Add ElevenLabs voiceover pipeline to ArbEdge ads project - #43
Open
jdthorsen62-lgtm wants to merge 1 commit into
Open
Add ElevenLabs voiceover pipeline to ArbEdge ads project#43jdthorsen62-lgtm wants to merge 1 commit into
jdthorsen62-lgtm wants to merge 1 commit into
Conversation
Per-beat narration field in script.json, idempotent tools/gen_voiceover.py (hash-based skip, ffprobe duration sync to duration_frames), and generated audio for all 5 beats using voice G5FFvULjfTouEEWKNmuH. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Author
|
@digitalsamba Could someone with write access review and merge this when you get a chance? It's clean and mergeable, no CI configured on this repo to block on. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
narrationfield per beat inprojects/arbedge-ads/script.json, replacing the priorvoiceoverfieldtools/gen_voiceover.pygenerates one MP3 per beat via ElevenLabs (voiceG5FFvULjfTouEEWKNmuH, modeleleven_multilingual_v2, stability 0.5), idempotent via a text hash so unchanged beats are skipped on rerunduration_framesis synced to its actual audio duration (viaffprobe) plus ~0.4s padding<Audio>playback (already wired per-beat inside its<Sequence>) now has real generated audio to playscript.json/types.ts/gen_voiceover.pyTest plan
tools/gen_voiceover.py— generated audio + updated durations for all 5 beatstools/gen_voiceover.py— confirmed idempotency (all beats cached, no regeneration)npx remotion render FullAd) and verified viaffprobe/volumedetectthat the output has a real (non-silent) AAC audio track spanning the full video duration🤖 Generated with Claude Code