Docker deployment for Kyutai's 1.6B parameter streaming text-to-speech model supporting English and French. Provides production-ready containerized service with Web UI, REST API, and MCP server interfaces for generating high-quality speech from text. Features GPU-resident model loading for fast inference (350ms latency with 32 concurrent users on L40S), supports voice conditioning with 10-second audio samples, and includes automated GPU selection with lazy loading for efficient memory management.
Cognium trust score
63%
Tier
Scanned
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Last scanned 2026-09-02.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.