VibeVoice TTS Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VIBEVOICE_TTS_HOST | No | Server host | 0.0.0.0 |
| VIBEVOICE_TTS_PORT | No | Server port | 8101 |
| VIBEVOICE_TTS_DTYPE | No | Data type (auto, bfloat16, float32) | auto |
| VIBEVOICE_TTS_DEVICE | No | Device to use (auto, cuda, mps, cpu) | auto |
| VIBEVOICE_TTS_MODEL_ID | No | Model identifier | vibevoice/VibeVoice-7B |
| VIBEVOICE_TTS_CFG_SCALE | No | Classifier-free guidance scale | 1.3 |
| VIBEVOICE_TTS_IDLE_TIMEOUT | No | Seconds before unloading model (0 = never) | 300 |
| VIBEVOICE_TTS_QUANTIZE_4BIT | No | Enable 4-bit quantization | false |
| VIBEVOICE_TTS_MAX_NEW_TOKENS | No | Maximum new audio tokens (0 = unlimited) | 0 |
| VIBEVOICE_TTS_N_DIFFUSION_STEPS | No | Number of diffusion denoising steps | 10 |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/tjameswilliams/ai-tts-vibe-openai'
If you have feedback or need assistance with the MCP directory API, please join our Discord server