Show HN: Give your AI agent a personality (and a voice) without external APIs

Jul 20, 2026 · 1:01 PM UTC ·1 min read · 0 reactions · 0 comments · 23 views

via

Github

#ai #voice #open-source #setup #personality

TL;DR · WeSearch summary

The article presents an open‑source tool that adds voice output and selectable personalities to AI agents without relying on external APIs. It provides step‑by‑step instructions for cloning the repository, running a setup script, and configuring the voice server across various environments. Users can choose from several predefined personality profiles to alter the agent’s spoken behavior.

Key facts

▪The repository can be cloned and initialized with a Python setup script that automatically configures persona, permissions, and a virtual environment.
▪Manual configuration is supported via JSON files for platforms such as Google Antigravity, Claude CLI, Cursor IDE, and Windsurf Editor, specifying the voice command and arguments.
▪The tool offers multiple personality profiles—including Sarcastic Senior, Eager Intern, Existential Emo, and others—that modify how the agent speaks.
▪All voice functionality runs locally, eliminating the need for external API calls.

About this source

Hacker News (AI / LLM) files mainly under ai. We currently carry 3,329 of its stories.

All Hacker News (AI / LLM) coverage →

Original article

Github

Read full at Github →

Story provenance

Source · retrieval · rights · ranking — open for full record

inspect →

Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.

Record

Original publisher	Github
Canonical URL	https://fellowgeek.github.io/mcp-speak/
Publication time	Mon, 20 Jul 2026 13:01:26 +0000
Retrieval time	2026-07-20T13:10:44.028Z
Last seen	2026-07-20T13:14:57.968Z
Headline source	Publisher (no WeSearch rewrite)
Excerpt source	publisher body
Excerpt method	First ~120 words (~800 chars) of extracted publisher body, fair-use limited.
Summary	WeSearch · cerebras-chat (WeSearch summarizer)
Summary source text	contentText
Citation coverage	Summary is a WeSearch-generated derivative; primary citation is the original publisher URL.
Cluster	uRniltmvUryz
Cluster logic	Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison.
Ranking reason	Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking.
Publisher visit	Yes — open original
Substitutes article?	No — link-out required for full text

Rights status (four layers)

Publisher-declared

No publisher-confirmed rights record for this source yet.

Machine-readable

No source-specific machine-readable restriction detected beyond the public feed.

WeSearch interpretation

WeSearch declared handling (basis: Derived from the published RSS/Atom feed). This is WeSearch policy, not a legal grant on the publisher's behalf.

Unknown

Retrieval and training permissions are not asserted unless the publisher confirms them.

WeSearch handling by dimension

Indexing	May the item be indexed (stored, ranked, made findable)?	Allowed
Snippet	May a short excerpt of the publisher's text be shown?	Allowed
AI summary	May WeSearch generate its own short summary of the article?	Limited
Retrieval / RAG	May the content be exposed for third-party retrieval-augmented generation?	Not asserted
Model training	May the content be used to train AI models?	Not asserted
Commercial reuse	May the content be reused commercially?	Not permitted

Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.

Open original publisher → Source rights JSON → Machine-readable provenance → Rights framework → WESEARCH-STORY-PROVENANCE-V1

Opening excerpt (first ~120 words) tap to expand

Setup Guide Follow these steps to initialize your voice server. 1 Clone Repository Fetch the code and navigate into the project directory. git clone https://github.com/fellowgeek/mcp-speak.git && cd mcp-speak 2 Run Setup Wizard Configures your persona, permissions, and virtual environment automatically. python3 setup.py Manual Integration (Optional) Running python3 setup.py configures your client automatically. Below are manual JSON reference snippets. Google Antigravity Config (~/.gemini/antigravity/mcp_config.json) { "mcpServers": { "voice": { "command": "/ABSOLUTE/PATH/TO/run.sh" } } } Claude CLI Config claude mcp add --scope user voice /ABSOLUTE/PATH/TO/run.sh Claude Desktop Config (~/Library/Application Support/Claude/claude_desktop_config.json) { "mcpServers": { "voice": {…

Excerpt limited to ~120 words for fair-use compliance. The full article is at Github.

Anonymous · no account needed

Discussion

0 comments