Server Configuration
Describes the environment variables required to run the server.
Name | Required | Description | Default |
---|---|---|---|
TTS_OUTPUT_DIR | No | Directory for saving audio output files | ./audio_output |
KOKORO_MODEL_PATH | No | Path to the Kokoro model file | ./kokoro-v1.0.onnx |
TTS_DEFAULT_VOICE | No | Default voice to use for synthesis | af_heart |
KOKORO_VOICES_PATH | No | Path to the voices binary file | ./voices-v1.0.bin |
TTS_MAX_QUEUE_SIZE | No | Maximum number of requests in the processing queue | 100 |
TTS_ENABLE_STREAMING | No | Enable real-time audio streaming | true |
Schema
Prompts
Interactive templates invoked by user choice
Name | Description |
---|---|
create_podcast_intro | Generate a professional podcast introduction with warm, engaging tone |
create_tutorial_narration | Create clear, educational narration for tutorials and instructional content |
create_marketing_copy | Generate persuasive marketing audio with confident, professional tone |
create_accessibility_description | Generate clear audio descriptions for visual content accessibility |
Resources
Contextual data attached and managed by the client
Name | Description |
---|---|
Available TTS Voices | Comprehensive list of available voices and their capabilities |
TTS Usage Examples | Examples demonstrating various TTS features and use cases |
Tools
Functions exposed to the LLM to take actions
Name | Description |
---|---|
synthesize_speech | Convert text to speech with advanced voice controls and natural expression |
batch_synthesize | Synthesize multiple text segments with optional merging and intelligent pacing |
get_voices | Get list of available voices with their capabilities and supported features |
get_status | Get processing status for a synthesis request |
list_output_files | List saved audio files in the output directory with metadata |