Synthesize local text-to-speech via configurable multi-backend proxy with fallbacks.
npx skills add https://github.com/servitola/dotfiles --skill tts-servitola
Please help me install this Agent Skill. Skill: tts Source: https://github.com/servitola/dotfiles/tree/main/claude-code/skills/tts Command: npx skills add https://github.com/servitola/dotfiles --skill tts-servitola
This Skill enables local text-to-speech synthesis using a configurable multi-backend proxy, avoiding reliance on external cloud services and enabling offline or tightly controlled playback workflows.
Synthesize the Russian phrase 'Привет, мир' using the default local tts backend.
High-intent search queries and answers about installing and using this skill.
Local text-to-speech synthesis is achieved by configuring a multi-backend proxy that routes requests to local services, avoiding external cloud dependencies. This enables offline or tightly controlled playback workflows.
Yes, the text-to-speech proxy supports Russian and multilingual voice synthesis. It provides optional SSML control to manage voice parameters and pronunciation accurately across different languages.
Long-text chunking for text-to-speech playback is handled automatically by splitting extended text inputs into smaller segments. The proxy synthesizes these chunks individually and concatenates the resulting audio for continuous playback.
Available backends for local text-to-speech synthesis include Gemini tts, tts-piper, and tts-azure. The proxy supports clear fallback paths between these backends, requiring explicit voice configuration for each.
Yes, a running LiteLLM proxy is required to route synthesis requests. You must also have the respective backend services running and provide explicit voice configuration per backend to generate speech successfully.
When a primary text-to-speech backend fails during synthesis, the configurable multi-backend proxy utilizes predefined fallback paths. It automatically routes the request to an alternative configured backend to ensure continuous speech generation.
sentientspriteGenerate speech audio files locally using sherpa-onnx and Piper TTS models.
BEIRUXGenerate ElevenLabs text-to-speech audio and play it locally via CLI.
tony2015116Synthesize and clone voices with MiniMax Voice API and FFmpeg.
frankhli843Synthesize speech audio locally from text using sherpa-onnx.
