From wispr-pack
Provides performance tuning for Wispr Flow voice-to-text API via WebSocket or REST. Covers auth, audio formats, errors for dictation, streaming, voice apps.
How this skill is triggered — by the user, by Claude, or both
Slash command
/wispr-pack:wispr-performance-tuningThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Guidance for performance tuning with Wispr Flow voice-to-text API.
Guidance for performance tuning with Wispr Flow voice-to-text API.
wss://api.wisprflow.ai/api/v1/ws (recommended, low latency)POST /api/v1/transcribe (simpler, higher latency)| Error | Cause | Solution |
|---|---|---|
401 Unauthorized | Invalid key | Check at wisprflow.ai/developers |
| WebSocket closed | Network issue | Reconnect with backoff |
| Poor accuracy | Wrong context | Set context to 'programming' for code |
See related Wispr Flow skills for more patterns.
npx claudepluginhub jeremylongshore/claude-code-plugins-plus-skills --plugin wispr-packProvides Wispr Flow production checklist for voice-to-text API integration via WebSocket or REST. Covers auth, error handling, audio formats, and best practices for dictation apps.
Builds voice AI applications using OpenAI Realtime API, Deepgram, ElevenLabs, Vapi, and LiveKit. Handles real-time audio streaming, voice agent architecture, and latency optimization.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.