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.
- License 许可
- Apache-2.0
- 最近更新
- 2026-10-13
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- speech
- author
- openai
- 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.
02 资源文件 18
- 参考文档agents/openai.yaml299 B
- 资产文件assets/speech-small.svg742 B
- 资产文件assets/speech.png1.2 KB
- 许可证LICENSE.txt10.5 KB
- 参考文档references/accessibility.md696 B
- 参考文档references/atlas-cloud.md2.4 KB
- 参考文档references/audio-api.md1.0 KB
- 参考文档references/cli.md4.0 KB
- 参考文档references/codex-network.md1.1 KB
- 参考文档references/ivr.md708 B
- 参考文档references/narration.md671 B
- 参考文档references/prompting.md1.5 KB
- 参考文档references/sample-prompts.md991 B
- 参考文档references/voice-directions.md2.1 KB
- 参考文档references/voiceover.md790 B
- 脚本scripts/atlas_text_to_speech.py13.8 KB
- 脚本scripts/text_to_speech.py15.2 KB
- 脚本tests/test_atlas_text_to_speech.py6.6 KB
03 SKILL.md 正文
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
- 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
scripts/text_to_speech.pyfor the default OpenAI path, orscripts/atlas_text_to_speech.pyonly when Atlas Cloud was selected (seereferences/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.
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
--outor--out-dirto control output paths; keep filenames stable and descriptive.
Dependencies (install if missing)
Prefer uv for dependency management.
OpenAI backend package:
uv pip install openai
If uv is unavailable:
python3 -m pip install openai
The Atlas Cloud backend uses only the Python standard library.
Environment
- Default OpenAI calls require
OPENAI_API_KEY. - Optional Atlas Cloud calls require
ATLASCLOUD_API_KEY.
If the selected provider key is missing, give the user these steps:
- Create an API key in that provider's console.
- Set
OPENAI_API_KEYorATLASCLOUD_API_KEYas an environment variable in their system. - Offer to guide them through setting the environment variable for their OS/shell if needed.
- Keep provider credentials out of chat. Direct the user to set the selected key locally and confirm when ready.
If installation isn't possible in this environment, tell the user which dependency is missing and how to install it locally.
Defaults & rules
- Keep OpenAI as the default provider. Do not switch to Atlas Cloud unless the user requests it.
- Use
gpt-4o-mini-tts-2025-12-15unless the user requests another model. - Default voice:
cedar. If the user wants a brighter tone, prefermarin. - Built-in voices only. Custom voices are out of scope for this skill.
instructionsare supported for GPT-4o mini TTS models, but not fortts-1ortts-1-hd.- Input length must be <= 4096 characters per request. Split longer text into chunks.
- Enforce 50 requests/minute. The CLI caps
--rpmat 50. - Require
OPENAI_API_KEYbefore any live API call. - For Atlas Cloud, default to
xai/tts-v1, voiceeve, languageauto, and requireATLASCLOUD_API_KEY. - Atlas generation submits exactly one POST. Only prediction GET requests may retry, and polling must stay finite.
- Download Atlas outputs without an Authorization header and reject non-HTTPS or private-network targets.
- Provide a clear disclosure to end users that the voice is AI-generated.
- Use the OpenAI Python SDK (
openaipackage) for default OpenAI calls; the dedicated Atlas CLI uses its asynchronous HTTP contract. - Prefer the matching bundled CLI over writing new one-off scripts.
Instruction augmentation
Reformat user direction into a short, labeled spec. Only make implicit details explicit; do not invent new requirements.
Quick clarification (augmentation vs invention):
- If the user says "narration for a demo", you may add implied delivery constraints (clear, steady pacing, friendly tone).
- Do not introduce a new persona, accent, or emotional style the user did not request.
Template (include only relevant lines):
Voice Affect: <overall character and texture of the voice>
Tone: <attitude, formality, warmth>
Pacing: <slow, steady, brisk>
Emotion: <key emotions to convey>
Pronunciation: <words to enunciate or emphasize>
Pauses: <where to add intentional pauses>
Emphasis: <key words or phrases to stress>
Delivery: <cadence or rhythm notes>
Augmentation rules:
- Keep it short; add only details the user already implied or provided elsewhere.
- Do not rewrite the input text.
- If any critical detail is missing and blocks success, ask a question; otherwise proceed.
Examples
Single example (narration)
Input text: "Welcome to the demo. Today we'll show how it works."
Instructions:
Voice Affect: Warm and composed.
Tone: Friendly and confident.
Pacing: Steady and moderate.
Emphasis: Stress "demo" and "show".
Batch example (IVR prompts)
{"input":"Thank you for calling. Please hold.","voice":"cedar","response_format":"mp3","out":"hold.mp3"}
{"input":"For sales, press 1. For support, press 2.","voice":"marin","instructions":"Tone: Clear and neutral. Pacing: Slow.","response_format":"wav"}
Instructioning best practices (short list)
- Structure directions as: affect -> tone -> pacing -> emotion -> pronunciation/pauses -> emphasis.
- Keep 4 to 8 short lines; avoid conflicting guidance.
- For names/acronyms, add pronunciation hints (e.g., "enunciate A-I") or supply a phonetic spelling in the text.
- For edits/iterations, repeat invariants (e.g., "keep pacing steady") to reduce drift.
- Iterate with single-change follow-ups.
More principles: references/prompting.md. Copy/paste specs: references/sample-prompts.md.
Guidance by use case
Use these modules when the request is for a specific delivery style. They provide targeted defaults and templates.
- Narration / explainer:
references/narration.md - Product demo / voiceover:
references/voiceover.md - IVR / phone prompts:
references/ivr.md - Accessibility reads:
references/accessibility.md
CLI + environment notes
- CLI commands + examples:
references/cli.md - API parameter quick reference:
references/audio-api.md - Atlas Cloud asynchronous workflow and safeguards:
references/atlas-cloud.md - Instruction patterns + examples:
references/voice-directions.md - If network approvals / sandbox settings are getting in the way:
references/codex-network.md
Reference map
references/cli.md: how to run speech generation/batches viascripts/text_to_speech.py(commands, flags, recipes).references/audio-api.md: API parameters, limits, voice list.references/atlas-cloud.md: optional Atlas Cloud model, CLI, polling, and download contract.references/voice-directions.md: instruction patterns and examples.references/prompting.md: instruction best practices (structure, constraints, iteration patterns).references/sample-prompts.md: copy/paste instruction recipes (examples only; no extra theory).references/narration.md: templates + defaults for narration and explainers.references/voiceover.md: templates + defaults for product demo voiceovers.references/ivr.md: templates + defaults for IVR/phone prompts.references/accessibility.md: templates + defaults for accessibility reads.references/codex-network.md: environment/sandbox/network-approval troubleshooting.
04 同仓库更多 Skills
zapier-make-patterns
No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points. This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power
yeet
Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).
workflow-automation
Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workflows resume exactly where they left off. This skill covers the platforms (n8n, Temporal, Inngest) and patterns (sequential, parallel, orchestrator-worker) that turn brittle scripts into production-grade automation. Key insight: The platforms make different tradeoffs. n8n optimizes for accessibility
trigger-dev
Trigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and TypeScript-first design. Use when: trigger.dev, trigger dev, background task, ai background job, long running task.
slack-automation
Automate Slack workspace operations including messaging, search, channel management, and reaction workflows through Composio's Slack toolkit.
rote
Compile a proven agent skill (a SKILL.md plus references) into a deterministic pipeline that runs without an LLM in the loop, then serve it back to Claude as an MCP tool. Use when: rote, compile this skill, turn this skill into a workflow, make this skill deterministic, make this skill cheaper or faster, harden this skill for production, run this skill as a background job.