voice is agent-read markdown (skill) from corvinlabs/corvinos: Voice mode for Claude Code — automatically reads assistant replies aloud via TTS, with German/English auto-detection and optional summarization for long responses. Trigger when the user mentions voice, vorlesen, sprachausgabe, TTS, "speak", "say it out loud", or asks about /voice-* commands..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Claude Voice — Read-Aloud TTS Mode
Dieses Skill steuert das Vorlese-Verhalten von Claude Code. Es ergänzt
das eingebaute STT (Spracheingabe via `/voice` und Hold-Space) um
**Sprachausgabe** der Assistant-Antworten.
## Was es macht
- Stop-Hook: Nach jeder Claude-Antwort wird die letzte Textnachricht
automatisch vorgelesen (wenn `enabled=true`).
- Sprache wird automatisch erkannt (Deutsch / Englisch) oder fest
per Config gesetzt.
- Lange Antworten (> Threshold) werden vor dem Vorlesen via Anthropic
Haiku zusammengefasst, damit das Vorlesen erträglich kurz bleibt.
Steuerbar pro Antwort (Phrasen wie "lies vollständig vor" /
"fass zusammen") und global (`/voice-mode`).
- Engine-Auswahl ist auto-detect: bevorzugt OpenAI TTS (wenn
`OPENAI_API_KEY` gesetzt), sonst Piper (lokal) oder espeak-ng als
letzter Fallback.
## Slash-Commands
- `/voice-on` — automatisches Vorlesen aktivieren
- `/voice-off` — automatisches Vorlesen deaktivieren
- `/voice-status` — aktueller Status, Engine, Config
- `/voice-test [de|en|both]` — Audio-Pipeline testen
- `/voice-speak <text>` — Text manuell vorlesen
- `/voice-lang auto|de|en` — Sprach-Modus setzen
…
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
GET https://markdownregistry.com/api/v1/artifacts/art_nkfxloirlzgtxo7r
GET https://markdownregistry.com/api/v1/resolve?ref=corvinlabs/corvinos/voice
GET https://markdownregistry.com/api/v1/blob/6e93ce461383d59301f2af6e408f3dc0c4ed4dd5a058b5dca8d788f995edad2d
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
corvinlabs/corvinos · corvin_operator/bundle/skills/ldd/adr_gate/SKILL.md · ADR Gate — evaluates after non-trivial tasks whether an ADR is warranted; writes to Corvin-ADR repo when yes, names the…
corvinlabs/corvinos · corvin_operator/bundle/skills/ldd/concept_gate/SKILL.md · Concept Gate — evaluates after non-trivial tasks whether a reusable WORKING METHOD (not a decision, not a bug fix) is…
guaardvark/guaardvark · .agents/skills/voice/SKILL.md · Narration and text-to-speech on the user's machine through Guaardvark's Audio Foundry (Chatterbox, Kokoro, Piper) and…
mancerayder42/jarvis-os · optional-skills/voice/SKILL.md · Turn spoken audio into text, and text into a spoken reply, via ElevenLabs (needs an ELEVENLABS_API_KEY). Use when the…