Stats
Actions
Tags
From wispr-pack
Guides Wispr Flow local dev loop for voice-to-text API integration via WebSocket or REST, covering auth, 16kHz PCM audio, programming context, and error handling.
How this skill is triggered — by the user, by Claude, or both
Slash command
/wispr-pack:wispr-local-dev-loopThis 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 local dev loop with Wispr Flow voice-to-text API.
Guidance for local dev loop 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-packGuides Wispr Flow voice-to-text API integration for dictation, WebSocket streaming, and voice apps via WebSocket/REST, auth, audio formats, errors, and deployment.
Enables voice conversations with Claude Code using speech-to-text and text-to-speech. Includes setup, diagnostics, and MCP-based voice interaction.
Builds voice AI applications using OpenAI Realtime API, Deepgram, ElevenLabs, Vapi, and LiveKit. Handles real-time audio streaming, voice agent architecture, and latency optimization.