE": "128",
+        "FISH_AUTO_PLAY": "false",
+        "AUDIO_OUTPUT_DIR": "~/.fish-audio-mcp/audio_output"
+      }
+    }
+  }
+}
+```
+
+## Environment Variables
+
+| Variable | Description | Default | Required |
+|----------|-------------|---------|----------|
+| `FISH_API_KEY` | Your Fish Audio API key | - | Yes |
+| `FISH_MODEL_ID` | TTS model to use (s1, speech-1.5, speech-1.6) | `s1` | Optional |
+| `FISH_REFERENCE_ID` | Default voice reference ID (single reference mode) | - | Optional |
+| `FISH_REFERENCES` | Multiple voice references (see below) | - | Optional |
+| `FISH_DEFAULT_REFERENCE` | Default reference ID when using multiple references | - | Optional |
+| `FISH_OUTPUT_FORMAT` | Default audio format (mp3, wav, pcm, opus) | `mp3` | Optional |
+| `FISH_STREAMING` | Enable streaming mode (HTTP/WebSocket) | `false` | Optional |
+| `FISH_LATENCY` | Latency mode (normal, balanced) | `balanced` | Optional |
+| `FISH_MP3_BITRATE` | MP3 bitrate (64, 128, 192) | `128` | Optional |
+| `FISH_AUTO_PLAY` | Auto-play audio and enable real-time playback | `false` | Optional |
+| `AUDIO_OUTPUT_DIR` | Directory for audio file output | `~/.fish-audio-mcp/audio_output` | Optional |
+
+### Configuring Multiple Voice References
+
+You can configure multiple voice references in two ways:
+
+#### JSON Array Format (Recommended)
+Use the `FISH_REFERENCES` environment variable with a JSON array:
+
+```bash
+FISH_REFERENCES='[
+  {"reference_id":"id1","name":"Alice","tags":["female","english"]},
+  {"reference_id":"id2","name":"Bob","tags":["male","japanese"]},
+  {"reference_id":"id3","name":"Carol","tags":["female","japanese","anime"]}
+]'
+FISH_DEFAULT_REFERENCE="id1"
+```
+
+#### Individual Format (Backward Compatibility)
+Use numbered environment variables:
+
+```bash
+FISH_REFERENCE_1_ID=id1
+FISH_REFERENCE_1_NAME=Alice
+FISH_REFERENCE_1_TAGS=female,english
+
+FISH_REFERENCE_2_ID=id2
+FISH_REFERENCE_2_NAME=Bob
+FISH_REFERENCE_2_TAGS=male,japanese
+```
+
+## Usage
+
+Once configured, the Fish Audio MCP server provides two tools to LLMs.
+
+### Tool 1: `fish_audio_tts`
+
+Generates speech from text using Fish Audio's TTS API.
+
+#### Parameters
+
+- `text` (required): Text to convert to speech (max 10,000 characters)
+- `reference_id` (optional): Voice model reference ID
+- `reference_name` (optional): Select voice by name
+- `reference_tag` (optional): Select voice by tag
+- `streaming` (optional): Enable streaming mode
+- `format` (optional): Output format (mp3, wav, pcm, opus)
+- `mp3_bitrate` (optional): MP3 bitrate (64, 128, 192)
+- `normalize` (optional): Enable text normalization (default: true)
+- `latency` (optional): Latency mode (normal, balanced)
+- `output_path` (optional): Custom output file path
+- `auto_play` (optional): Automatically play the generated audio
+- `websocket_streaming` (optional): Use WebSocket streaming instead of HTTP
+- `realtime_play` (optional): Play audio in real-time during WebSocket streaming
+- `speed` (optional): Speaking rate multiplier (0.5=half speed, 1.0=normal, 2.0=double speed)
+- `volume` (optional): Volume adjustment in dB (0=no change, positive=louder, negative=quieter)
+- `temperature` (optional): Expressiveness/emotion control (0=consistent, 1=emotional, default: 0.7)
+
+**Voice Selection Priority**: reference_id > reference_name > reference_tag > default
+
+### Tool 2: `fish_audio_list_references`
+
+Lists all configured voice references.
+
+#### Parameters
+
+No parameters required.
+
+#### Returns
+
+- List of configured voice references with their IDs, names, and tags
+- Default reference ID
+
+### Examples
+
+#### Basic Text-to-Speech
+
+```
+User: "Generate speech saying 'Hello, world! Welcome to Fish Audio TTS.'"
+
+Claude: I'll generate speech for that text using Fish Audio TTS.
+
+[Uses fish_audio_tts tool with text parameter]
+
+Result: Audio file saved to ./audio_output/tts_2025-01-03T10-30-00.mp3
+```
+
+#### Using Custom Voice by ID
+
+```
+User: "Generate speech with voice model xyz123 saying 'This is a custom voice test'"
+
+Claude: I'll generate speech using the specified voice model.
+
+[Uses fish_audio_tts tool with text and reference_id parameters]
+
+Result: Audio generated with custom voice model xyz123
+```
+
+#### Using Voice by Name
+
+```
+User: "Use Alice's voice to say 'Hello from Alice'"
+
+Claude: I'll generate speech using Alice's voice.
+
+[Uses fish_audio_tts tool with reference_name: "Alice"]
+
+Result: Audio generated with Alice's voice
+```
+
+#### Using Voice by Tag
+
+```
+User: "Generate Japanese speech saying 'こんにちは' with an anime voice"
+
+Claude: I'll generate Japanese speech with an anime-style voice.
+
+[Uses fish_audio_tts tool with reference_tag: "anime"]
+
+Result: Audio generated with anime voice style
+```
+
+#### List Available Voices
+
+```
+User: "What voices are available?"
+
+Claude: I'll list all configured voice references.
+
+[Uses fish_audio_list_references tool]
+
+Result:
+- Alice (id: id1) - Tags: female, english [Default]
+- Bob (id: id2) - Tags: male, japanese
+- Carol (id: id3) - Tags: female, japanese, anime
+```
+
+#### HTTP Streaming Mode
+
+```
+User: "Generate a long speech in streaming mode about the benefits of AI"
+
+Claude: I'll generate the speech in streaming mode for faster response.
+
+[Uses fish_audio_tts tool with streaming: true]
+
+Result: Streaming audio saved to ./audio_output/tts_2025-01-03T10-35-00.mp3
+```
+
+#### WebSocket Real-time Streaming
+
+```
+User: "Stream and play in real-time: 'Welcome to the future of AI'"
+
+Claude: I'll stream the speech via WebSocket and play it in real-time.
+
+[Uses fish_audio_tts tool with websocket_streaming: true, realtime_play: true]
+
+Result: Audio streamed and played in real-time via WebSocket
+```
+
+#### Adjusting Speed, Volume, and Expressiveness
+
+```
+User: "Generate speech saying 'Breaking news!' at 1.5x speed with high emotion"
+
+Claude: I'll generate expressive, fast-paced speech.
+
+[Uses fish_audio_tts tool with text, speed: 1.5, temperature: 0.9]
+
+Result: Audio generated with increased speed and expressiveness
+```
+
+## Development
+
+### Local Development
+
+1. Clone the repository:
+```bash
+git clone https://github.com/da-okazaki/mcp-fish-audio-server.git
+cd mcp-fish-audio-server
+```
+
+2. Install dependencies:
+```bash
+npm install
+```
+
+3. Create `.env` file:
+```bash
+cp .env.example .env
+# Edit .env with your API key
+```
+
+4. Build the project:
+```bash
+npm run build
+```
+
+5. Run in development mode:
+```bash
+npm run dev
+```
+
+### Testing
+
+Run the test suite:
+```bash
+npm test
+```
+
+### Project Structure
+
+```
+mcp-fish-audio-server/
+├── src/
+│   ├── index.ts          # MCP server entry point
+│   ├── tools/
+│   │   └── tts.ts        # TTS tool implementation
+│   ├── services/
+│   │   └── fishAudio.ts  # Fish Audio API client
+│   ├── types/
+│   │   └── index.ts      # TypeScript definitions
+│   └── utils/
+│       └── config.ts     # Configuration management
+├── tests/                # Test files
+├── audio_output/         # Default audio output directory
+├── package.json
+├── tsconfig.json
+└── README.md
+```
+
+## API Documentation
+
+### Fish Audio Service
+
+The service provides two main methods:
+
+1. **generateSpeech**: Standard TTS generation
+   - Returns audio buffer
+   - Suitable for short texts
+   - Lower memory usage
+
+2. **generateSpeechStream**: Streaming TTS generation
+   - Returns audio stream
+   - Suitable for long texts
+   - Real-time processing
+
+### Error Handling
+
+The server handles various error scenarios:
+
+- **INVALID_API_KEY**: Invalid or missing API key
+- **NETWORK_ERROR**: Connection issues with Fish Audio API
+- **INVALID_PARAMS**: Invalid request parameters
+- **QUOTA_EXCEEDED**: API rate limit exceeded
+- **SERVER_ERROR**: Fish Audio server errors
+
+## Troubleshooting
+
+### Common Issues
+
+1. **"FISH_API_KEY environment variable is required"**
+   - Ensure you've set the `FISH_API_KEY` environment variable
+   - Check that the API key is valid
+
+2. **"Network error: Unable to reach Fish Audio API"**
+   - Check your internet connection
+   - Verify Fish Audio API is accessible
+   - Check for proxy/firewall issues
+
+3. **"Text length exceeds maximum limit"**
+   - Split long texts into smaller chunks
+   - Maximum supported length is 10,000 characters
+
+4. **Audio files not appearing**
+   - Check the `AUDIO_OUTPUT_DIR` path exists
+   - Ensure write permissions for the directory
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request.
+
+1. Fork the repository
+2. Create your feature branch (`git checkout -b feature/AmazingFeature`)
+3. Commit your changes (`git commit -m 'Add some AmazingFeature'`)
+4. Push to the branch (`git push origin feature/AmazingFeature`)
+5. Open a Pull Request
+
+## License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+## Acknowledgments
+
+- [Fish Audio](https://fish.audio/) for providing the excellent TTS API
+- [Anthropic](https://anthropic.com/) for creating the Model Context Protocol
+- The MCP community for inspiration and examples
+
+## Support
+
+For issues, questions, or contributions, please visit the [GitHub repository](https://github.com/da-okazaki/mcp-fish-audio-server).
+
+## Changelog
+
+See [CHANGELOG.md](CHANGELOG.md) for a detailed list of changes.

package/dist/index.d.ts

@@ -0,0 +1,3 @@
+#!/usr/bin/env node
+export {};
+//# sourceMappingURL=index.d.ts.map

package/dist/index.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":""}

package/dist/index.js

@@ -0,0 +1,72 @@
+#!/usr/bin/env node
+import { Server } from '@modelcontextprotocol/sdk/server/index.js';
+import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
+import { CallToolRequestSchema, ListToolsRequestSchema } from '@modelcontextprotocol/sdk/types.js';
+import { TTSTool } from './tools/tts.js';
+import { ListReferencesTool } from './tools/listReferences.js';
+import { loadConfig } from './utils/config.js';
+import { logger } from './utils/logger.js';
+async function main() {
+    try {
+        // Validate configuration on startup
+        loadConfig();
+        // Create MCP server
+        const server = new Server({
+            name: 'fish-audio-mcp-server',
+            version: '0.1.0',
+        }, {
+            capabilities: {
+                tools: {},
+            },
+        });
+        // Create and register tools
+        const ttsTool = new TTSTool();
+        const listRefTool = new ListReferencesTool();
+        const tools = [ttsTool, listRefTool];
+        server.setRequestHandler(ListToolsRequestSchema, async () => ({
+            tools: tools.map(tool => ({
+                name: tool.name,
+                description: tool.description,
+                inputSchema: tool.inputSchema,
+            })),
+        }));
+        server.setRequestHandler(CallToolRequestSchema, async (request) => {
+            const tool = tools.find(t => t.name === request.params.name);
+            if (tool) {
+                const result = await tool.run(request.params.arguments);
+                return {
+                    content: [
+                        {
+                            type: 'text',
+                            text: JSON.stringify(result, null, 2),
+                        },
+                    ],
+                };
+            }
+            throw new Error(`Unknown tool: ${request.params.name}`);
+        });
+        // Start server with stdio transport
+        const transport = new StdioServerTransport();
+        await server.connect(transport);
+        logger.info('Fish Audio MCP Server started successfully');
+    }
+    catch (error) {
+        logger.error('Failed to start Fish Audio MCP Server:', error);
+        process.exit(1);
+    }
+}
+// Handle graceful shutdown
+process.on('SIGINT', () => {
+    logger.info('Shutting down Fish Audio MCP Server...');
+    process.exit(0);
+});
+process.on('SIGTERM', () => {
+    logger.info('Shutting down Fish Audio MCP Server...');
+    process.exit(0);
+});
+// Run the server
+main().catch((error) => {
+    logger.error('Unhandled error:', error);
+    process.exit(1);
+});
+//# sourceMappingURL=index.js.map

package/dist/index.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":";AAEA,OAAO,EAAE,MAAM,EAAE,MAAM,2CAA2C,CAAC;AACnE,OAAO,EAAE,oBAAoB,EAAE,MAAM,2CAA2C,CAAC;AACjF,OAAO,EACL,qBAAqB,EACrB,sBAAsB,EACvB,MAAM,oCAAoC,CAAC;AAC5C,OAAO,EAAE,OAAO,EAAE,MAAM,gBAAgB,CAAC;AACzC,OAAO,EAAE,kBAAkB,EAAE,MAAM,2BAA2B,CAAC;AAC/D,OAAO,EAAE,UAAU,EAAE,MAAM,mBAAmB,CAAC;AAC/C,OAAO,EAAE,MAAM,EAAE,MAAM,mBAAmB,CAAC;AAE3C,KAAK,UAAU,IAAI;IACjB,IAAI,CAAC;QACH,oCAAoC;QACpC,UAAU,EAAE,CAAC;QAEb,oBAAoB;QACpB,MAAM,MAAM,GAAG,IAAI,MAAM,CACvB;YACE,IAAI,EAAE,uBAAuB;YAC7B,OAAO,EAAE,OAAO;SACjB,EACD;YACE,YAAY,EAAE;gBACZ,KAAK,EAAE,EAAE;aACV;SACF,CACF,CAAC;QAEF,4BAA4B;QAC5B,MAAM,OAAO,GAAG,IAAI,OAAO,EAAE,CAAC;QAC9B,MAAM,WAAW,GAAG,IAAI,kBAAkB,EAAE,CAAC;QAE7C,MAAM,KAAK,GAAG,CAAC,OAAO,EAAE,WAAW,CAAC,CAAC;QAErC,MAAM,CAAC,iBAAiB,CAAC,sBAAsB,EAAE,KAAK,IAAI,EAAE,CAAC,CAAC;YAC5D,KAAK,EAAE,KAAK,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;gBACxB,IAAI,EAAE,IAAI,CAAC,IAAI;gBACf,WAAW,EAAE,IAAI,CAAC,WAAW;gBAC7B,WAAW,EAAE,IAAI,CAAC,WAAW;aAC9B,CAAC,CAAC;SACJ,CAAC,CAAC,CAAC;QAEJ,MAAM,CAAC,iBAAiB,CAAC,qBAAqB,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE;YAChE,MAAM,IAAI,GAAG,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,IAAI,KAAK,OAAO,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC;YAE7D,IAAI,IAAI,EAAE,CAAC;gBACT,MAAM,MAAM,GAAG,MAAM,IAAI,CAAC,GAAG,CAAC,OAAO,CAAC,MAAM,CAAC,SAAgB,CAAC,CAAC;gBAC/D,OAAO;oBACL,OAAO,EAAE;wBACP;4BACE,IAAI,EAAE,MAAM;4BACZ,IAAI,EAAE,IAAI,CAAC,SAAS,CAAC,MAAM,EAAE,IAAI,EAAE,CAAC,CAAC;yBACtC;qBACF;iBACF,CAAC;YACJ,CAAC;YAED,MAAM,IAAI,KAAK,CAAC,iBAAiB,OAAO,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC;QAC1D,CAAC,CAAC,CAAC;QAEH,oCAAoC;QACpC,MAAM,SAAS,GAAG,IAAI,oBAAoB,EAAE,CAAC;QAC7C,MAAM,MAAM,CAAC,OAAO,CAAC,SAAS,CAAC,CAAC;QAEhC,MAAM,CAAC,IAAI,CAAC,4CAA4C,CAAC,CAAC;IAC5D,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACf,MAAM,CAAC,KAAK,CAAC,wCAAwC,EAAE,KAAK,CAAC,CAAC;QAC9D,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IAClB,CAAC;AACH,CAAC;AAED,2BAA2B;AAC3B,OAAO,CAAC,EAAE,CAAC,QAAQ,EAAE,GAAG,EAAE;IACxB,MAAM,CAAC,IAAI,CAAC,wCAAwC,CAAC,CAAC;IACtD,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;AAClB,CAAC,CAAC,CAAC;AAEH,OAAO,CAAC,EAAE,CAAC,SAAS,EAAE,GAAG,EAAE;IACzB,MAAM,CAAC,IAAI,CAAC,wCAAwC,CAAC,CAAC;IACtD,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;AAClB,CAAC,CAAC,CAAC;AAEH,iBAAiB;AACjB,IAAI,EAAE,CAAC,KAAK,CAAC,CAAC,KAAK,EAAE,EAAE;IACrB,MAAM,CAAC,KAAK,CAAC,kBAAkB,EAAE,KAAK,CAAC,CAAC;IACxC,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;AAClB,CAAC,CAAC,CAAC"}

package/dist/services/fishAudioSDK.d.ts

@@ -0,0 +1,29 @@
+import { TTSParams, TTSResponse } from '../types/index.js';
+import { Writable } from 'stream';
+export declare class FishAudioSDKService {
+    private apiKey;
+    private modelId;
+    constructor();
+    /**
+     * Generate speech using standard HTTP API
+     */
+    generateSpeech(params: TTSParams): Promise<TTSResponse>;
+    /**
+     * Generate speech with streaming to file
+     */
+    generateSpeechStream(params: TTSParams, outputPath: string): Promise<number>;
+    /**
+     * Generate speech using WebSocket for real-time streaming
+     */
+    generateSpeechWebSocket(params: TTSParams, textChunks: string[] | AsyncGenerator<string>): AsyncGenerator<Buffer>;
+    /**
+     * Stream speech to a writable stream (for real-time playback)
+     */
+    streamToPlayer(params: TTSParams, textChunks: string[] | AsyncGenerator<string>, playerStream: Writable): Promise<number>;
+    /**
+     * Helper to convert array to async generator
+     */
+    private arrayToAsyncGenerator;
+    private handleError;
+}
+//# sourceMappingURL=fishAudioSDK.d.ts.map

package/dist/services/fishAudioSDK.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"fishAudioSDK.d.ts","sourceRoot":"","sources":["../../src/services/fishAudioSDK.ts"],"names":[],"mappings":"AAEA,OAAO,EACL,SAAS,EACT,WAAW,EAGZ,MAAM,mBAAmB,CAAC;AAG3B,OAAO,EAAE,QAAQ,EAAE,MAAM,QAAQ,CAAC;AAsBlC,qBAAa,mBAAmB;IAC9B,OAAO,CAAC,MAAM,CAAS;IACvB,OAAO,CAAC,OAAO,CAAS;;IAQxB;;OAEG;IACG,cAAc,CAAC,MAAM,EAAE,SAAS,GAAG,OAAO,CAAC,WAAW,CAAC;IAsC7D;;OAEG;IACG,oBAAoB,CAAC,MAAM,EAAE,SAAS,EAAE,UAAU,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM,CAAC;IAqClF;;OAEG;IACI,uBAAuB,CAC5B,MAAM,EAAE,SAAS,EACjB,UAAU,EAAE,MAAM,EAAE,GAAG,cAAc,CAAC,MAAM,CAAC,GAC5C,cAAc,CAAC,MAAM,CAAC;IAkCzB;;OAEG;IACG,cAAc,CAClB,MAAM,EAAE,SAAS,EACjB,UAAU,EAAE,MAAM,EAAE,GAAG,cAAc,CAAC,MAAM,CAAC,EAC7C,YAAY,EAAE,QAAQ,GACrB,OAAO,CAAC,MAAM,CAAC;IAkBlB;;OAEG;YACY,qBAAqB;IAMpC,OAAO,CAAC,WAAW;CAuDpB"}