--- title: "How to add an echo text with Claude (tested prompt and script)" description: "A hot pink \"GLOW\" lands near the top, then four copies peel off behind it and stack upward, each one smaller, fainter and blurrier than the last. Install one skill and ask Claude Code, or run the Python script we tested yourself." url: https://www.recharm.com/effects/echo-text --- # How to add an echo text with Claude A hot pink "GLOW" lands near the top, then four copies peel off behind it and stack upward, each one smaller, fainter and blurrier than the last. 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 an echo text to input.mp4 Text: GLOW ``` ## 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 an echo text 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 | | --------- | ---------------- | -------------------------------------------------------------------------------- | | `TEXT` | `GLOW` | The word. | | `START` | `0.5` | Second the word appears. | | `ECHOES` | `4` | How many copies trail behind the word. | | `DELAY` | `0.12` | Seconds between one copy setting off and the next. | | `SPREAD` | `0.5` | Seconds each copy takes to slide out to its place. | | `GAP` | `0.04` | How far up each copy sits from the one in front, as a share of the frame height. | | `SHRINK` | `0.08` | How much smaller each copy is than the one in front. | | `OPACITY` | `0.6` | Opacity of the nearest copy; each farther one has 0.6 times the one before. | | `BLUR` | `1.5` | Blur radius in pixels added per copy. | | `COLOR` | `(235, 40, 120)` | Text color. | ## Without the skill Don’t want to install the skill? Paste this prompt into Claude Code and Claude writes the script itself. ``` Add echo text to input.mp4: the word "GLOW" in Arial Black (or any heavy bold font) at a font size of 24% of the frame width, hot pink (235, 40, 120), centered across the frame with its center 22% of the way down. It fades in from transparent to fully opaque over 0.2 seconds starting at 0.5 seconds; nothing is on screen before that. Behind it are 4 copies of the word, drawn under it and centered across the frame. Copy i (1 to 4) has a font size of (1 - 0.08 i) times the word's, opacity 0.6 times 0.6^(i-1) (so 0.6, 0.36, 0.22, 0.13) and a Gaussian blur of 1.5 i pixels. Each copy starts hidden behind the word at 0.5 + 0.12 i seconds and slides straight up over 0.5 seconds with a cubic ease-out to sit 4 i% of the frame height above the word's center, then stays there to the end along with the word. Use Python with Pillow to draw the text and ffmpeg to put it on the video (don't rely on ffmpeg's drawtext filter), keep the audio, and save it as output.mp4. ``` ## Run it without Claude This is the exact script we tested. Save it as `echo-text.py` and run: ``` python3 echo-text.py input.mp4 output.mp4 ``` ``` #!/usr/bin/env python3 """Echo text: a pink word appears and fainter, smaller, softer copies of it fan out upward behind it. Usage: python3 echo-text.py input.mp4 output.mp4 Needs ffmpeg and Pillow (pip install pillow). """ import json import math import subprocess import sys from pathlib import Path from PIL import Image, ImageDraw, ImageFilter, ImageFont TEXT = "GLOW" START = 0.5 # second the word appears FADE = 0.2 # seconds the word takes to fade in ECHOES = 4 # copies trailing behind the word DELAY = 0.12 # seconds between one copy setting off and the next SPREAD = 0.5 # seconds each copy takes to slide out to its place SIZE = 0.24 # word height as a share of the frame width Y = 0.22 # where the word's center sits (0 = top, 1 = bottom) GAP = 0.04 # how far up each copy sits from the one in front, as a share of the frame height SHRINK = 0.08 # each copy is this much smaller than the one in front OPACITY = 0.6 # opacity of the nearest copy; each farther copy has 0.6 times the one before BLUR = 1.5 # blur radius in pixels added per copy COLOR = (235, 40, 120) # text color, a hot pink FONTS = ["/System/Library/Fonts/Supplemental/Arial Black.ttf", # macOS "/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf", # Linux "C:/Windows/Fonts/ariblk.ttf"] # 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") def copy_of_word(i): """Copy i of the word (0 is the word itself), smaller, fainter and softer the farther back it is, cropped tight.""" font = ImageFont.truetype(FONT_FILE, round(w * SIZE * (1 - SHRINK * i))) pad = font.size // 4 x0, y0, x1, y1 = font.getbbox(TEXT) img = Image.new("RGBA", (x1 - x0 + 2 * pad, y1 - y0 + 2 * pad)) alpha = 255 if i == 0 else round(255 * OPACITY * 0.6 ** (i - 1)) ImageDraw.Draw(img).text((pad - x0, pad - y0), TEXT, font=font, fill=COLOR + (alpha,)) return img.filter(ImageFilter.GaussianBlur(BLUR * i)) if i else img def overlay(t): """The word fades in; copy i sets off from behind it i * DELAY later and eases up to i * GAP above it.""" img = Image.new("RGBA", (w, h)) if t < START: return img fade = min((t - START) / FADE, 1) for i in range(ECHOES, -1, -1): # farthest copy first, so the word ends up on top p = min(max((t - START - i * DELAY) / SPREAD, 0), 1) if i and p == 0: continue y = h * Y - i * GAP * h * (1 - (1 - p) ** 3) # ease out: fast start, soft stop layer = copies[i].copy() layer.putalpha(layer.getchannel("A").point(lambda a: round(a * fade))) img.alpha_composite(layer, (round((w - layer.width) / 2), round(y - layer.height / 2))) return img 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) copies = [copy_of_word(i) for i in range(ECHOES + 1)] render(src, out) ``` ## More text and titles - [Animated text frame **Animated text frame**](https://www.recharm.com/effects/animated-text-frame) - [Brush stroke text reveal **Brush stroke text reveal**](https://www.recharm.com/effects/brush-stroke-text-reveal) - [Burning text **Burning text**](https://www.recharm.com/effects/burning-text) - [Drop shadow text **Drop shadow text**](https://www.recharm.com/effects/drop-shadow-text) - [3D extruded text **3D extruded text**](https://www.recharm.com/effects/extruded-3d-text) ## 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)