← Creative ClawCONTENT HISTORY

Update to Creative Claw

Snapshot Nov 20, 2026 · 00:10 UTC · version 5.7.3

Collection source: downloaded plugin package.

WHAT CHANGED

Instructions updated for creativeclaw-clone-voice

Skill instructions — Now says: give the user the click path: open the [Creative Claw plugin...

Observed in instructions or declared skills. Runtime behavior has not been tested.

Save Creative Claw and check future changes in Following.

Up to 3 plugins free · no card required.

All fields and original values.

Skill instructions

Before

Oct 24, 2026 · 12:48 UTC

tell the user to open the plugin's Connectors tab in their app (or the MCP server list in a terminal client), connect Creative Claw, sign in, and ask again. Do not substitute other tools or describe a result that was not generated. Ask t...

After

Nov 20, 2026 · 00:10 UTC

give the user the click path: open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude, then the **Connectors** tab, press **Conne...

Supporting files

Before

Oct 24, 2026 · 12:48 UTC

[{"relative_path":"agents/openai.yaml","size_in_bytes":507},{"relative_path":"references/job-recovery.md","size_in_bytes":3786},{"relative_path":"references/media-assembly.md","size_in_bytes":8654},{"relative_path":"references/platform-u...

After

Nov 20, 2026 · 00:10 UTC

[{"relative_path":"agents/openai.yaml","size_in_bytes":507},{"relative_path":"references/job-recovery.md","size_in_bytes":3774},{"relative_path":"references/media-assembly.md","size_in_bytes":11689},{"relative_path":"references/platform-...

Compare saved observations

Download comparison JSON

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -7,24 +7,38 @@
 
 For each Creative Claw tool call that exposes it, pass the optional `skills_used` array with `creativeclaw-clone-voice`, any other Creative Claw skills actually followed, and guide entries in the form `<skill-name>/<relative-guide-path>` (for example, `creativeclaw-clone-voice/references/workflow-basics.md`). Include only skills and guides followed for that call. Omit attribution if the user declines tracking or the field is unavailable. Never send other plugin names, private data, or local paths.
 
-**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and tell the user to open the plugin's Connectors tab in their app (or the MCP server list in a terminal client), connect Creative Claw, sign in, and ask again. Do not substitute other tools or describe a result that was not generated.
+**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude, then the **Connectors** tab, press **Connect**, press **Add** if an "Add custom connector" dialog opens, and sign in. In Claude Code they run `/mcp` instead. Then they ask again. Do not substitute other tools or describe a result that was not generated.
 
 Read [shared execution guidance](references/workflow-basics.md) before tools and [recording, upload, consent and reuse](references/voices/cloning.md) for this workflow.
 
-Ask the user for a recording of at least one minute of clean solo speech, upload it privately, clone it, audition a short sample, and reuse the saved Character. One to two minutes is our onboarding recommendation, not a universal provider API minimum.
-
 Clone only the user's own voice, or a voice whose speaker has given explicit permission. Do not clone a public figure or anyone else without their permission. Without a consented recording, offer design_voice instead ([voice design](references/voices/voice-design.md)).
 
+## Default: the voice card
+
+When the user wants to clone their voice and hasn't given you an audio file, call `clone_voice` without audio and without `consent`: `clone_voice({ language })` when you know the language, plus `character_id` when the voice belongs on an existing Character. Provide `consent` only together with an audio file. Leave out `provider`. Its result is the voice card.
+
+The card does the whole flow: the consent agreement, a one-minute reading script in the user's language (or an uploaded file), the clone on Cartesia, a test line, an optional blind comparison with ElevenLabs and Fish Audio, and saving the voice as a new Character or on one of the user's Characters. It also shows plan and voice-limit messages before anyone records.
+
+- Don't ask for consent or a recording in chat first, and don't send the user to record with another app or a command line; the card collects both.
+- Don't call `clone_voice` for a recording made in the card. Wait for the card's note, which gives the `character_id` and the model to use.
+- Where the host gives the card no microphone, the card offers upload and recording on a phone or in the browser. Nothing to do in chat.
+- If no card shows, the result is `status: "awaiting_sample"` (for example in a terminal) or, from a server without the card, `reason: "voice_sample_not_provided"`. Nothing was charged. Follow its `recoveryOptions` through the file route below.
+
+## When the user already has a recording
+
+For an attached file, a local file or a link:
+
 1. Identify the intended delivery and an existing Character, if any. Reuse an avatar's Character instead of creating a duplicate.
-2. Ask for consent once, up front, in the same message as the recording request: name the provider, quote the full consent statement with its terms and privacy links from [the reference](references/voices/cloning.md), and ask for the recording's language. One "I agree" plus the language covers both. Possessing a recording is not consent.
+2. Ask for consent once, up front: name the provider, quote the full consent statement with its terms and privacy links from [the reference](references/voices/cloning.md), and ask for the recording's language. One "I agree" plus the language covers both. Possessing a recording is not consent.
 3. Import with purpose `voice_clone` to obtain a private `audio_asset_id`. Follow the reference for the current client's upload route.
-4. As soon as the upload returns, call `clone_voice` with that asset, `consent: true`, the recording's `language` code (for example `he`; it defaults to `en`), and `provider: "cartesia"` (the default), or `provider: "elevenlabs"` when the user chooses ElevenLabs. Do not ask for consent or confirmation again: the step 2 agreement is the explicit consent the upload result mentions. Use `character_id` for an existing Character or `character_name` for a new voice-only Character. The tool saves the clone automatically.
-5. Audition using `generate_speech` and the returned `character_id`. Read the selected model reference below. Include a name, number and natural sentence in the intended language. Present the audio for approval before a longer production.
-6. Reuse `character_id`, not the private source recording, for future speech. Never replace a saved voice merely to change speech models.
+4. As soon as the upload returns, call `clone_voice` with that asset, `consent: true`, the recording's `language` code (for example `he`; it defaults to `en`), and `provider: "cartesia"` (the default), or `provider: "elevenlabs"` when the user chooses ElevenLabs. Do not ask for consent or confirmation again. Use `character_id` for an existing Character or `character_name` for a new voice-only Character. The tool saves the clone automatically.
+5. Audition using `generate_speech` and the returned `character_id`. Include a name, number and natural sentence in the intended language. Present the audio for approval before a longer production. If the user says a word sounds wrong (the stress, an acronym, a homograph or a loanword), fix only that word as [pronunciation](references/voices/pronunciation.md) describes and regenerate before suggesting feedback.
+
+Reuse `character_id`, not the private source recording, for future speech. Never replace a saved voice merely to change speech models.
 
 ## Choose the synthesis model
 
-Speak a clone with its provider's model, and pass the model explicitly.
+Each clone saves its engine on the Character: the clone's own provider, or the one the user picked in the card. `generate_speech` with that `character_id` and no `model` uses it. Set `model` only to override it, using the matching guide:
 
 - [Cartesia Sonic](references/voices/cartesia.md): a Cartesia clone.
 - [ElevenLabs v2](references/voices/elevenlabs-v2.md): an ElevenLabs clone, steady read in its supported languages.
Full technical diff · 2 changed fields

changed /included_files

BEFORE
[
  {
    "relative_path": "agents/openai.yaml",
    "size_in_bytes": 507
  },
  {
    "relative_path": "references/job-recovery.md",
    "size_in_bytes": 3786
  },
  {
    "relative_path": "references/media-assembly.md",
    "size_in_bytes": 8654
  },
  {
    "relative_path": "references/platform-upload.md",
    "size_in_bytes": 1416
  },
  {
    "relative_path": "references/voices/alternatives.md",
    "size_in_bytes": 1943
  },
  {
    "relative_path": "references/voices/cartesia-sonic-guide.md",
    "size_in_bytes": 5002
  },
  {
    "relative_path": "references/voices/cartesia.md",
    "size_in_bytes": 2238
  },
  {
    "relative_path": "references/voices/chatterbox-guide.md",
    "size_in_bytes": 3509
  },
  {
    "relative_path": "references/voices/cloning.md",
    "size_in_bytes": 6290
  },
  {
    "relative_path": "references/voices/elevenlabs-v2-guide.md",
    "size_in_bytes": 8079
  },
  {
    "relative_path": "references/voices/elevenlabs-v2.md",
    "size_in_bytes": 1786
  },
  {
    "relative_path": "references/voices/elevenlabs-v3-guide.md",
    "size_in_bytes": 9376
  },
  {
    "relative_path": "references/voices/elevenlabs-v3.md",
    "size_in_bytes": 1935
  },
  {
    "relative_path": "references/voices/elevenlabs-v4-guide.md",
    "size_in_bytes": 8693
  },
  {
    "relative_path": "references/voices/elevenlabs-v4.md",
    "size_in_bytes": 2069
  },
  {
    "relative_path": "references/voices/fish.md",
    "size_in_bytes": 17534
  },
  {
    "relative_path": "references/voices/heygen.md",
    "size_in_bytes": 3560
  },
  {
    "relative_path": "references/voices/languages.md",
    "size_in_bytes": 4133
  },
  {
    "relative_path": "references/voices/minimax-speech-guide.md",
    "size_in_bytes": 3490
  },
  {
    "relative_path": "references/voices/speech-localization.md",
    "size_in_bytes": 3869
  },
  {
    "relative_path": "references/voices/voice-design.md",
    "size_in_bytes": 3897
  },
  {
    "relative_path": "references/voices/xai-tts-guide.md",
    "size_in_bytes": 11591
  },
  {
    "relative_path": "references/workflow-basics.md",
    "size_in_bytes": 10396
  }
]
AFTER
[
  {
    "relative_path": "agents/openai.yaml",
    "size_in_bytes": 507
  },
  {
    "relative_path": "references/job-recovery.md",
    "size_in_bytes": 3774
  },
  {
    "relative_path": "references/media-assembly.md",
    "size_in_bytes": 11689
  },
  {
    "relative_path": "references/platform-upload.md",
    "size_in_bytes": 1416
  },
  {
    "relative_path": "references/voices/alternatives.md",
    "size_in_bytes": 1943
  },
  {
    "relative_path": "references/voices/cartesia-sonic-guide.md",
    "size_in_bytes": 5002
  },
  {
    "relative_path": "references/voices/cartesia.md",
    "size_in_bytes": 2238
  },
  {
    "relative_path": "references/voices/chatterbox-guide.md",
    "size_in_bytes": 3509
  },
  {
    "relative_path": "references/voices/cloning.md",
    "size_in_bytes": 7929
  },
  {
    "relative_path": "references/voices/elevenlabs-v2-guide.md",
    "size_in_bytes": 8079
  },
  {
    "relative_path": "references/voices/elevenlabs-v2.md",
    "size_in_bytes": 1786
  },
  {
    "relative_path": "references/voices/elevenlabs-v3-guide.md",
    "size_in_bytes": 9262
  },
  {
    "relative_path": "references/voices/elevenlabs-v3.md",
    "size_in_bytes": 1935
  },
  {
    "relative_path": "references/voices/elevenlabs-v4-guide.md",
    "size_in_bytes": 8696
  },
  {
    "relative_path": "references/voices/elevenlabs-v4.md",
    "size_in_bytes": 2078
  },
  {
    "relative_path": "references/voices/fish.md",
    "size_in_bytes": 17618
  },
  {
    "relative_path": "references/voices/heygen.md",
    "size_in_bytes": 3574
  },
  {
    "relative_path": "references/voices/languages.md",
    "size_in_bytes": 4622
  },
  {
    "relative_path": "references/voices/minimax-speech-guide.md",
    "size_in_bytes": 3490
  },
  {
    "relative_path": "references/voices/pronunciation.md",
    "size_in_bytes": 9162
  },
  {
    "relative_path": "references/voices/speech-localization.md",
    "size_in_bytes": 5972
  },
  {
    "relative_path": "references/voices/voice-design.md",
    "size_in_bytes": 4873
  },
  {
    "relative_path": "references/voices/xai-tts-guide.md",
    "size_in_bytes": 11450
  },
  {
    "relative_path": "references/workflow-basics.md",
    "size_in_bytes": 10299
  }
]

changed /skill_md_contents

BEFORE
"---\nname: creativeclaw-clone-voice\ndescription: Guide recording, private upload, cloning, testing, and reuse of a consented personal voice with Cartesia or ElevenLabs. Use when someone asks to clone their voice, save it on a Character, or replace or audition a clone. Not for inventing a new voice from a description; use creativeclaw-generate-voiceover.\n---\n\n# Clone your voice\n\nFor each Creative Claw tool call that exposes it, pass the optional `skills_used` array with `creativeclaw-clone-voice`, any other Creative Claw skills actually followed, and guide entries in the form `<skill-name>/<relative-guide-path>` (for example, `creativeclaw-clone-voice/references/workflow-basics.md`). Include only skills and guides followed for that call. Omit attribution if the user declines tracking or the field is unavailable. Never send other plugin names, private data, or local paths.\n\n**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and tell the user to open the plugin's Connectors tab in their app (or the MCP server list in a terminal client), connect Creative Claw, sign in, and ask again. Do not substitute other tools or describe a result that was not generated.\n\nRead [shared execution guidance](references/workflow-basics.md) before tools and [recording, upload, consent and reuse](references/voices/cloning.md) for this workflow.\n\nAsk the user for a recording of at least one minute of clean solo speech, upload it privately, clone it, audition a short sample, and reuse the saved Character. One to two minutes is our onboarding recommendation, not a universal provider API minimum.\n\nClone only the user's own voice, or a voice whose speaker has given explicit permission. Do not clone a public figure or anyone else without their permission. Without a consented recording, offer design_voice instead ([voice design](references/voices/voice-design.md)).\n\n1. Identify the intended delivery and an existing Character, if any. Reuse an avatar's Character instead of creating a duplicate.\n2. Ask for consent once, up front, in the same message as the recording request: name the provider, quote the full consent statement with its terms and privacy links from [the reference](references/voices/cloning.md), and ask for the recording's language. One \"I agree\" plus the language covers both. Possessing a recording is not consent.\n3. Import with purpose `voice_clone` to obtain a private `audio_asset_id`. Follow the reference for the current client's upload route.\n4. As soon as the upload returns, call `clone_voice` with that asset, `consent: true`, the recording's `language` code (for example `he`; it defaults to `en`), and `provider: \"cartesia\"` (the default), or `provider: \"elevenlabs\"` when the user chooses ElevenLabs. Do not ask for consent or confirmation again: the step 2 agreement is the explicit consent the upload result mentions. Use `character_id` for an existing Character or `character_name` for a new voice-only Character. The tool saves the clone automatically.\n5. Audition using `generate_speech` and the returned `character_id`. Read the selected model reference below. Include a name, number and natural sentence in the intended language. Present the audio for approval before a longer production.\n6. Reuse `character_id`, not the private source recording, for future speech. Never replace a saved voice merely to change speech models.\n\n## Choose the synthesis model\n\nSpeak a clone with its provider's model, and pass the model explicitly.\n\n- [Cartesia Sonic](references/voices/cartesia.md): a Cartesia clone.\n- [ElevenLabs v2](references/voices/elevenlabs-v2.md): an ElevenLabs clone, steady read in its supported languages.\n- [ElevenLabs v4](references/voices/elevenlabs-v4.md): an ElevenLabs clone, expressive delivery or dialogue, and languages v2 lacks.\n- [Language routing](references/voices/languages.md): read for non-English speech, dialect requests, or mixed-language scripts.\n\nOnly change provider when the user chooses it. A missing Cartesia clone can be created from the retained consented sample when Cartesia is selected. Replacing the source invalidates both providers' clones, so explain and confirm replacement first. Do not silently substitute a stock voice after a clone fails.\n\nFor a Fish clone, use `provider: \"fish\"` with the private recording and existing consent. Speak with `speech/fish-drama-3`. Read [Fish guidance](references/voices/fish.md) and current `get_model_params`. Selecting Fish for an existing consented Character can create a missing private Fish copy without replacing its other provider copies.\n"
AFTER
"---\nname: creativeclaw-clone-voice\ndescription: Guide recording, private upload, cloning, testing, and reuse of a consented personal voice with Cartesia or ElevenLabs. Use when someone asks to clone their voice, save it on a Character, or replace or audition a clone. Not for inventing a new voice from a description; use creativeclaw-generate-voiceover.\n---\n\n# Clone your voice\n\nFor each Creative Claw tool call that exposes it, pass the optional `skills_used` array with `creativeclaw-clone-voice`, any other Creative Claw skills actually followed, and guide entries in the form `<skill-name>/<relative-guide-path>` (for example, `creativeclaw-clone-voice/references/workflow-basics.md`). Include only skills and guides followed for that call. Omit attribution if the user declines tracking or the field is unavailable. Never send other plugin names, private data, or local paths.\n\n**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude, then the **Connectors** tab, press **Connect**, press **Add** if an \"Add custom connector\" dialog opens, and sign in. In Claude Code they run `/mcp` instead. Then they ask again. Do not substitute other tools or describe a result that was not generated.\n\nRead [shared execution guidance](references/workflow-basics.md) before tools and [recording, upload, consent and reuse](references/voices/cloning.md) for this workflow.\n\nClone only the user's own voice, or a voice whose speaker has given explicit permission. Do not clone a public figure or anyone else without their permission. Without a consented recording, offer design_voice instead ([voice design](references/voices/voice-design.md)).\n\n## Default: the voice card\n\nWhen the user wants to clone their voice and hasn't given you an audio file, call `clone_voice` without audio and without `consent`: `clone_voice({ language })` when you know the language, plus `character_id` when the voice belongs on an existing Character. Provide `consent` only together with an audio file. Leave out `provider`. Its result is the voice card.\n\nThe card does the whole flow: the consent agreement, a one-minute reading script in the user's language (or an uploaded file), the clone on Cartesia, a test line, an optional blind comparison with ElevenLabs and Fish Audio, and saving the voice as a new Character or on one of the user's Characters. It also shows plan and voice-limit messages before anyone records.\n\n- Don't ask for consent or a recording in chat first, and don't send the user to record with another app or a command line; the card collects both.\n- Don't call `clone_voice` for a recording made in the card. Wait for the card's note, which gives the `character_id` and the model to use.\n- Where the host gives the card no microphone, the card offers upload and recording on a phone or in the browser. Nothing to do in chat.\n- If no card shows, the result is `status: \"awaiting_sample\"` (for example in a terminal) or, from a server without the card, `reason: \"voice_sample_not_provided\"`. Nothing was charged. Follow its `recoveryOptions` through the file route below.\n\n## When the user already has a recording\n\nFor an attached file, a local file or a link:\n\n1. Identify the intended delivery and an existing Character, if any. Reuse an avatar's Character instead of creating a duplicate.\n2. Ask for consent once, up front: name the provider, quote the full consent statement with its terms and privacy links from [the reference](references/voices/cloning.md), and ask for the recording's language. One \"I agree\" plus the language covers both. Possessing a recording is not consent.\n3. Import with purpose `voice_clone` to obtain a private `audio_asset_id`. Follow the reference for the current client's upload route.\n4. As soon as the upload returns, call `clone_voice` with that asset, `consent: true`, the recording's `language` code (for example `he`; it defaults to `en`), and `provider: \"cartesia\"` (the default), or `provider: \"elevenlabs\"` when the user chooses ElevenLabs. Do not ask for consent or confirmation again. Use `character_id` for an existing Character or `character_name` for a new voice-only Character. The tool saves the clone automatically.\n5. Audition using `generate_speech` and the returned `character_id`. Include a name, number and natural sentence in the intended language. Present the audio for approval before a longer production. If the user says a word sounds wrong (the stress, an acronym, a homograph or a loanword), fix only that word as [pronunciation](references/voices/pronunciation.md) describes and regenerate before suggesting feedback.\n\nReuse `character_id`, not the private source recording, for future speech. Never replace a saved voice merely to change speech models.\n\n## Choose the synthesis model\n\nEach clone saves its engine on the Character: the clone's own provider, or the one the user picked in the card. `generate_speech` with that `character_id` and no `model` uses it. Set `model` only to override it, using the matching guide:\n\n- [Cartesia Sonic](references/voices/cartesia.md): a Cartesia clone.\n- [ElevenLabs v2](references/voices/elevenlabs-v2.md): an ElevenLabs clone, steady read in its supported languages.\n- [ElevenLabs v4](references/voices/elevenlabs-v4.md): an ElevenLabs clone, expressive delivery or dialogue, and languages v2 lacks.\n- [Language routing](references/voices/languages.md): read for non-English speech, dialect requests, or mixed-language scripts.\n\nOnly change provider when the user chooses it. A missing Cartesia clone can be created from the retained consented sample when Cartesia is selected. Replacing the source invalidates both providers' clones, so explain and confirm replacement first. Do not silently substitute a stock voice after a clone fails.\n\nFor a Fish clone, use `provider: \"fish\"` with the private recording and existing consent. Speak with `speech/fish-drama-3`. Read [Fish guidance](references/voices/fish.md) and current `get_model_params`. Selecting Fish for an existing consented Character can create a missing private Fish copy without replacing its other provider copies.\n"
Full snapshot data
{
  "description": "Guide recording, private upload, cloning, testing, and reuse of a consented personal voice with Cartesia or ElevenLabs. Use when someone asks to clone their voice, save it on a Character, or replace or audition a clone. Not for inventing a new voice from a description; use creativeclaw-generate-voiceover.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 507
    },
    {
      "relative_path": "references/job-recovery.md",
      "size_in_bytes": 3774
    },
    {
      "relative_path": "references/media-assembly.md",
      "size_in_bytes": 11689
    },
    {
      "relative_path": "references/platform-upload.md",
      "size_in_bytes": 1416
    },
    {
      "relative_path": "references/voices/alternatives.md",
      "size_in_bytes": 1943
    },
    {
      "relative_path": "references/voices/cartesia-sonic-guide.md",
      "size_in_bytes": 5002
    },
    {
      "relative_path": "references/voices/cartesia.md",
      "size_in_bytes": 2238
    },
    {
      "relative_path": "references/voices/chatterbox-guide.md",
      "size_in_bytes": 3509
    },
    {
      "relative_path": "references/voices/cloning.md",
      "size_in_bytes": 7929
    },
    {
      "relative_path": "references/voices/elevenlabs-v2-guide.md",
      "size_in_bytes": 8079
    },
    {
      "relative_path": "references/voices/elevenlabs-v2.md",
      "size_in_bytes": 1786
    },
    {
      "relative_path": "references/voices/elevenlabs-v3-guide.md",
      "size_in_bytes": 9262
    },
    {
      "relative_path": "references/voices/elevenlabs-v3.md",
      "size_in_bytes": 1935
    },
    {
      "relative_path": "references/voices/elevenlabs-v4-guide.md",
      "size_in_bytes": 8696
    },
    {
      "relative_path": "references/voices/elevenlabs-v4.md",
      "size_in_bytes": 2078
    },
    {
      "relative_path": "references/voices/fish.md",
      "size_in_bytes": 17618
    },
    {
      "relative_path": "references/voices/heygen.md",
      "size_in_bytes": 3574
    },
    {
      "relative_path": "references/voices/languages.md",
      "size_in_bytes": 4622
    },
    {
      "relative_path": "references/voices/minimax-speech-guide.md",
      "size_in_bytes": 3490
    },
    {
      "relative_path": "references/voices/pronunciation.md",
      "size_in_bytes": 9162
    },
    {
      "relative_path": "references/voices/speech-localization.md",
      "size_in_bytes": 5972
    },
    {
      "relative_path": "references/voices/voice-design.md",
      "size_in_bytes": 4873
    },
    {
      "relative_path": "references/voices/xai-tts-guide.md",
      "size_in_bytes": 11450
    },
    {
      "relative_path": "references/workflow-basics.md",
      "size_in_bytes": 10299
    }
  ],
  "name": "creativeclaw-clone-voice",
  "skill_md_contents": "---\nname: creativeclaw-clone-voice\ndescription: Guide recording, private upload, cloning, testing, and reuse of a consented personal voice with Cartesia or ElevenLabs. Use when someone asks to clone their voice, save it on a Character, or replace or audition a clone. Not for inventing a new voice from a description; use creativeclaw-generate-voiceover.\n---\n\n# Clone your voice\n\nFor each Creative Claw tool call that exposes it, pass the optional `skills_used` array with `creativeclaw-clone-voice`, any other Creative Claw skills actually followed, and guide entries in the form `<skill-name>/<relative-guide-path>` (for example, `creativeclaw-clone-voice/references/workflow-basics.md`). Include only skills and guides followed for that call. Omit attribution if the user declines tracking or the field is unavailable. Never send other plugin names, private data, or local paths.\n\n**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude, then the **Connectors** tab, press **Connect**, press **Add** if an \"Add custom connector\" dialog opens, and sign in. In Claude Code they run `/mcp` instead. Then they ask again. Do not substitute other tools or describe a result that was not generated.\n\nRead [shared execution guidance](references/workflow-basics.md) before tools and [recording, upload, consent and reuse](references/voices/cloning.md) for this workflow.\n\nClone only the user's own voice, or a voice whose speaker has given explicit permission. Do not clone a public figure or anyone else without their permission. Without a consented recording, offer design_voice instead ([voice design](references/voices/voice-design.md)).\n\n## Default: the voice card\n\nWhen the user wants to clone their voice and hasn't given you an audio file, call `clone_voice` without audio and without `consent`: `clone_voice({ language })` when you know the language, plus `character_id` when the voice belongs on an existing Character. Provide `consent` only together with an audio file. Leave out `provider`. Its result is the voice card.\n\nThe card does the whole flow: the consent agreement, a one-minute reading script in the user's language (or an uploaded file), the clone on Cartesia, a test line, an optional blind comparison with ElevenLabs and Fish Audio, and saving the voice as a new Character or on one of the user's Characters. It also shows plan and voice-limit messages before anyone records.\n\n- Don't ask for consent or a recording in chat first, and don't send the user to record with another app or a command line; the card collects both.\n- Don't call `clone_voice` for a recording made in the card. Wait for the card's note, which gives the `character_id` and the model to use.\n- Where the host gives the card no microphone, the card offers upload and recording on a phone or in the browser. Nothing to do in chat.\n- If no card shows, the result is `status: \"awaiting_sample\"` (for example in a terminal) or, from a server without the card, `reason: \"voice_sample_not_provided\"`. Nothing was charged. Follow its `recoveryOptions` through the file route below.\n\n## When the user already has a recording\n\nFor an attached file, a local file or a link:\n\n1. Identify the intended delivery and an existing Character, if any. Reuse an avatar's Character instead of creating a duplicate.\n2. Ask for consent once, up front: name the provider, quote the full consent statement with its terms and privacy links from [the reference](references/voices/cloning.md), and ask for the recording's language. One \"I agree\" plus the language covers both. Possessing a recording is not consent.\n3. Import with purpose `voice_clone` to obtain a private `audio_asset_id`. Follow the reference for the current client's upload route.\n4. As soon as the upload returns, call `clone_voice` with that asset, `consent: true`, the recording's `language` code (for example `he`; it defaults to `en`), and `provider: \"cartesia\"` (the default), or `provider: \"elevenlabs\"` when the user chooses ElevenLabs. Do not ask for consent or confirmation again. Use `character_id` for an existing Character or `character_name` for a new voice-only Character. The tool saves the clone automatically.\n5. Audition using `generate_speech` and the returned `character_id`. Include a name, number and natural sentence in the intended language. Present the audio for approval before a longer production. If the user says a word sounds wrong (the stress, an acronym, a homograph or a loanword), fix only that word as [pronunciation](references/voices/pronunciation.md) describes and regenerate before suggesting feedback.\n\nReuse `character_id`, not the private source recording, for future speech. Never replace a saved voice merely to change speech models.\n\n## Choose the synthesis model\n\nEach clone saves its engine on the Character: the clone's own provider, or the one the user picked in the card. `generate_speech` with that `character_id` and no `model` uses it. Set `model` only to override it, using the matching guide:\n\n- [Cartesia Sonic](references/voices/cartesia.md): a Cartesia clone.\n- [ElevenLabs v2](references/voices/elevenlabs-v2.md): an ElevenLabs clone, steady read in its supported languages.\n- [ElevenLabs v4](references/voices/elevenlabs-v4.md): an ElevenLabs clone, expressive delivery or dialogue, and languages v2 lacks.\n- [Language routing](references/voices/languages.md): read for non-English speech, dialect requests, or mixed-language scripts.\n\nOnly change provider when the user chooses it. A missing Cartesia clone can be created from the retained consented sample when Cartesia is selected. Replacing the source invalidates both providers' clones, so explain and confirm replacement first. Do not silently substitute a stock voice after a clone fails.\n\nFor a Fish clone, use `provider: \"fish\"` with the private recording and existing consent. Speak with `speech/fish-drama-3`. Read [Fish guidance](references/voices/fish.md) and current `get_model_params`. Selecting Fish for an existing consented Character can create a missing private Fish copy without replacing its other provider copies.\n"
}

SHA-256 of public snapshot: 20af9af6d1d1ed98bc6913b9af96e2674ceee96fb934b189fad65301b539eaa6