Skip to content

robstrayer/voice-foundations

v1.2.0MIT

Thirteen provider-neutral skills for building, debugging and reviewing AI voice agents: stack selection, turn taking, conversation design, speech pipeline, audio frontends, latency, media debugging, call reliability, data capture, evaluation, cost, phone compliance and security.

voice-speech-pipeline

Select, integrate, and evaluate streaming speech recognition and synthesis for a voice agent, including transcript revisions, language support, pronunciation, text buffering, and playable audio delivery. Use when choosing speech-to-text or text-to-speech providers, when names, numbers or words are misheard or mispronounced, or when streaming transcripts are unstable or speech starts late.

License
MIT
Read SKILL.md at the source

Pinned to revision 61e429e8f723, so it is the text this page describes rather than whatever the author pushed since.

Files

Every link opens the file at its source, pinned to the revision this page describes.