--- title: "How to add emoji captions with Claude (tested prompt and script)" description: "Each spoken line appears in white outlined type with a matching emoji popping in at its end: a green check mark after \"cleared\", sparkles after \"skin\". Install one skill and ask Claude Code, or run the Python script we tested yourself." url: https://www.recharm.com/effects/emoji-captions --- # How to add emoji captions with Claude Each spoken line appears in white outlined type with a matching emoji popping in at its end: a green check mark after "cleared", sparkles after "skin". Made by the script on this page, from our own test clip. ## Get this effect 1. ### Switch to Code in your [Claude Desktop App](https://claude.com/download) 2. ### Install the skill (once) ``` Install the Recharm video effects skill: download https://recharm-growth-staging.s3.us-east-2.amazonaws.com/website/downloads/recharm-video-effects.zip and unzip it into ~/.claude/skills ``` 3. ### Ask for the effect ``` Add emoji captions to input.mp4 Emoji: cleared → ✅, skin → ✨, love → 😍, ... ``` ## Several videos, several effects, one ask Put your clips in the folder, mention them with @, and ask for everything at once. Claude runs one tested script after another on each clip, then joins them. Add emoji captions to **@clip1.mp4**, put a sale badge on **@clip2.mp4**, give **@clip3.mp4** a VHS look, then join all three with crossfades. ## Settings you can change Ask Claude to change any of these, or edit them at the top of the script. | Setting | Default | What it does | | ------------ | --------------------------------------- | ---------------------------------------------------------------------------- | | `EMOJI` | `cleared → ✅, skin → ✨, love → 😍, ...` | Words that get an emoji, and which one. The first word found in a line wins. | | `SIZE` | `0.075` | Text height as a share of the frame width. | | `EMOJI_SIZE` | `2.0` | Emoji height as a multiple of the text height. | | `Y` | `0.8` | Where the caption sits, from 0 (top) to 1 (bottom). | | `POP` | `0.25` | Seconds the emoji takes to pop in. | | `MAX_WORDS` | `4` | Most words on one line. | ## Without the skill Don’t want to install the skill? Paste this prompt into Claude Code and Claude writes the script itself. ``` Add emoji captions to input.mp4 from its speech, with no script or subtitle file. Transcribe the audio with faster-whisper (model "base.en", device cpu, compute_type int8, word_timestamps=True). Group the words in order into lines of 4 words, and show each line from its first word's start until 0.4 seconds after its last word ends, or until the next line starts if that is sooner, with nothing on screen after the last line. Give a line an emoji when one of its words (lowercased, punctuation removed) is in this map, first match wins: cleared or clear -> ✅, skin or glow -> ✨, love -> 😍, money or cash -> 💰, fire or hot -> 🔥. Draw the line in white Arial Bold 7.5% of the frame width tall with a black outline 14% of the text height thick, and put the emoji right after the last word, 0.3 text heights away, 2 text heights tall, drawn in color from Apple Color Emoji (load it at size 160 and scale the image; use embedded_color=True). Center the text and emoji together horizontally with their middle 80% of the way down the frame, shrinking both if they are wider than 90% of the frame. The emoji pops in over the line's first 0.25 seconds, scaling from 0 with an ease-out-back overshoot to about 110% and settling at 100%. Use Python with Pillow to draw the text and emoji (don't use ffmpeg's drawtext or subtitles filter) and ffmpeg to put them on the video, keep the audio, and save it as output.mp4. ``` ## Run it without Claude This is the exact script we tested. Save it as `emoji-captions.py` and run: ``` python3 emoji-captions.py input.mp4 output.mp4 ``` ``` #!/usr/bin/env python3 """Emoji captions: Whisper transcribes the speech, and each caption line ends with a matching emoji that pops in. Usage: python3 emoji-captions.py input.mp4 output.mp4 faster-whisper listens to the audio on your computer and times every word; a line that contains a word from EMOJI gets that word's emoji. Add your own words to EMOJI. Needs ffmpeg, faster-whisper and Pillow (pip install faster-whisper pillow) and a color emoji font (Apple Color Emoji on macOS, Noto Color Emoji on Linux, Segoe UI Emoji on Windows). The first run downloads the "base.en" speech model (about 140 MB). """ import json import math import subprocess import sys from pathlib import Path from faster_whisper import WhisperModel from PIL import Image, ImageDraw, ImageFont MODEL = "base.en" # Whisper model: bigger ("small.en", "medium.en") is more accurate but slower EMOJI = {"cleared": "✅", "clear": "✅", "skin": "✨", "glow": "✨", "love": "😍", "money": "💰", "cash": "💰", "fire": "🔥", "hot": "🔥", "fast": "⚡", "free": "🎁", "sale": "🏷"} # word -> emoji; first word found wins SIZE = 0.075 # caption text height as a share of the frame width (shrinks to fit long lines) Y = 0.8 # where the caption's center sits (0 = top, 1 = bottom) MAX_WIDTH = 0.9 # widest line, emoji included, as a share of the frame width EMOJI_SIZE = 2.0 # emoji height as a multiple of the text height GAP = 0.3 # space between the last word and the emoji, as a multiple of the text height POP = 0.25 # seconds the emoji takes to pop in, overshooting a little MAX_WORDS = 4 # most words on one line HOLD = 0.4 # seconds a line stays up after its last word, unless the next line starts sooner STROKE = 0.14 # black outline round the letters, as a share of the text height FONTS = ["/System/Library/Fonts/Supplemental/Arial Bold.ttf", # macOS "/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf", # Linux "C:/Windows/Fonts/arialbd.ttf"] # Windows EMOJI_FONTS = [("/System/Library/Fonts/Apple Color Emoji.ttc", 160), # macOS (only draws at 160) ("/usr/share/fonts/truetype/noto/NotoColorEmoji.ttf", 109), # Linux (only draws at 109) ("C:/Windows/Fonts/seguiemj.ttf", 160)] # Windows FONT_FILE = next((f for f in FONTS if Path(f).exists()), None) or sys.exit("No bold font found: add one to FONTS") EMOJI_FONT = next((f for f in EMOJI_FONTS if Path(f[0]).exists()), None) or sys.exit("No emoji font: add one to EMOJI_FONTS") def transcribe(path): """Every spoken word as (text, start, end), times in seconds.""" model = WhisperModel(MODEL, device="cpu", compute_type="int8") segments, _ = model.transcribe(path, word_timestamps=True) return [(word.word.strip(), word.start, word.end) for segment in segments for word in segment.words] def caption_lines(words): """Lines of up to MAX_WORDS words: [(text, emoji or None, start, end)].""" groups = [words[i:i + MAX_WORDS] for i in range(0, len(words), MAX_WORDS)] lines = [] for i, group in enumerate(groups): end = group[-1][2] + HOLD if i + 1 < len(groups): end = min(end, groups[i + 1][0][1]) keys = ["".join(ch for ch in text.lower() if ch.isalpha()) for text, _, _ in group] emoji = next((EMOJI[k] for k in keys if k in EMOJI), None) lines.append((" ".join(text for text, _, _ in group), emoji, group[0][1], end)) return lines def emoji_image(emoji, height): """The emoji drawn at the font's own size, trimmed and scaled to height pixels.""" path, size = EMOJI_FONT img = Image.new("RGBA", (size * 2, size * 2)) ImageDraw.Draw(img).text((size, size), emoji, font=ImageFont.truetype(path, size), anchor="mm", embedded_color=True) img = img.crop(img.getbbox()) scale = height / max(img.size) return img.resize((round(img.width * scale), round(img.height * scale)), Image.LANCZOS) def caption(text, emoji): """The line drawn once, centered together with its emoji: (image, emoji, where the emoji's center goes).""" size = w * SIZE width = ImageFont.truetype(FONT_FILE, round(size)).getlength(text) + (size * (GAP + EMOJI_SIZE) if emoji else 0) size *= min(1, w * MAX_WIDTH / width) font = ImageFont.truetype(FONT_FILE, round(size)) pic = emoji_image(emoji, round(size * EMOJI_SIZE)) if emoji else None width = font.getlength(text) + (size * GAP + pic.width if pic else 0) x = (w - width) / 2 img = Image.new("RGBA", (w, h)) ImageDraw.Draw(img).text((x, h * Y), text, font=font, anchor="lm", fill="white", stroke_width=round(size * STROKE), stroke_fill="black") return img, pic, (x + width - (pic.width / 2 if pic else 0), h * Y) def pop_scale(p): """Ease-out-back: 0 -> about 1.1 -> 1 as p goes from 0 to 1.""" return 1 + 2.7 * (p - 1) ** 3 + 1.7 * (p - 1) ** 2 def overlay(t): for i, (text, emoji, start, end) in enumerate(lines): if start <= t < end: img, pic, (cx, cy) = drawn.get(i) or drawn.setdefault(i, caption(text, emoji)) if not pic: return img scale = pop_scale(min((t - start) / POP, 1)) pic = pic.resize((max(1, round(pic.width * scale)), max(1, round(pic.height * scale))), Image.LANCZOS) img = img.copy() img.alpha_composite(pic, (round(cx - pic.width / 2), round(cy - pic.height / 2))) return img return blank def probe(path): info = json.loads(subprocess.check_output(["ffprobe", "-v", "error", "-select_streams", "v:0", "-show_entries", "stream=width,height,r_frame_rate:format=duration", "-of", "json", path])) s = info["streams"][0] num, den = s["r_frame_rate"].split("/") return s["width"], s["height"], s["r_frame_rate"], float(num) / float(den), float(info["format"]["duration"]) def render(src, out): """Draw overlay(t) on every frame of src and save to out, keeping the audio.""" ff = subprocess.Popen(["ffmpeg", "-y", "-v", "error", "-i", src, "-f", "rawvideo", "-pix_fmt", "rgba", "-s", f"{w}x{h}", "-r", rate, "-i", "-", "-filter_complex", "[0:v][1:v]overlay=shortest=1,format=yuv420p[v]", "-map", "[v]", "-map", "0:a?", "-c:v", "libx264", "-crf", "18", "-c:a", "copy", out], stdin=subprocess.PIPE) for i in range(math.ceil(duration * fps)): ff.stdin.write(overlay(i / fps).tobytes()) ff.stdin.close() if ff.wait(): sys.exit("ffmpeg failed") src, out = sys.argv[1:3] w, h, rate, fps, duration = probe(src) lines = caption_lines(transcribe(src)) blank = Image.new("RGBA", (w, h)) drawn = {} render(src, out) ``` ## More captions and text - [AI chat reply animation **AI chat reply animation**](https://www.recharm.com/effects/ai-chat-typing) - [Animated bar chart **Animated bar chart**](https://www.recharm.com/effects/animated-bar-chart) - [Animated checklist **Animated checklist**](https://www.recharm.com/effects/animated-checklist) - [Animated line graph **Animated line graph**](https://www.recharm.com/effects/animated-line-graph) - [Animated pie chart **Animated pie chart**](https://www.recharm.com/effects/animated-pie-chart) ## Find 3x _winning ads_ Recharm cuts your ad footage into tagged, searchable clips: hooks, testimonials, product shots. Find the shots that win, add the effect with Claude, and ship 3x more ad edits. [Start 14-day free trial](https://www.recharm.com/get-started)