vibevoice-asr
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VIBEVOICE_DTYPE | No | Data type: auto, bfloat16, float32 | auto |
| VIBEVOICE_DEVICE | No | Device: auto, cuda, mps, cpu | auto |
| VIBEVOICE_MODEL_ID | No | HuggingFace model ID | microsoft/VibeVoice-ASR-HF |
| VIBEVOICE_CACHE_DIR | No | Where to store downloaded model weights (default: HuggingFace default) | |
| VIBEVOICE_LOG_LEVEL | No | Logging level | warning |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| transcribe_audioA | Transcribe an audio file using VibeVoice-ASR. Args: file_path: Absolute path to the audio file (wav, mp3, flac, etc.) response_format: Output format: text, json, verbose_json, srt, vtt (default: text) prompt: Optional prompt/context to guide transcription language: Language code for verbose_json output (default: en) |
| load_vibevoice_modelA | Pre-load the VibeVoice-ASR model into memory. Call this before transcribing to avoid a long wait on the first transcription. Model loading takes ~60-90 seconds depending on hardware. |
| get_vibevoice_statusA | Check the current status of the VibeVoice-ASR server. Returns model loaded state, device, dtype, and version info. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a unique purpose: checking server status, loading the model, and transcribing audio. No functional overlap, making it clear which tool to use for each task.
All tool names follow a consistent verb_noun pattern in snake_case (get_vibevoice_status, load_vibevoice_model, transcribe_audio), making them predictable and easy to remember.
Three tools cover the essential operations of an ASR server—status check, model loading, and transcription. The count is well-scoped for the domain without unnecessary extras.
The set covers the core workflow (status, load, transcribe). A minor gap is the lack of an unload model tool, but this does not severely hinder functionality for typical use cases.