MCP server for Whisper speech-to-text
## Whisper MCP Server: Speech Recognition AI The **Whisper MCP Server** integrates OpenAI's Whisper speech recognition model into Google Antigravity. This industry-leading model provides accurate transcription across 99 languages with automatic language detection and translation capabilities. ### Why Whisper MCP? Whisper sets the standard for speech recognition: - **99 Languages**: Transcribe almost any language - **High Accuracy**: State-of-the-art word error rates - **Translation**: Translate audio to English - **Timestamps**: Word and segment level timing - **Open Source**: Run locally or via API ### Key Features #### 1. Transcription ```python from openai import OpenAI client = OpenAI() # Transcribe audio file with open("meeting.mp3", "rb") as audio_file: transcript = client.audio.transcriptions.create( model="whisper-1", file=audio_file, response_format="verbose_json", timestamp_granularities=["word", "segment"] ) print(transcript.text) ``` #### 2. Translation ```python # Translate any language to English with open("french_audio.mp3", "rb") as audio_file: translation = client.audio.translations.create( model="whisper-1", file=audio_file ) print(translation.text) # English translation ``` #### 3. Local Whisper ```python import whisper # Run locally with open source model model = whisper.load_model("large-v3") result = model.transcribe( "audio.mp3", language="en", word_timestamps=True ) for segment in result["segments"]: print(f"[{segment['start']:.2f}s] {segment['text']}") ``` ### Configuration ```json { "mcpServers": { "whisper": { "command": "npx", "args": ["-y", "@anthropic/mcp-whisper"], "env": { "OPENAI_API_KEY": "your-key", "WHISPER_MODEL": "large-v3" } } } } ``` ### Use Cases **Meeting Transcription**: Automatically transcribe meetings and calls. **Subtitle Generation**: Create subtitles with accurate timestamps. **Voice Commands**: Build voice-controlled applications. The Whisper MCP Server brings world-class speech recognition to Antigravity.
{
"mcpServers": {
"whisper": {
"mcpServers": {
"whisper": {
"env": {
"OPENAI_API_KEY": "YOUR_OPENAI_API_KEY"
},
"args": [
"-y",
"whisper-mcp"
],
"command": "npx"
}
}
}
}
}