Keys Ghost Machine — audio/visual agent, powered by TensorFold
The voices (Drama 3), the promo and screenshots for Boo.
Fourteen named voices for Fish Audio Drama 3, made for Boo, the audio/visual agent in drowzeys/keys-ghost-machine-audio-visual-agent. Vesper is Boo's default.
Requirements
Drama 3 served by TensorFold with named voices (--voices): about 21 GB of weights (the
NVFP4 pruned build); about 28 GB wired on a Mac with Apple
silicon (macOS 26, Metal) or about 21 GB on an NVIDIA DGX Spark (CUDA 13). The full Boo stack needs about 79 GB on a Mac
(96 GB minimum, 128 GB or more recommended) or about 61 GB on a DGX Spark; see the GitHub README. Software: TensorFold
1.1.4 (the prebuilt builds in the GitHub release add NVFP4 pruned Drama 3, the voice-prefix cache and Cosmos3-Edge; the
DGX Spark's Drama 3 runs on plotarmordev's NVFP4 fork, because stock 1.1.4 refuses the pruned checkpoint).
Install
The whole Boo stack, these voices included, installs with one command on a DGX Spark or an Apple silicon Mac:
curl -fsSL https://raw.githubusercontent.com/drowzeys/keys-ghost-machine-audio-visual-agent/main/install.sh | bash
It checks memory and disk, fetches the TensorFold 1.1.4 builds, the models and these voices, and starts Boo; kgm start,
kgm stop and kgm status run it after that. Settings, the Docker alternative and uninstalling are in the
One-shot install section of the
GitHub README.
See it work
Real recordings of the page, hands-free. The voices are synthetic Drama 3 voices and the desk is a computer-made scene; no person appears. On TensorFold 1.1.4, voice-to-voice is 0.47–0.60 s on a Mac (M5 Ultra) and 0.55–0.77 s on a DGX Spark, with Drama 3's first audio in Vesper at 122 ms and 121 ms.
Screenshots
| Phone (camera on) | Desktop |
|---|---|
 |
  |
A task handed to Hermes: the card shows only the tool's name while it works, then the answer.
The voices
| Voice | Description |
|---|---|
| vesper | British female; low, smooth and confident (default) |
| elara | British female; low, sleek and quick |
| lyra | British female; calm, smooth and assured |
| imogen | British female; warm, poised and articulate |
| seren | British female; light, elegant and lively |
| aria | British female; crisp, bright and polished |
| oliver | British male; warm and measured |
| skye | American female; low, smooth and steady |
| atlas | Deep, steady male narrator; unhurried storytelling |
| milo | Calm, low male voice; relaxed and reassuring |
| june | Warm female voice; natural and conversational |
| nova | Bright, energetic young female voice |
| sam | Friendly mid-range voice; clear, upbeat assistant |
| wren | Soft, gentle female voice; quiet and close |
previews/NAME.wav is each voice saying "Hi, I am NAME. Tell me what you would like to make today."
How they were made
Every voice is a take of Drama 3's own built-in voice, generated by the model; no recorded person is in any of
them. Drama 3 picks a different speaker for each random seed, so many takes of one line were generated and scored on
pitch, word error (Parakeet v3) and accent (SpeechBrain CommonAccent), and the chosen takes were encoded with Drama 3's
codec into reference codes. Each file says so in its source field.
Files
voices/mac/NAME.json:drama3-http-voice/1(frame-major codes, with a description), for the TensorFold Metal build with named voices.voices/spark/NAME.json:drama3-voice/1([10, frames]codes withcodes_sha256), for plotarmordev's TensorFold CUDA build.previews/NAME.wav: a short sample of each.
Use
tensorfold serve DRAMA3_DIR --voices voices/mac --default-voice vesper # voices/spark on the CUDA build
curl -s http://127.0.0.1:8098/v1/audio/speech -H 'Content-Type: application/json' \
-d '{"model": "drama-3", "voice": "vesper", "input": "Hello there.", "response_format": "wav"}' -o hello.wav
Licence
The voice codes are derived from Drama 3's output, so they fall under the Fish Audio Community License. Hosted services that generate speech for third parties need a separate licence from Fish Audio.
Questions: GitHub Issues.
Credits
| Component | What it does in Boo | Author / org | Licence | Link |
|---|---|---|---|---|
| Nemotron 3.5 Bolt | The front brain: answers most turns, with mood tags for the face | NVIDIA | NVIDIA Open Model License | Hugging Face |
| Cosmos3-Edge | Camera questions and memory captions (its reasoner tower) | NVIDIA | OpenMDW 1.1 | Hugging Face |
| Parakeet TDT 0.6B v3 | Speech to text | NVIDIA | CC-BY-4.0 | Hugging Face |
| parakeet-mlx | Runs Parakeet on the Mac | senstella | Apache-2.0 | GitHub |
| NeMo | Runs Parakeet on the DGX Spark | NVIDIA | Apache-2.0 | GitHub |
| Drama 3 | The voice (speech synthesis); the 14 named voices are takes of its built-in voice | Fish Audio | Fish Audio Community License | Hugging Face |
| drama-3-NVFP4-Pruned, NVFP4 CUDA fork and named voices | The 4-bit pruned Drama 3 checkpoint, the DGX Spark's Drama engine and --voices |
plotarmordev | Fish Audio Community License (weights) · Apache-2.0 (engine) | checkpoint · fork |
| TensorFold | The engine for Bolt, Drama 3 and Cosmos3-Edge, on Metal and CUDA | Ash Hart | Apache-2.0 | GitHub |
| Eyes of Kai | The continuity log: timestamped captions so Boo can answer about the past | tonyd2wild | MIT | GitHub |
| Hermes Agent | The back agent with tools and skills, over ACP | Nous Research | see repository | GitHub |
| qwen-audio-agent | Design inspiration: the frontstage/backstage split (a fast voice in front, a tool-using agent behind that reports back); no code from it is used | Qwen Audio team | Apache-2.0 | GitHub |
| RED-SNOW 5.3 Flash | The back agent's model in the reference setup (a GLM-5.3-Flash build); any OpenAI-compatible model works | RED-SNOW | see model card | — |
| Silero VAD v5 | Hears when someone is speaking (silero_vad.onnx ships in the GitHub repo) |
Silero | MIT | GitHub |
| MediaPipe Face Detector and Hand Landmarker | Gaze tracking, exact finger counts and which hand, in the page | Apache-2.0 | GitHub | |
| Three.js | Boo, the 3D ghost | three.js authors (mrdoob) | MIT | GitHub |
| ddgs | Web search for quick live facts | deedy5 | MIT | GitHub |
| wttr.in | Weather for quick live facts (data from WorldWeatherOnline) | Igor Chubin | Apache-2.0 | GitHub |
| NVIDIA PyTorch container | The Docker image's base (nvcr.io/nvidia/pytorch:26.07-py3) |
NVIDIA | NVIDIA Deep Learning Container License | NGC |
| Qwen3.5-0.8B (earlier versions) | The first memory captioner | Qwen team, Alibaba Cloud | Apache-2.0 | Hugging Face |
| AEON-7 Nemotron 3 Nano Omni build (earlier versions) | The first camera model, from NVIDIA's Nemotron 3 Nano Omni | AEON-7 | NVIDIA Open Model License | Hugging Face |
Full details: CREDITS.md
Model tree for drowzeys/keys-ghost-machine-audio-visual-agent
Base model
fishaudio/drama-3