Skip to main content
Glama
tjameswilliams

VibeVoice TTS Server

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
VIBEVOICE_TTS_HOSTNoServer host0.0.0.0
VIBEVOICE_TTS_PORTNoServer port8101
VIBEVOICE_TTS_DTYPENoData type (auto, bfloat16, float32)auto
VIBEVOICE_TTS_DEVICENoDevice to use (auto, cuda, mps, cpu)auto
VIBEVOICE_TTS_MODEL_IDNoModel identifiervibevoice/VibeVoice-7B
VIBEVOICE_TTS_CFG_SCALENoClassifier-free guidance scale1.3
VIBEVOICE_TTS_IDLE_TIMEOUTNoSeconds before unloading model (0 = never)300
VIBEVOICE_TTS_QUANTIZE_4BITNoEnable 4-bit quantizationfalse
VIBEVOICE_TTS_MAX_NEW_TOKENSNoMaximum new audio tokens (0 = unlimited)0
VIBEVOICE_TTS_N_DIFFUSION_STEPSNoNumber of diffusion denoising steps10

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

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