AI SummaryGenerates spoken audio from text using OpenAI's TTS API, supporting single clips, batch operations, and accessibility reads. Developers building voiceovers, IVR systems, or accessible content will find this directly useful.
Install
Copy this and paste it into Claude Code, Cursor, or any AI assistant:
I want to install the "speech" skill in my project. Please run this command in my terminal: # Install skill into your project (16 files) mkdir -p .claude/skills/speech && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/speech/SKILL.md "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/speech/SKILL.md" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/speech/LICENSE.txt "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/speech/LICENSE.txt" && mkdir -p .claude/skills/speech/agents && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/speech/agents/openai.yaml "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/speech/agents/openai.yaml" && mkdir -p .claude/skills/speech/assets && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/speech/assets/speech-small.svg "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/speech/assets/speech-small.svg" && mkdir -p .claude/skills/speech/assets && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/speech/assets/speech.png "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/speech/assets/speech.png" && mkdir -p .claude/skills/speech/references && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/speech/references/accessibility.md "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/speech/references/accessibility.md" && mkdir -p .claude/skills/speech/references && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/speech/references/audio-api.md "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/speech/references/audio-api.md" && mkdir -p .claude/skills/speech/references && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/speech/references/cli.md "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/speech/references/cli.md" && mkdir -p .claude/skills/speech/references && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/speech/references/codex-network.md "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/speech/references/codex-network.md" && mkdir -p .claude/skills/speech/references && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/speech/references/ivr.md "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/speech/references/ivr.md" && mkdir -p .claude/skills/speech/references && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/speech/references/narration.md "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/speech/references/narration.md" && mkdir -p .claude/skills/speech/references && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/speech/references/prompting.md "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/speech/references/prompting.md" && mkdir -p .claude/skills/speech/references && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/speech/references/sample-prompts.md "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/speech/references/sample-prompts.md" && mkdir -p .claude/skills/speech/references && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/speech/references/voice-directions.md "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/speech/references/voice-directions.md" && mkdir -p .claude/skills/speech/references && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/speech/references/voiceover.md "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/speech/references/voiceover.md" && mkdir -p .claude/skills/speech/scripts && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/speech/scripts/text_to_speech.py "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/speech/scripts/text_to_speech.py" Then restart Claude Code (or reload the window in Cursor) so the skill is picked up.
Description
Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.
Speech Generation Skill
Generate spoken audio for the current project (narration, product demo voiceover, IVR prompts, accessibility reads). Defaults to gpt-4o-mini-tts-2025-12-15 and built-in voices, and prefers the bundled CLI for deterministic, reproducible runs.
When to use
• Generate a single spoken clip from text • Generate a batch of prompts (many lines, many files)
Decision tree (single vs batch)
• If the user provides multiple lines/prompts or wants many outputs -> batch • Else -> single
Workflow
• Decide intent: single vs batch (see decision tree above). • Collect inputs up front: exact text (verbatim), desired voice, delivery style, format, and any constraints. • If batch: write a temporary JSONL under tmp/ (one job per line), run once, then delete the JSONL. • Augment instructions into a short labeled spec without rewriting the input text. • Run the bundled CLI (scripts/text_to_speech.py) with sensible defaults (see references/cli.md). • For important clips, validate: intelligibility, pacing, pronunciation, and adherence to constraints. • Iterate with a single targeted change (voice, speed, or instructions), then re-check. • Save/return final outputs and note the final text + instructions + flags used.
Discussion
Health Signals
My Fox Den
Community Rating
Sign in to rate this booster