Generate a voiceover (VO) clip via ElevenLabs text-to-speech, ROUTED THROUGH THE elevenlabs-proxy so it bills the Ads agent. Voice id + script text come from the template recipe. Use for the spoken narration of VO-driven video-ad formats (cgi-app-sizzle, flat-vector-explainer, hypermotion). Never call ElevenLabs directly — the proxy attribution is required.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Superseded: the video kit now does this with the voice-elevenlabs part, version 1.0.1, in the parts folder of this repository. It speaks every scene's line through the private line, keeps character timings as word timings and swaps in confirmed pronunciations the same way. This atom stays, unchanged in behaviour, for skills outside the kit until they move; its scripts still run.
VO via the elevenlabs-proxy (bills the Ads agent). gen_vo.py --text "..." --voice <id> --out vo.mp3.
The template recipe supplies the voice + text; paid call routes through media_proxy.
A brand name or product name the voice gets wrong is spoken from its phonetic
spelling, never from a (pronounced …) note (the voice reads notes aloud):
gen_vo.py --text "Meet Drinkag1." --voice <id> --out vo.mp3 --rules working/brand-rules.json
# or: --say-as "Drinkag1=drink A G one"
Only the SPOKEN text changes. Captions, on-screen text and the approved script keep the written name. When captions are timed from this VO, map the spoken words back to the written term.
At the start of every video, read the selected brand's persistent facts, including user-authored pronunciation rules. A previous video's notes or a cached rules file do not establish current pronunciation. For an unknown or ambiguous name, resolve how it is said before the paid voice step. Save the user's confirmed choice in the existing brand-facts store, update an existing rule by its id, then make a separate read and confirm it survived. Never infer successful persistence from a write acknowledgement.
The bundled read_pronunciations.py exports user-authored must rules from a fresh context snapshot (the brand read's payload, its {"result": …} wrapper, or the whole tool result). A rule's text is Pronounce "<term>" as "<say_as>"; the older Pronunciation: <term> => <say_as> is also read. It rejects a different brand, conflicting rules and required names that remain unknown. The resulting local rules file is a per-run voice input; the brand store remains the durable source. gen_vo.py supports a free dry run to review the resulting spoken text. Captions retain written names.
How the ElevenLabs voices behave, measured on shipped projects. Each note lives here once.
[curious], [pause]): tag characters get
invented times and nearby characters bunch together. For captions or sound sync, re-transcribe
the rendered audio with fal-ai/whisper at word level.style is the expressiveness dial (0.05 unless there is a reason);
the text cannot buy pauses (an ellipsis or a break tag changes nothing), so pad silence after
generation; speed is the only rate control (0.85 lands in conversational range, and the
scale is close to linear from 0.80 to 1.00); stability changes delivery, not rate.The bundled generator supports timestamped voiceover with per-voice settings. Use the timestamp option for podcast dialogue and other edits that must follow speech. It saves an MP3 and a character-alignment JSON beside it, sharing the same filename stem. The existing audio-only invocation keeps its behavior. A missing alignment is an error; do not render captions from guessed timings. See the bundled timestamp tests for the request and output contract.
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Research supported advertising promises from a specific buyer's context, current product facts, customer language and observed ads. Turn them into static, video or copy ideas; match video ideas to actual recipes and save a product-scoped angle bank for write-video-ad-script. Product-led discovery can use verified facts without reviews. Reference persistence and reach are observations, not proof of performance.
日本語の概要は準備中です。原文の説明を表示しています。
Analyze ad campaign performance data (Google, Meta, LinkedIn) to identify what's working, what's wasting budget, and specific cut/scale/test recommendations. Runs statistical analysis, funnel diagnostics, and multi-channel budget reallocation with specific dollar-amount shift recommendations and scenario modeling.
日本語の概要は準備中です。原文の説明を表示しています。
For paid lead-gen and participant-recruitment ads, replaces vanity CPA with true CAC per qualified lead by joining ad-platform data with downstream funnel events, surfaces tracking gaps, and classifies every creative into Scale / Keep / Investigate / Cut.
日本語の概要は準備中です。原文の説明を表示しています。
The intake stage of a Meta ad harness. Researches the brand first, states what it assumes, and asks only what it cannot infer and what would change money, claims or legal exposure if guessed wrong — at most four questions a turn, in plain business language. Writes the brand's stable facts (ads/brand.md), the campaign brief, and a log of what was asked vs assumed. Use it when someone wants to run Meta ads and the brand's ad facts are not yet recorded.
日本語の概要は準備中です。原文の説明を表示しています。
Analyze the message match between your ads and landing pages. Checks if the promise in the ad copy carries through to the landing page headline, body, and CTA. Flags disconnects that kill conversion rates. Works with Google, Meta, and LinkedIn ads.
日本語の概要は準備中です。原文の説明を表示しています。
Turn a brand's facts, a campaign brief and the product into a one-minute Meta ad strategy with its reasoning — goal, audience, objective and placements, budget split, how many ads and how different they must be (generate 3x so the user can choose), the test frame, the success metric, and safety rules for the user to accept. Decides what launch-meta-ad-campaign then executes, and re-reads the strategy after a deep check to show which assumption changed. Use it after intake and before any creative is generated or any campaign is built.
日本語の概要は準備中です。原文の説明を表示しています。