Research Voicebox for local voice cloning

[CCOSTAN]

Context

Carlo wants to evaluate Voicebox as a local voice-cloning option that can run on his own hardware.

Why it matters

If this works well, it could provide a self-hosted path for voice cloning and local speech generation without sending audio to a cloud service.

Proposed next step

Check whether Voicebox fits a home-lab workflow, confirm the hardware and dependency requirements, and identify any integration path that would make it useful for the existing setup.

Research links

• https://github.com/jamiepine/voicebox
• https://github.com/jamiepine/voicebox/blob/main/docs/content/docs/index.mdx
• https://github.com/jamiepine/voicebox/blob/main/docs/content/docs/overview/docker.mdx

[CCOSTAN]

Research update: on-demand Voicebox appliance

An on-demand deployment looks like the best fit for this use case.

Rather than running Voicebox as an always-on service, treat it as a temporary voice-generation appliance that is started only when producing narration. During a VO run, pause the heavier camera/NVR workload to free CPU and memory, start the Voicebox stack, generate the narration assets, export the audio, then stop Voicebox and restore the normal workload.

Proposed shape:

• Dedicated VM or container host placement on shared storage, not inside the existing Home Assistant runtime.
• Size the test appliance around 4 vCPU and 12-16 GB RAM so Voicebox has enough headroom for one engine without competing with always-on services.
• Keep the service LAN-only or behind auth. Voicebox's Docker/API docs currently describe no built-in API authentication.
• Start with CPU-friendly engines for the first benchmark: LuxTTS for cloned English voice, Kokoro for preset voice speed, then Qwen 0.6B only if quality justifies the slower path.
• Avoid assuming the larger models are practical on CPU until tested. Qwen 1.7B, Chatterbox Multilingual, and TADA 3B are likely GPU/VRAM-oriented for comfortable long-form use.

Next benchmark should be a real YouTube script sample, not a synthetic sentence:

1. Create/import a clean voice profile sample.
2. Generate a 1-2 minute narration chunk with LuxTTS and one alternate engine.
3. Record wall-clock generation time, CPU/RAM pressure, pronunciation issues, edit burden, and final audio quality.
4. Decide whether this can replace the current paid VO path or should remain a fallback/local experiment.