A presenter video, localized for other markets

Make the host portrait with GPT Image 2.5 Sunburst (model_openai-gpt-image-2-5-sunburst): referenceImages [packshot] as an array, width 1536, height 864, quality "high". Quote the cost with a dry run first and wait for my go.

Prompt, word for word:
Photoreal medium shot of a woman in her late 30s, warm olive skin, dark brown hair tied back loosely, a few loose strands, light freckles, no makeup look. She wears a faded rust-colored canvas work apron over a cream knit sweater with sleeves pushed up. She sits at a wooden pottery workbench in a small sunlit ceramics studio; behind her, softly out of focus, wooden shelves with a few unglazed bowls and a potter's wheel. On the bench in front of her, at the lower right, stands the exact mug from the reference image with its printed wren logo and the words KILNWREN and TRAIL MUG facing the camera. Waist-up framing, straight-on, eye-level, camera on a tripod in front, she looks directly into the lens, mouth closed with a calm friendly expression, both hands resting relaxed on the bench, five normal fingers each. Soft window daylight from the left, natural skin texture, 35mm photo. Not a selfie, no arm toward the camera, no side profile, no other text or logos.

Show it to me and wait: I check the face, both hands and the label at 1:1 before we go on.

Make the voice with ElevenLabs v4 (model_elevenlabs-tts-v4): voice Sarah, stability 0.5, similarity 0.75 (read model_schema_get for the parameter names). Script, word for word:
Every Kilnwren Trail Mug is made by hand, right here in this studio. It's fired hot enough for cold campsite mornings, and each green rim is glazed one mug at a time. Take it wherever you wake up early.

When I approve the voice, run Minimax H3 Max Lip Sync (model_minimax-h3-max-lip-sync) with image set to the approved portrait and audio set to the voice track, resolution 768P. For comparison, run Omni Human 1.5 (model_bytedance-omni-human-1-5) with the same image and audio. Quote every video job with a dry run first and wait for my go.

Download both videos with asset_download. Extract 6 frames from each into one contact sheet, plus a close crop of the mug, and transcribe each video's audio with whisper. Compare each transcript with the script word by word and tell me which take passes. Then create a collection for the host with the approved portrait and the kept video, and put the voice settings and the chosen model in its description.

Make the Spanish (Spain) version two ways. Quote the cost with a dry run first and wait for my go.

1. HeyGen Video Translate Precision (model_heygen-v2-translate-precision) on the kept English video: outputLanguage "Spanish (Spain)", speakerNum 1, enableDynamicDuration false.

2. ElevenLabs v4 (model_elevenlabs-tts-v4) with the same voice settings as the English source. Text, word for word:
Cada Kilnwren Trail Mug se hace a mano, aquí mismo, en este taller. Se cuece a alta temperatura para las mañanas frías de acampada, y cada borde verde se esmalta taza a taza. Llévala allí donde madrugues.

Then Sync-3 Lipsync (model_sync-lipsync-v3) with the English video and the Spanish audio, syncMode "bounce", since the Spanish audio runs longer than the video.

Transcribe both Spanish videos with whisper, compare them word by word with the approved Spanish text, and extract 6 frames from each into a contact sheet. Tell me which to keep. Then correct the product name and line breaks in the subtitle file, burn the subtitles in clear of the mug label, and check one frame per line. Add the kept version to the host's collection and report the models, every asset ID and the total cost spent.

Photoreal medium shot of a woman in her late 30s, warm olive skin, dark brown hair tied back loosely, a few loose strands, light freckles, no makeup look. She wears a faded rust-colored canvas work apron over a cream knit sweater with sleeves pushed up. She sits at a wooden pottery workbench in a small sunlit ceramics studio; behind her, softly out of focus, wooden shelves with a few unglazed bowls and a potter's wheel. On the bench in front of her, at the lower right, stands the exact mug from the reference image with its printed wren logo and the words KILNWREN and TRAIL MUG facing the camera. Waist-up framing, straight-on, eye-level, camera on a tripod in front, she looks directly into the lens, mouth closed with a calm friendly expression, both hands resting relaxed on the bench, five normal fingers each. Soft window daylight from the left, natural skin texture, 35mm photo. Not a selfie, no arm toward the camera, no side profile, no other text or logos.

Cada Kilnwren Trail Mug se hace a mano, aquí mismo, en este taller. Se cuece a alta temperatura para las mañanas frías de acampada, y cada borde verde se esmalta taza a taza. Llévala allí donde madrugues.