@khalidsaidi/skillrunner 0.1.1 → 0.1.3

package/dist/registry/skills/openai-speech/SKILL.md

@@ -0,0 +1,159 @@
+---
+name: openai-speech
+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. (Imported from openai upstream skills)"
+version: "1.0.0"
+tags: ["openai", "upstream", "imported"]
+kind: knowledge
+risk: low
+availability: advanced
+docs:
+  source: "https://github.com/openai/skills/tree/main/skills/.curated/speech"
+---
+
+# openai-speech
+
+Imported upstream skill.
+
+- Provider source: https://github.com/openai/skills/tree/main/skills/.curated/speech
+- Original skill name: speech
+
+## Upstream Content
+
+# 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
+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 the bundled CLI (`scripts/text_to_speech.py`) with sensible defaults (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.
+
+Python packages:
+```
+uv pip install openai
+```
+If `uv` is unavailable:
+```
+python3 -m pip install openai
+```
+
+## Environment
+- `OPENAI_API_KEY` must be set for live API calls.
+
+If the key is missing, give the user these steps:
+1. Create an API key in the OpenAI platform UI: https://platform.openai.com/api-keys
+2. Set `OPENAI_API_KEY` as an environment variable in their system.
+3. Offer to guide them through setting the environment variable for their OS/shell if needed.
+- Never ask the user to paste the full key in chat. Ask them to set it 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
+- Use `gpt-4o-mini-tts-2025-12-15` unless the user requests another model.
+- Default voice: `cedar`. If the user wants a brighter tone, prefer `marin`.
+- Built-in voices only. Custom voices are out of scope for this skill.
+- `instructions` are supported for GPT-4o mini TTS models, but not for `tts-1` or `tts-1-hd`.
+- Input length must be <= 4096 characters per request. Split longer text into chunks.
+- Enforce 50 requests/minute. The CLI caps `--rpm` at 50.
+- Require `OPENAI_API_KEY` before any live API call.
+- Provide a clear disclosure to end users that the voice is AI-generated.
+- Use the OpenAI Python SDK (`openai` package) for all API calls; do not use raw HTTP.
+- Prefer the bundled CLI (`scripts/text_to_speech.py`) over writing new one-off scripts.
+- Never modify `scripts/text_to_speech.py`. If something is missing, ask the user before doing anything else.
+
+## 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`
+- 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 via `scripts/text_to_speech.py` (commands, flags, recipes).
+- **`references/audio-api.md`**: API parameters, limits, voice list.
+- **`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.

package/dist/registry/skills/openai-speech/upstream/LICENSE.txt

@@ -0,0 +1,201 @@
+Apache License
+Version 2.0, January 2004
+http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1. Definitions.
+
+   "License" shall mean the terms and conditions for use, reproduction,
+   and distribution as defined by Sections 1 through 9 of this document.
+
+   "Licensor" shall mean the copyright owner or entity authorized by
+   the copyright owner that is granting the License.
+
+   "Legal Entity" shall mean the union of the acting entity and all
+   other entities that control, are controlled by, or are under common
+   control with that entity. For the purposes of this definition,
+   "control" means (i) the power, direct or indirect, to cause the
+   direction or management of such entity, whether by contract or
+   otherwise, or (ii) ownership of fifty percent (50%) or more of the
+   outstanding shares, or (iii) beneficial ownership of such entity.
+
+   "You" (or "Your") shall mean an individual or Legal Entity
+   exercising permissions granted by this License.
+
+   "Source" form shall mean the preferred form for making modifications,
+   including but not limited to software source code, documentation
+   source, and configuration files.
+
+   "Object" form shall mean any form resulting from mechanical
+   transformation or translation of a Source form, including but
+   not limited to compiled object code, generated documentation,
+   and conversions to other media types.
+
+   "Work" shall mean the work of authorship, whether in Source or
+   Object form, made available under the License, as indicated by a
+   copyright notice that is included in or attached to the work
+   (an example is provided in the Appendix below).
+
+   "Derivative Works" shall mean any work, whether in Source or Object
+   form, that is based on (or derived from) the Work and for which the
+   editorial revisions, annotations, elaborations, or other modifications
+   represent, as a whole, an original work of authorship. For the purposes
+   of this License, Derivative Works shall not include works that remain
+   separable from, or merely link (or bind by name) to the interfaces of,
+   the Work and Derivative Works thereof.
+
+   "Contribution" shall mean any work of authorship, including
+   the original version of the Work and any modifications or additions
+   to that Work or Derivative Works thereof, that is intentionally
+   submitted to Licensor for inclusion in the Work by the copyright owner
+   or by an individual or Legal Entity authorized to submit on behalf of
+   the copyright owner. For the purposes of this definition, "submitted"
+   means any form of electronic, verbal, or written communication sent
+   to the Licensor or its representatives, including but not limited to
+   communication on electronic mailing lists, source code control systems,
+   and issue tracking systems that are managed by, or on behalf of, the
+   Licensor for the purpose of discussing and improving the Work, but
+   excluding communication that is conspicuously marked or otherwise
+   designated in writing by the copyright owner as "Not a Contribution."
+
+   "Contributor" shall mean Licensor and any individual or Legal Entity
+   on behalf of whom a Contribution has been received by Licensor and
+   subsequently incorporated within the Work.
+
+2. Grant of Copyright License. Subject to the terms and conditions of
+   this License, each Contributor hereby grants to You a perpetual,
+   worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+   copyright license to reproduce, prepare Derivative Works of,
+   publicly display, publicly perform, sublicense, and distribute the
+   Work and such Derivative Works in Source or Object form.
+
+3. Grant of Patent License. Subject to the terms and conditions of
+   this License, each Contributor hereby grants to You a perpetual,
+   worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+   (except as stated in this section) patent license to make, have made,
+   use, offer to sell, sell, import, and otherwise transfer the Work,
+   where such license applies only to those patent claims licensable
+   by such Contributor that are necessarily infringed by their
+   Contribution(s) alone or by combination of their Contribution(s)
+   with the Work to which such Contribution(s) was submitted. If You
+   institute patent litigation against any entity (including a
+   cross-claim or counterclaim in a lawsuit) alleging that the Work
+   or a Contribution incorporated within the Work constitutes direct
+   or contributory patent infringement, then any patent licenses
+   granted to You under this License for that Work shall terminate
+   as of the date such litigation is filed.
+
+4. Redistribution. You may reproduce and distribute copies of the
+   Work or Derivative Works thereof in any medium, with or without
+   modifications, and in Source or Object form, provided that You
+   meet the following conditions:
+
+   (a) You must give any other recipients of the Work or
+       Derivative Works a copy of this License; and
+
+   (b) You must cause any modified files to carry prominent notices
+       stating that You changed the files; and
+
+   (c) You must retain, in the Source form of any Derivative Works
+       that You distribute, all copyright, patent, trademark, and
+       attribution notices from the Source form of the Work,
+       excluding those notices that do not pertain to any part of
+       the Derivative Works; and
+
+   (d) If the Work includes a "NOTICE" text file as part of its
+       distribution, then any Derivative Works that You distribute must
+       include a readable copy of the attribution notices contained
+       within such NOTICE file, excluding those notices that do not
+       pertain to any part of the Derivative Works, in at least one
+       of the following places: within a NOTICE text file distributed
+       as part of the Derivative Works; within the Source form or
+       documentation, if provided along with the Derivative Works; or,
+       within a display generated by the Derivative Works, if and
+       wherever such third-party notices normally appear. The contents
+       of the NOTICE file are for informational purposes only and
+       do not modify the License. You may add Your own attribution
+       notices within Derivative Works that You distribute, alongside
+       or as an addendum to the NOTICE text from the Work, provided
+       that such additional attribution notices cannot be construed
+       as modifying the License.
+
+   You may add Your own copyright statement to Your modifications and
+   may provide additional or different license terms and conditions
+   for use, reproduction, or distribution of Your modifications, or
+   for any such Derivative Works as a whole, provided Your use,
+   reproduction, and distribution of the Work otherwise complies with
+   the conditions stated in this License.
+
+5. Submission of Contributions. Unless You explicitly state otherwise,
+   any Contribution intentionally submitted for inclusion in the Work
+   by You to the Licensor shall be under the terms and conditions of
+   this License, without any additional terms or conditions.
+   Notwithstanding the above, nothing herein shall supersede or modify
+   the terms of any separate license agreement you may have executed
+   with Licensor regarding such Contributions.
+
+6. Trademarks. This License does not grant permission to use the trade
+   names, trademarks, service marks, or product names of the Licensor,
+   except as required for reasonable and customary use in describing the
+   origin of the Work and reproducing the content of the NOTICE file.
+
+7. Disclaimer of Warranty. Unless required by applicable law or
+   agreed to in writing, Licensor provides the Work (and each
+   Contributor provides its Contributions) on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+   implied, including, without limitation, any warranties or conditions
+   of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+   PARTICULAR PURPOSE. You are solely responsible for determining the
+   appropriateness of using or redistributing the Work and assume any
+   risks associated with Your exercise of permissions under this License.
+
+8. Limitation of Liability. In no event and under no legal theory,
+   whether in tort (including negligence), contract, or otherwise,
+   unless required by applicable law (such as deliberate and grossly
+   negligent acts) or agreed to in writing, shall any Contributor be
+   liable to You for damages, including any direct, indirect, special,
+   incidental, or consequential damages of any character arising as a
+   result of this License or out of the use or inability to use the
+   Work (including but not limited to damages for loss of goodwill,
+   work stoppage, computer failure or malfunction, or any and all
+   other commercial damages or losses), even if such Contributor
+   has been advised of the possibility of such damages.
+
+9. Accepting Warranty or Additional Liability. While redistributing
+   the Work or Derivative Works thereof, You may choose to offer,
+   and charge a fee for, acceptance of support, warranty, indemnity,
+   or other liability obligations and/or rights consistent with this
+   License. However, in accepting such obligations, You may act only
+   on Your own behalf and on Your sole responsibility, not on behalf of
+   any other Contributor, and only if You agree to indemnify,
+   defend, and hold each Contributor harmless for any liability
+   incurred by, or claims asserted against, such Contributor by reason
+   of your accepting any such warranty or additional liability.
+
+END OF TERMS AND CONDITIONS
+
+APPENDIX: How to apply the Apache License to your work.
+
+   To apply the Apache License to your work, attach the following
+   boilerplate notice, with the fields enclosed by brackets "[]"
+   replaced with your own identifying information. (Don\'t include
+   the brackets!)  The text should be enclosed in the appropriate
+   comment syntax for the file format. We also recommend that a
+   file or class name and description of purpose be included on the
+   same "printed page" as the copyright notice for easier
+   identification within third-party archives.
+
+Copyright [yyyy] [name of copyright owner]
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

package/dist/registry/skills/openai-speech/upstream/SKILL.md

@@ -0,0 +1,144 @@
+---
+name: "speech"
+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
+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 the bundled CLI (`scripts/text_to_speech.py`) with sensible defaults (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.
+
+Python packages:
+```
+uv pip install openai
+```
+If `uv` is unavailable:
+```
+python3 -m pip install openai
+```
+
+## Environment
+- `OPENAI_API_KEY` must be set for live API calls.
+
+If the key is missing, give the user these steps:
+1. Create an API key in the OpenAI platform UI: https://platform.openai.com/api-keys
+2. Set `OPENAI_API_KEY` as an environment variable in their system.
+3. Offer to guide them through setting the environment variable for their OS/shell if needed.
+- Never ask the user to paste the full key in chat. Ask them to set it 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
+- Use `gpt-4o-mini-tts-2025-12-15` unless the user requests another model.
+- Default voice: `cedar`. If the user wants a brighter tone, prefer `marin`.
+- Built-in voices only. Custom voices are out of scope for this skill.
+- `instructions` are supported for GPT-4o mini TTS models, but not for `tts-1` or `tts-1-hd`.
+- Input length must be <= 4096 characters per request. Split longer text into chunks.
+- Enforce 50 requests/minute. The CLI caps `--rpm` at 50.
+- Require `OPENAI_API_KEY` before any live API call.
+- Provide a clear disclosure to end users that the voice is AI-generated.
+- Use the OpenAI Python SDK (`openai` package) for all API calls; do not use raw HTTP.
+- Prefer the bundled CLI (`scripts/text_to_speech.py`) over writing new one-off scripts.
+- Never modify `scripts/text_to_speech.py`. If something is missing, ask the user before doing anything else.
+
+## 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`
+- 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 via `scripts/text_to_speech.py` (commands, flags, recipes).
+- **`references/audio-api.md`**: API parameters, limits, voice list.
+- **`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.

package/dist/registry/skills/openai-speech/upstream/agents/openai.yaml

@@ -0,0 +1,6 @@
+interface:
+  display_name: "Speech Generation Skill"
+  short_description: "Generate narrated audio from text"
+  icon_small: "./assets/speech-small.svg"
+  icon_large: "./assets/speech.png"
+  default_prompt: "Generate spoken audio for this text with the right voice style, pacing, and output format."

package/dist/registry/skills/openai-speech/upstream/assets/speech-small.svg

@@ -0,0 +1,3 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" viewBox="0 0 14 14">
+  <path d="M7.78 4.001c.245 0 .444.199.444.444v6.666a.444.444 0 0 1-.887 0V4.445c0-.245.199-.444.444-.444ZM5.836 7.89c.245 0 .443.199.443.443v1.112a.444.444 0 0 1-.886 0V8.333c0-.244.198-.443.443-.443Zm3.889-2.222c.244 0 .443.199.443.443v3.334a.444.444 0 0 1-.887 0V6.11c0-.244.199-.443.444-.443ZM11.67 6.78c.244 0 .443.198.443.443v1.11a.444.444 0 0 1-.887 0v-1.11c0-.245.198-.444.443-.444ZM6.114 1.779c.245 0 .443.198.443.443v.988a.444.444 0 0 1-.886 0v-.545H4.335v3.558h.297l.09.01a.444.444 0 0 1 0 .868l-.09.009h-1.48a.444.444 0 0 1-.001-.887h.297V2.665H2.113v.545a.444.444 0 0 1-.887 0v-.988c0-.245.199-.443.443-.443h4.445Z"/>
+</svg>

package/dist/registry/skills/openai-speech/upstream/references/accessibility.md

@@ -0,0 +1,32 @@
+# Accessibility read defaults
+
+## Suggested defaults
+- Voice: `cedar`
+- Format: `mp3` or `wav`
+- Speed: `0.95` to `1.0`
+
+## Guidance
+- Keep delivery steady and neutral.
+- Enunciate acronyms and numbers.
+- Avoid dramatic or stylized delivery.
+
+## Instruction template
+```
+Voice Affect: Neutral and clear.
+Tone: Informational and steady.
+Pacing: Slow and consistent.
+Pronunciation: Enunciate acronyms and numbers.
+Emphasis: Stress key warnings or labels.
+```
+
+## Example (short)
+Input text:
+"Warning: High voltage. Keep hands clear."
+
+Instructions:
+```
+Voice Affect: Neutral and clear.
+Tone: Informational and steady.
+Pacing: Slow and consistent.
+Emphasis: Stress "Warning" and "High voltage".
+```

package/dist/registry/skills/openai-speech/upstream/references/audio-api.md

@@ -0,0 +1,31 @@
+# Audio Speech API quick reference
+
+## Endpoint
+- Create speech: `POST /v1/audio/speech`
+
+## Default model
+- `gpt-4o-mini-tts-2025-12-15`
+
+## Other speech models (if requested)
+- `gpt-4o-mini-tts`
+- `tts-1`
+- `tts-1-hd`
+
+## Core parameters
+- `model`: speech model
+- `input`: text to synthesize (max 4096 characters)
+- `voice`: built-in voice name
+- `instructions`: optional style directions (not supported for `tts-1` or `tts-1-hd`)
+- `response_format`: `mp3`, `opus`, `aac`, `flac`, `wav`, or `pcm`
+- `speed`: 0.25 to 4.0
+
+## Built-in voices
+- `alloy`, `ash`, `ballad`, `cedar`, `coral`, `echo`, `fable`, `marin`, `nova`, `onyx`, `sage`, `shimmer`, `verse`
+
+## Output notes
+- Default format is `mp3`.
+- `pcm` is raw 24 kHz 16-bit little-endian samples (no header).
+- `wav` includes a header (better for quick playback).
+
+## Compliance note
+- Provide a clear disclosure that the voice is AI-generated.