Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

text-to-speech · calesthio — Claude Code skill: what it does, how to install

Generates speech audio with HeyGen Starfish and lets you choose a voice, speed, and pitch. Useful for voiceovers, narration, and podcasts.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add calesthio/OpenMontage --skill text-to-speech -a claude-code
Open on GitHub

What text-to-speech does

This skill turns text into an audio file through HeyGen Starfish. It can list voices by language and gender, select a voice_id, and set speech speed, pitch, and locale. A locale can be supplied for multilingual voices.

The usual flow starts with mcp__heygen__list_audio_voices, followed by mcp__heygen__text_to_speech. These MCP tools are preferred over direct requests to GET /v1/audio/voices and POST /v1/audio/text_to_speech. The response includes an audio_url and word timestamps.

You need HEYGEN_API_KEY set before use, so check that first. Starfish voices come from GET /v1/audio/voices, while video voices use GET /v2/voices; the two sets are not always compatible.

What it helps with

  • turn text into a standalone audio file
  • find a voice by language and gender
  • adjust speech speed and pitch
  • create audio for narration or a podcast
  • return word-level timestamps

Example prompts for the agent

  • List HeyGen voices for the target language, then turn this script into audio with the selected voice.
  • Generate speech from this text with the given `voice_id`, speed 1.0, and pitch 0.
  • Find a voice for the requested locale and return the `audio_url` with word timestamps.

How to install text-to-speech

1Skills CLI (Vercel)

npx skills add calesthio/OpenMontage --skill text-to-speech -a claude-code

2Manually: put the files in place

~/.claude/skills/text-to-speech/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/text-to-speech/

From the same set28

The whole set →
video-understand calesthio This skill extracts video frames and transcribes audio locally with ffmpeg and Whisper. Use it to inspect video content without API keys. Claude Code CX Codex Cursor +1 1,300installs remotion calesthio Teaches AI agents toolkit-specific Remotion patterns, including custom transition shaders and 30 fps video rules. Claude Code CX Codex Cursor +1 1,200installs video-download calesthio Uses yt-dlp to fetch video, audio, subtitles, or URL metadata. Use it when you need a local file, a selected resolution, or details without downloading media. Claude Code CX Codex Cursor +1 1,200installs lottie-bodymovin calesthio Applies Disney's 12 animation principles to Lottie vector animations. Bridges After Effects setup with runtime JavaScript controls. Claude Code CX Codex Cursor +1 1,100installs create-video calesthio This skill turns a description into a finished video: write what you want to see, and HeyGen generates the script, picks an avatar, adds voiceover and editing. Good for quick demos, explainers and promos without tweaking every detail. Claude Code CX Codex Cursor +1 1,100installs video-toolkit calesthio Automates video creation: generates voiceovers, background music, animates talking heads, and composes scenes with Remotion. Requires Node.js, Python3, ffmpeg, and cloud GPU access (Modal or RunPod). Claude Code CX Codex Cursor +1 1,100installs bfl-api Black Forest Labs This skill helps connect BFL FLUX API for image generation and editing. It covers async requests, polling, rate limits, and webhooks. Claude Code CX Codex Cursor +1 1,000installs threejs-textures calesthio Skill for working with Three.js textures: image loading, UV coordinates, cubemaps, HDR environments and optimization. Use when building 3D scenes with materials, skyboxes and reflection maps. Claude Code CX Codex Cursor +1 1,000installs

Other versions of text-to-speech

text-to-speech elevenlabs Turns text into speech with ElevenLabs. Use it for voiceovers, audio output, or speech features in an application. Claude Code CX Codex Cursor +1 16,600installs

Similar

manim-video SHL0MS, Hermes Agent Builds Manim CE projects for math, algorithm, and technical animations. Useful when an AI agent needs to turn an explanation into a rendered video. Claude Code CX Codex Cursor +1 455installs ace-step prime-skills Generates music from tags, edits sections of existing tracks, and extends audio through the RunComfy CLI. Use it for instrumentals, vocal songs, and track revisions. Claude Code CX Codex Cursor +1 368,000installs mastra Mastra This skill helps build with Mastra by checking current documentation. Use it to verify APIs, set up TypeScript projects, and investigate errors. Claude Code CX Codex Cursor +1 82,600installs ascii-video SHL0MS, Hermes Agent Converts video, audio, and images into colored ASCII video (MP4, GIF). Supports audio-reactive visualization, generative animation, and text overlays. Claude Code CX Codex Cursor +1 435installs omni-inference cheaper-inference Connects OpenAI-compatible inference endpoints for chat, embeddings, audio, and images. Useful for AI agents calling OmniRoute endpoints. Claude Code CX Codex Cursor +1 1,100installs cli-routing cheaper-inference Manage model routing combos from the command line with omniroute. Test routing strategies, inspect metrics, and configure fallback chains interactively. Claude Code CX Codex Cursor +1 1,100installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs writing-for-agents Matt Pocock Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them. Claude Code 466,719installs

Questions about text-to-speech

How do I install text-to-speech in Claude Code?

Run npx skills add calesthio/OpenMontage --skill text-to-speech -a claude-code, then run the same command again: npx skills add calesthio/OpenMontage --skill text-to-speech -a claude-code. The skill file is placed at ~/.claude/skills/text-to-speech/SKILL.md.

What does text-to-speech do?

It creates speech audio from text with HeyGen Starfish. You can select a voice and set speed, pitch, and locale before receiving the audio file URL.

How is the Starfish voice list different from HeyGen video voices?

Starfish uses GET /v1/audio/voices, while video voices use GET /v2/voices. A video voice is not necessarily compatible with Starfish TTS.

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor