AdAnvil
by maxbuildog
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ADANVIL_CACHE | No | Moves the cache folder. | |
| ADANVIL_FFMPEG | No | Full path to the ffmpeg binary (absolute path; otherwise it is looked up on PATH, never in the current folder). | |
| ADANVIL_SPEECH | No | Set to off to stop library_index from transcribing on its own (transcribe="auto"); transcribe=true still does. | |
| ADANVIL_FFPROBE | No | Full path to the ffprobe binary (absolute path; otherwise it is looked up on PATH, never in the current folder). | |
| ADANVIL_WORKERS | No | How many files, thumbnails or segments are processed at once. Default max(1, min(4, cpus // 2)), and at most 2 when the machine has under 12 GB of RAM. | |
| ADANVIL_PROJECTS_DIR | No | The folder that holds your projects: the server then refuses any project outside it. Projects are subfolders of it (for example ~/AdAnvil/summer-ad). | |
| ADANVIL_SPEECH_MODEL | No | The model used to transcribe speech during indexing. Default base: fast, good enough to search. | base |
| ADANVIL_SPEECH_PROMPT | No | An optional text that biases the transcriber, for example towards keeping hesitations. | |
| ADANVIL_VOICE_THREADS | No | The torch and Whisper threads (default: usable cores). | |
| ADANVIL_FFMPEG_THREADS | No | Threads of each ffmpeg decoder or encoder. Default max(1, cpus // workers). | |
| ADANVIL_VOICE_PERSISTENT | No | Set to 0 to go back to one process per step instead of one worker per job. | |
| ADANVIL_VOICE_CHECK_MODEL | No | The Whisper model of the pronunciation check (unless the voice spec sets check_model). | |
| ADANVIL_ALLOW_PRIVATE_URLS | No | Set to 1 to let brand_onboard and the downloads reach localhost and the local network (development only). | |
| ADANVIL_VOICE_CHECK_CONFIDENCE | No | The word confidence from 0 to 1 above which the alignment transcript replaces the check model (off to always run the check model; the spec's check_confidence wins). |
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
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 | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo recent community issues