Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FISH_API_KEY | Yes | Your Fish Audio API key | |
| FISH_MODEL_ID | No | TTS model to use (s1, speech-1.5, speech-1.6) | s1 |
| FISH_STREAMING | No | Enable streaming by default | false |
| AUDIO_OUTPUT_DIR | No | Directory for audio file output | ~/.fish-audio-mcp/audio_output |
| FISH_MP3_BITRATE | No | MP3 bitrate (64, 128, 192) | 128 |
| FISH_REFERENCE_ID | No | Default voice reference ID | |
| FISH_OUTPUT_FORMAT | No | Default audio format (mp3, wav, pcm, opus) | mp3 |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| fish_audio_tts | Generate speech from text using Fish Audio TTS API |
| fish_audio_list_references | List all configured voice references |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |