---
name: reels-voice-clone
description: Clone the person's voice from their own consented recording (or from a designed voice), keep it as a saved FlashBoards voice and reuse it for every line; check, replace or delete it.
---
# Clone, save and reuse a voice

FlashBoards user skill, version 1.2.3 (2026-10-13).

On the board, read these guides with `list_skills` and `get_skill` when the assistant exposes them; otherwise use the hosted index through an available read-only retrieval tool. Use that runtime’s actual model discovery, current page context and guarded board actions for execution. Keep native readiness, approval and cost gates; do not claim a guide was read when retrieval is unavailable.

Read related guides with `get_skill({skillId:"<id>"})` or the [hosted index](https://pub-78da82d51ed14147ac554d38094b0c0b.r2.dev/user-skills/1.2.3/index.html). Reading a guide does not start or authorize a paid generation.

Read `reels` for the shared rules. Clone {voice} from the person's own recording, with their consent.

## Clone through MCP

1. **The sample**: 10–180 s of one speaker, clear and without music. Take it from:
   - an upload: `show_media_upload_picker` gives an audio receipt;
   - one of their own results: an audio `generationId`, an `audioFinishingTaskId` (for example a speech span cut with `cut_audio_span`, or a voice isolated with the ElevenLabs Audio Isolation model) or an `audioVoiceTaskId`.
2. `create_audio_voice` with `name`, `description`, `consent: true` and either `audioBase64` (WAV) or `audioSource: {source: <the sample>, startSeconds, endSeconds}` — the server cuts that span.
3. The result names the new voice; `list_audio_voices` shows it with its slot. Keep its id with the character.
4. Voice a test line with `generate_voice_audio` (`model: "eleven_v4"`) and check it with `transcribe_media`.

A voice can be **designed, then kept**: `preview_audio_voice` from a description, pick a preview, `save_audio_voice`.

## Rules

- Clone only voices the person has the right to use.
- Clone from a real recording of the person. A sample of generated speech is accepted, but the voice service then refuses to speak with it (`audio_voice_sample_rejected`).
- Each person has three voice slots for clones and designed voices, which also take one of the voice service's shared slots; library voices take none. `audio_voice_slots_full` means the person's three are used; `audio_voice_slots_exhausted` means the service has none free right now. `delete_audio_voice` frees both; deleting is permanent.
- Other clone models FlashBoards offers (Qwen3-TTS clone, MiniMax voice clone) are listed by `list_generation_models` and run with `run_skill_model`; their results are files, not saved voices.

## Execute through MCP or on the board

Use the person's FlashBoards account; never ask for a personal provider key or run the source's local scripts. Discover `get_account`, `list_generation_models` and the tools of this client first: a published guide does not prove a feature is deployed.

**Headless, no open board.** Quote with `estimate_generation_cost` (skill models: `estimate_skill_model`), then run `generate_image`, `generate_video`, `generate_audio` or `run_skill_model` with one stable `generationAttemptId` per logical attempt. Pass `maxCostUsd` only when the current operation and selected model support it; otherwise use the quoted cost and the person's explicit approval with the supported controls. Never silently ignore an unsupported spending cap; make one `get_generation` check after `retryAfterSeconds`. Pass the person's own results by `generationId`: images in `referenceGenerationIds`, `firstFrameUrl` and `endFrameUrl`, audio in `referenceAudioUrls` or `targetAudioUrl`, videos in `referenceVideoGenerationIds`. They are read on the server; signed result links do not work as public URLs. Every `generationId` a tool returns stays valid: a later read of the same result gives a different string, and both work. Film frames and gallery pictures go in by `previewHandle`: `referencePreviewHandles` of the generation tools, a `{previewHandle}` source of `arrange_images`, `crop_image` and `pad_image`, and `describe_media`. New files come from `show_media_upload_picker` as receipts. The person's character comes in as its sheet, by `generationId` or as an upload; there is no search by name. If the person names a character without the sheet, ask for it or make one with `character-sheet`; do not scan recent results for it. Free server steps: `trim_video`, `concat_videos`, `conform_video`, `replace_video_audio`, `extract_video_frame`, `extract_video_audio`, `detect_video_cuts`, `crop_image`, `pad_image`, `arrange_images`, `cut_audio_span`, `concat_audio_tracks`, `mix_audio_tracks`, `fit_audio_duration`, `add_audio_reverb`. Check every result with `describe_media` (a question about an image; `model`, `mode` and `sourceRange` only for a video) and `transcribe_media` for speech. Both checks are paid: `describe_media` costs a fraction of a cent for an image and about 2–4 ¢ for a short video (more for a long one), `transcribe_media` under 1 ¢ a minute — count the checks you plan in the price you name before the first paid step. `describe_media` is not reliable about sound: it misses effects mixed under music and can hear voices or instruments that are not there. Check speech with `transcribe_media` and ask the person to listen for effects and music. Never repay an uncertain submission; reuse an attempt ID only for the identical request. Make each new `requestId` or `generationAttemptId` unique, for example the task, the date and a short random suffix: an ID used before, even in another chat, replays that earlier request or answers `REQUEST_ID_CONFLICT`.

**On the board.** Inspect with `list_board_sessions` and `get_board_snapshot` and carry the same `sessionId` and a fresh `activeBoardId` as `expectedBoardId`. Native cards: `execute_board_action` (`listNativeModels`, `setModel`), `prepare_board_generation` with ordered board items or owned outputs, then one `generate_on_board` within the authorized budget. Board media tools: `list_media_tools` → `start_media_tool` → `get_media_tool_run`. Put headless results on a board with `add_media_to_board`.

Keep mandatory safety settings and the live limits of each model. Prices, timings, endpoints and "free retry" claims in the sources are historical, not FlashBoards contracts. If a step this guide needs is not available or is refused (a tool error, `audio_not_configured`, a missing model or input), keep the finished assets, tell the person which step is blocked and why, and ask how to go on. A single generation that ends `failed` is not a blocked step: submit it once more with a new `generationAttemptId` (reworded if it may have hit the content checker), and stop to ask only if it fails again. A failed attempt is not always refunded, so the retry may be paid again and `maxCostUsd` caps each request on its own: count both against the budget the person approved. Never swap in another route on your own: no image model redrawing a layout or a frame, no `describe_media` in place of the frames it should check, no clip generated only to take its sound, no picture drawn where the guide takes a film frame.

## Source and related guides

- [Original Learn guide](https://flashboards-h01.vercel.app/learn/formats-and-exhibition/ai-reels-and-shorts/skills/reels-voice-clone.md)
- Updated from the owner's skill sources of 2026-10-11.

Read: `reels`, `reels-voice`. Source experiments and demo materials are historical; use the person's own approved media.