Skill · em Criar imagem, vídeo e arte
speech
Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation. OpenAI remains the default; Atlas Cloud is an explicit optional backend for asynchronous multilingual speech. Custom voice creation is out of scope.
Procedência
- Origem: davila7/claude-code-templates
- Caminho:
cli-tool/components/skills/media/speech - Versão fixada:
57f899e5394bb8ca166f38eacae8f0853cbfe033 - Licença: Apache-2.0
- Espelhado em 25/09/2026
- 4 downloads no Claude Code Templates (lido em 25/09/2026)
Antes de instalar
19 arquivos · 72,2 KB · inclui 3 scripts que executam: scripts/atlas_text_to_speech.py, scripts/text_to_speech.py, tests/test_atlas_text_to_speech.py
Instalar na sua CLI
O comando baixa a versão fixada (commit 57f899e) direto da origem, para a pasta que a CLI lê. Precisa de curl (macOS e Linux); no Windows não há comando, porque o Rook Labs é para macOS.
Claude Code
Neste projeto: instala em .claude/skills/speech/.
d=".claude/skills/speech" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/media/speech" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/agents/openai.yaml" "$u/agents/openai.yaml" \ -o "$d/assets/speech-small.svg" "$u/assets/speech-small.svg" \ -o "$d/assets/speech.png" "$u/assets/speech.png" \ -o "$d/LICENSE.txt" "$u/LICENSE.txt" \ -o "$d/references/accessibility.md" "$u/references/accessibility.md" \ -o "$d/references/atlas-cloud.md" "$u/references/atlas-cloud.md" \ -o "$d/references/audio-api.md" "$u/references/audio-api.md" \ -o "$d/references/cli.md" "$u/references/cli.md" \ -o "$d/references/codex-network.md" "$u/references/codex-network.md" \ -o "$d/references/ivr.md" "$u/references/ivr.md" \ -o "$d/references/narration.md" "$u/references/narration.md" \ -o "$d/references/prompting.md" "$u/references/prompting.md" \ -o "$d/references/sample-prompts.md" "$u/references/sample-prompts.md" \ -o "$d/references/voice-directions.md" "$u/references/voice-directions.md" \ -o "$d/references/voiceover.md" "$u/references/voiceover.md" \ -o "$d/scripts/atlas_text_to_speech.py" "$u/scripts/atlas_text_to_speech.py" \ -o "$d/scripts/text_to_speech.py" "$u/scripts/text_to_speech.py" \ -o "$d/tests/test_atlas_text_to_speech.py" "$u/tests/test_atlas_text_to_speech.py"
Global: instala em ~/.claude/skills/speech/.
d="$HOME/.claude/skills/speech" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/media/speech" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/agents/openai.yaml" "$u/agents/openai.yaml" \ -o "$d/assets/speech-small.svg" "$u/assets/speech-small.svg" \ -o "$d/assets/speech.png" "$u/assets/speech.png" \ -o "$d/LICENSE.txt" "$u/LICENSE.txt" \ -o "$d/references/accessibility.md" "$u/references/accessibility.md" \ -o "$d/references/atlas-cloud.md" "$u/references/atlas-cloud.md" \ -o "$d/references/audio-api.md" "$u/references/audio-api.md" \ -o "$d/references/cli.md" "$u/references/cli.md" \ -o "$d/references/codex-network.md" "$u/references/codex-network.md" \ -o "$d/references/ivr.md" "$u/references/ivr.md" \ -o "$d/references/narration.md" "$u/references/narration.md" \ -o "$d/references/prompting.md" "$u/references/prompting.md" \ -o "$d/references/sample-prompts.md" "$u/references/sample-prompts.md" \ -o "$d/references/voice-directions.md" "$u/references/voice-directions.md" \ -o "$d/references/voiceover.md" "$u/references/voiceover.md" \ -o "$d/scripts/atlas_text_to_speech.py" "$u/scripts/atlas_text_to_speech.py" \ -o "$d/scripts/text_to_speech.py" "$u/scripts/text_to_speech.py" \ -o "$d/tests/test_atlas_text_to_speech.py" "$u/tests/test_atlas_text_to_speech.py"
Codex
Neste projeto: instala em .agents/skills/speech/.
d=".agents/skills/speech" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/media/speech" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/agents/openai.yaml" "$u/agents/openai.yaml" \ -o "$d/assets/speech-small.svg" "$u/assets/speech-small.svg" \ -o "$d/assets/speech.png" "$u/assets/speech.png" \ -o "$d/LICENSE.txt" "$u/LICENSE.txt" \ -o "$d/references/accessibility.md" "$u/references/accessibility.md" \ -o "$d/references/atlas-cloud.md" "$u/references/atlas-cloud.md" \ -o "$d/references/audio-api.md" "$u/references/audio-api.md" \ -o "$d/references/cli.md" "$u/references/cli.md" \ -o "$d/references/codex-network.md" "$u/references/codex-network.md" \ -o "$d/references/ivr.md" "$u/references/ivr.md" \ -o "$d/references/narration.md" "$u/references/narration.md" \ -o "$d/references/prompting.md" "$u/references/prompting.md" \ -o "$d/references/sample-prompts.md" "$u/references/sample-prompts.md" \ -o "$d/references/voice-directions.md" "$u/references/voice-directions.md" \ -o "$d/references/voiceover.md" "$u/references/voiceover.md" \ -o "$d/scripts/atlas_text_to_speech.py" "$u/scripts/atlas_text_to_speech.py" \ -o "$d/scripts/text_to_speech.py" "$u/scripts/text_to_speech.py" \ -o "$d/tests/test_atlas_text_to_speech.py" "$u/tests/test_atlas_text_to_speech.py"
Global: instala em ~/.agents/skills/speech/.
d="$HOME/.agents/skills/speech" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/media/speech" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/agents/openai.yaml" "$u/agents/openai.yaml" \ -o "$d/assets/speech-small.svg" "$u/assets/speech-small.svg" \ -o "$d/assets/speech.png" "$u/assets/speech.png" \ -o "$d/LICENSE.txt" "$u/LICENSE.txt" \ -o "$d/references/accessibility.md" "$u/references/accessibility.md" \ -o "$d/references/atlas-cloud.md" "$u/references/atlas-cloud.md" \ -o "$d/references/audio-api.md" "$u/references/audio-api.md" \ -o "$d/references/cli.md" "$u/references/cli.md" \ -o "$d/references/codex-network.md" "$u/references/codex-network.md" \ -o "$d/references/ivr.md" "$u/references/ivr.md" \ -o "$d/references/narration.md" "$u/references/narration.md" \ -o "$d/references/prompting.md" "$u/references/prompting.md" \ -o "$d/references/sample-prompts.md" "$u/references/sample-prompts.md" \ -o "$d/references/voice-directions.md" "$u/references/voice-directions.md" \ -o "$d/references/voiceover.md" "$u/references/voiceover.md" \ -o "$d/scripts/atlas_text_to_speech.py" "$u/scripts/atlas_text_to_speech.py" \ -o "$d/scripts/text_to_speech.py" "$u/scripts/text_to_speech.py" \ -o "$d/tests/test_atlas_text_to_speech.py" "$u/tests/test_atlas_text_to_speech.py"
Antigravity
Neste projeto: instala em .agents/skills/speech/.
d=".agents/skills/speech" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/media/speech" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/agents/openai.yaml" "$u/agents/openai.yaml" \ -o "$d/assets/speech-small.svg" "$u/assets/speech-small.svg" \ -o "$d/assets/speech.png" "$u/assets/speech.png" \ -o "$d/LICENSE.txt" "$u/LICENSE.txt" \ -o "$d/references/accessibility.md" "$u/references/accessibility.md" \ -o "$d/references/atlas-cloud.md" "$u/references/atlas-cloud.md" \ -o "$d/references/audio-api.md" "$u/references/audio-api.md" \ -o "$d/references/cli.md" "$u/references/cli.md" \ -o "$d/references/codex-network.md" "$u/references/codex-network.md" \ -o "$d/references/ivr.md" "$u/references/ivr.md" \ -o "$d/references/narration.md" "$u/references/narration.md" \ -o "$d/references/prompting.md" "$u/references/prompting.md" \ -o "$d/references/sample-prompts.md" "$u/references/sample-prompts.md" \ -o "$d/references/voice-directions.md" "$u/references/voice-directions.md" \ -o "$d/references/voiceover.md" "$u/references/voiceover.md" \ -o "$d/scripts/atlas_text_to_speech.py" "$u/scripts/atlas_text_to_speech.py" \ -o "$d/scripts/text_to_speech.py" "$u/scripts/text_to_speech.py" \ -o "$d/tests/test_atlas_text_to_speech.py" "$u/tests/test_atlas_text_to_speech.py"
Global: instala em ~/.gemini/antigravity-cli/skills/speech/.
d="$HOME/.gemini/antigravity-cli/skills/speech" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/media/speech" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/agents/openai.yaml" "$u/agents/openai.yaml" \ -o "$d/assets/speech-small.svg" "$u/assets/speech-small.svg" \ -o "$d/assets/speech.png" "$u/assets/speech.png" \ -o "$d/LICENSE.txt" "$u/LICENSE.txt" \ -o "$d/references/accessibility.md" "$u/references/accessibility.md" \ -o "$d/references/atlas-cloud.md" "$u/references/atlas-cloud.md" \ -o "$d/references/audio-api.md" "$u/references/audio-api.md" \ -o "$d/references/cli.md" "$u/references/cli.md" \ -o "$d/references/codex-network.md" "$u/references/codex-network.md" \ -o "$d/references/ivr.md" "$u/references/ivr.md" \ -o "$d/references/narration.md" "$u/references/narration.md" \ -o "$d/references/prompting.md" "$u/references/prompting.md" \ -o "$d/references/sample-prompts.md" "$u/references/sample-prompts.md" \ -o "$d/references/voice-directions.md" "$u/references/voice-directions.md" \ -o "$d/references/voiceover.md" "$u/references/voiceover.md" \ -o "$d/scripts/atlas_text_to_speech.py" "$u/scripts/atlas_text_to_speech.py" \ -o "$d/scripts/text_to_speech.py" "$u/scripts/text_to_speech.py" \ -o "$d/tests/test_atlas_text_to_speech.py" "$u/tests/test_atlas_text_to_speech.py"
Peça ao Rook
Já usa o Rook Labs? Cole no chat do Rook: instale a skill https://rooklabs.sh/marketplace/cct.speech
Prévia do SKILL.md
---
name: "speech"
description: "Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation. OpenAI remains the default; Atlas Cloud is an explicit optional backend for asynchronous multilingual speech. Custom voice creation is out of scope."
author: openai
---
# Speech Generation Skill
Generate spoken audio for the current project (narration, product demo voiceover, IVR prompts, accessibility reads). OpenAI remains the default with `gpt-4o-mini-tts-2025-12-15`; Atlas Cloud is available only when the user explicitly selects it. Prefer the bundled CLIs 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
1. Decide intent: single vs batch (see decision tree above).
2. Collect inputs up front: exact text (verbatim), desired voice, delivery style, format, and any constraints.
3. If batch: write a temporary JSONL under tmp/ (one job per line), run once, then delete the JSONL.
4. Augment instructions into a short labeled spec without rewriting the input text.
5. Run `scripts/text_to_speech.py` for the default OpenAI path, or `scripts/atlas_text_to_speech.py` only when Atlas Cloud was selected (see `references/cli.md`).
6. For important clips, validate: intelligibility, pacing, pronunciation, and adherence to constraints.
7. Iterate with a single targeted change (voice, speed, or instructions), then re-check.
8. Save/return final outputs and note the final text + instructions + flags used.
## Temp and output conventions
- Use `tmp/speech/` for intermediate files (for example JSONL batches); delete when done.
- Write final artifacts under `output/speech/` when working in this repo.
- Use `--out` or `--out-dir` to control output paths; keep filenames stable and descriptive.
## Dependencies (install if missing)
Prefer `uv` for dependency management.
OpenAI backend package:
```
uv pip install openai
…