Speechdash plugin skills

Agent skills that teach assistants when and how to use Speechdash document and speech tools over the public MCP connection. This repo holds workflow text only; live tools and user sign-in are provided by Speechdash’s hosted MCP server.

Resource	URL
Product	speechdash.com
Agents & integrations	speechdash.com/agents
Help Center (API keys & MCP)	docs.speechdash.com/settings/api-and-mcp
MCP endpoint (Streamable HTTP)	https://mcp.speechdash.com/mcp
REST examples	github.com/speechdash/speechdash-public-api
OpenAPI (live)	api.speechdash.com/v1/openapi.json

Users connect through the plugin or MCP client UI and sign in with their Speechdash account. This repository does not contain credentials or server code.

Cursor: register the hosted MCP as speechdash → https://mcp.speechdash.com/mcp with Authorization: Bearer sh_live_….

Layout

.codex-plugin/plugin.json
skills/
  speechdash-account/SKILL.md
  browse-speechdash-library/SKILL.md
  import-to-speechdash/SKILL.md
  edit-speechdash-document/SKILL.md
  translate-speechdash-document/SKILL.md
  export-speechdash-document/SKILL.md
  speechdash-text-to-speech/SKILL.md

Skills

Skill	When to use	MCP tools
speechdash-account	Plan and credit wallet	speechdash_get_account
browse-speechdash-library	List or read saved documents	speechdash_list_documents, speechdash_get_document
import-to-speechdash	Create documents from pasted text	speechdash_create_document
edit-speechdash-document	Update title, body, language, visibility, archive, or delete	speechdash_update_document, speechdash_delete_document
translate-speechdash-document	New translated version (billed like MP3 export)	speechdash_translate_document
export-speechdash-document	File download (txt, csv, srt, vtt, pdf, docx)	speechdash_export_document
speechdash-text-to-speech	Voices and non-streaming speech	speechdash_list_voices, speechdash_get_voice, speechdash_synthesize_speech

Every hosted MCP tool is covered:

MCP tool	REST
speechdash_get_account	GET /v1/me
speechdash_list_documents	GET /v1/documents
speechdash_get_document	GET /v1/documents/{document_id}
speechdash_create_document	POST /v1/documents
speechdash_update_document	PUT /v1/documents/{document_id}
speechdash_translate_document	POST /v1/documents/{document_id}/translate
speechdash_export_document	GET /v1/documents/{document_id}/export
speechdash_delete_document	DELETE /v1/documents/{document_id}
speechdash_list_voices	GET /v1/voices
speechdash_get_voice	GET /v1/voices/{voice_id}
speechdash_synthesize_speech	POST /v1/audio/speech

Streaming speech (POST /v1/audio/stream and POST /v1/audio/stream/with-timestamps) is REST-only. There is no MCP transcripts tool: finished jobs are library documents (source=transcription).

Contract limits match the public API: document title max 512 characters, text max 500,000, speech input max 5,000 on the MCP synthesize tool.

License

Documentation in this repository is provided under Apache-2.0 unless noted otherwise.

Bundle for upload

Portal uploads expect one top-level folder in the zip: either a single skill directory or a skills/ directory of skill roots. Do not add README, .codex-plugin, or other files to the skills archive unless your publish flow requires them separately.

All bundled skills:

zip -r speechdash-plugin-skills.zip skills

Single skill:

zip -r import-to-speechdash.zip skills/import-to-speechdash

Repository

github.com/speechdash/speechdash-skills

git clone https://github.com/speechdash/speechdash-skills.git