跳到主要内容

voicestudio

❖ Communityv1.0.0

Voice · by aska-digital · added

Client for the local VoiceStudio text-to-speech app (debpalash/VoiceStudio): speak short text, design or clone voices, browse voices, render chaptered long-form audio, dub videos, and check server status. Six tools with mirrored slash commands plus a bundled skill.

Open in Hermes Desktop
hermes plugins install voicestudio
Repository ↗Reviewed source @ efe5c19 ↗Documentation ↗

What it adds

Tools 6

vs_speakvs_design_voicevs_list_voicesvs_longformvs_dubvs_status

README

From the reviewed commit efe5c19 ↗; it updates when the author re-pins.

protean-voice-studio

VoiceStudio text-to-speech sidecar client for Hermes Agent, based on https://github.com/debpalash/VoiceStudio.

Site: https://aska-digital.github.io/protean-voice-studio/

What it does

Six tools, one per user intent:

  1. vs_speak: reads short text aloud in a chosen voice and saves it as an audio file.
  2. vs_design_voice: describes a voice in plain words (or clones one from a sample recording) and saves it for reuse.
  3. vs_list_voices: browses the voices you can use: your saved voices, the shared gallery, and ready-made presets.
  4. vs_longform: turns a long script into chaptered audio (audiobook/podcast).
  5. vs_dub: dubs a video into other languages using one of your voices.
  6. vs_status: checks that VoiceStudio is running, what is loaded, and what is missing.

Each tool is also mirrored as a slash command (/vs-speak, /vs-design, /vs-voices, /vs-longform, /vs-dub, /vs-status), plus one bundled skill (voice-studio).

Prerequisites

A local VoiceStudio server, default http://127.0.0.1:3900. Start the VoiceStudio app first; /vs-status tells you when it is back.

Install

From the Hermes plugin catalog:

hermes plugins install voicestudio

Manual install: point Hermes at the voicestudio/ subdirectory. It carries the manifest and the package together:

git clone https://github.com/aska-digital/protean-voice-studio
hermes plugins install ./protean-voice-studio/voicestudio

The plugin installs disabled (opt-in). Enable it with:

hermes plugins enable voicestudio

Configure

Plugin settings (see plugin.yaml config_schema):

  • base_url: VoiceStudio server base URL (default http://127.0.0.1:3900).
  • default_voice: default narrator voice id when the user names none (default empty: pick a voice per call with /vs-voices).
  • default_engine: preferred engine when several are loaded (default empty).
  • timeout_s: read timeout in seconds for generation calls (default 600).

Usage

/vs-status
/vs-speak --text 'Hello there.' --voice <id>

For chapters, audiobooks, or anything over a few minutes, use /vs-longform with a markdown script file (# headings split chapters).

Disclosure

What the plugin does on your machine, for the catalog record:

  • All network traffic stays between Hermes and your VoiceStudio server (default http://127.0.0.1:3900, configurable via base_url). Nothing is sent to third-party services.
  • vs_dub uploads your video file to the VoiceStudio server; vs_design_voice --sample uploads your sample recording. Both stay on your local server.
  • The plugin reads the script, video, and sample files you point it at, and writes generated audio under the plugin output directory (or the --out_path you give).
  • No credentials are read or stored. No telemetry. No self-updates: catalog installs stay pinned to the reviewed commit.

Dev

bash run_tests.sh        # unit suite, mocked HTTP (no server needed)
python3 -m pytest tests/ # same suite, direct

Live integration tests need the VoiceStudio server running.

License

MIT. See LICENSE.

More by aska-digital

All 5 plugins by aska-digital →
protean-ordaprompt❖ Community★ 2

Jev-style comparative classifier for OrdaPilot. It compares all topic labels and session choices in one batch, including new-topic, ambiguous, and new-session options. It uses calibrated score and margin gates, weighs continuity against context cost and contamination, and abstains when uncertain. OpenRouter is optional for provisional new-label proposals and disabled by default.

Automation
protean-model-sync❖ Community★ 1

Fleet-wide provider and model presets with CLI and Hermes Desktop support. Disclosure — writes model/provider keys into the config.yaml of the profiles you select (backup taken first).

Models
cognition❖ Community

Cognition session-end memory — facts regex-extracted from your messages at session end, stored in a local SQLite queue and JSON log under one repo label, with fetch-first merge, per-entry provenance, and budgeted prefetch (tools: cognition_search, cognition_status, read-only cognition_dream). Disclosure — saves verbatim excerpts (up to 400 chars) of your own messages that match preference/decision phrases in plain local files under HERMES_HOME/cognition/ (SQLite queue, JSON commit log) and re-injects them into later prompts sent to your model provider; the author name is read from ~/.gitconfig; the plugin makes no network calls of its own.

Memory
protean-subagent-viewer❖ Community★ 0

Read-only Hermes Desktop pane for live and past delegated subagent workers.

Desktop

← Back to the catalog · catalog built Oct 12, 2026