Wispr Ci Integration

---
name: wispr-ci-integration
description: "'Wispr Flow ci integration for voice-to-text API integration. Use when integrating Wispr Flow dictation, WebSocket streaming, or building voice-powered applications. Trigger: \"wispr ci integration\". '"
allowed-tools: "Read, Write, Edit, Bash(npm:*), Grep"
category: mcp-and-integrations
source_repo: jeremylongshore/claude-code-plugins-plus-skills
source_path: "plugins/saas-packs/wispr-pack/skills/wispr-ci-integration/SKILL.md"
source_url: https://github.com/jeremylongshore/claude-code-plugins-plus-skills/blob/HEAD/plugins/saas-packs/wispr-pack/skills/wispr-ci-integration/SKILL.md
---

# Wispr Flow Ci Integration

## Overview

Guidance for ci integration with Wispr Flow voice-to-text API.

## Instructions

### Key Wispr Flow Concepts

- **WebSocket API**: `wss://api.wisprflow.ai/api/v1/ws` (recommended, low latency)
- **REST API**: `POST /api/v1/transcribe` (simpler, higher latency)
- **Auth**: API key (backend) or access token (client-side)
- **Audio format**: 16kHz mono PCM preferred
- **Context awareness**: Understands code, CLI commands, dev jargon
- **Platforms**: Mac, Windows, iOS, browser API

## Error Handling

| 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 |

## Resources

- [Wispr Flow Developers](https://wisprflow.ai/developers)
- [API Docs](https://api-docs.wisprflow.ai/introduction)
- [WebSocket Quickstart](https://api-docs.wisprflow.ai/websocket_quickstart)

## Next Steps

See related Wispr Flow skills for more patterns.

---

**Source:** [`jeremylongshore/claude-code-plugins-plus-skills`](https://github.com/jeremylongshore/claude-code-plugins-plus-skills) → `plugins/saas-packs/wispr-pack/skills/wispr-ci-integration/SKILL.md`