diff --git a/src/__tests__/subtitles/subtitles.test.ts b/src/__tests__/subtitles/subtitles.test.ts
new file mode 100644
index 00000000..90d659dd
--- /dev/null
+++ b/src/__tests__/subtitles/subtitles.test.ts
@@ -0,0 +1,136 @@
+import { describe, it } from "vitest";
+import {
+  isSupportedSubtitle,
+  getMWCaptionTypeFromUrl,
+  parseSubtitles,
+} from "@/backend/helpers/captions";
+import { MWCaptionType } from "@/backend/helpers/streams";
+import { ass, srt, visibleSubtitlesTestVtt, vtt } from "./testdata";
+
+describe("subtitles", () => {
+  it("should return true if given url ends with a known subtitle type", ({
+    expect,
+  }) => {
+    expect(isSupportedSubtitle("https://example.com/test.srt")).toBe(true);
+    expect(isSupportedSubtitle("https://example.com/test.vtt")).toBe(true);
+    expect(isSupportedSubtitle("https://example.com/test.txt")).toBe(false);
+  });
+
+  it("should return corresponding MWCaptionType", ({ expect }) => {
+    expect(getMWCaptionTypeFromUrl("https://example.com/test.srt")).toBe(
+      MWCaptionType.SRT
+    );
+    expect(getMWCaptionTypeFromUrl("https://example.com/test.vtt")).toBe(
+      MWCaptionType.VTT
+    );
+    expect(getMWCaptionTypeFromUrl("https://example.com/test.txt")).toBe(
+      MWCaptionType.UNKNOWN
+    );
+  });
+
+  it("should throw when empty text is given", ({ expect }) => {
+    expect(() => parseSubtitles("")).toThrow("Given text is empty");
+  });
+
+  it("should parse srt", ({ expect }) => {
+    const parsed = parseSubtitles(srt);
+    const parsedSrt = [
+      {
+        type: "caption",
+        index: 1,
+        start: 0,
+        end: 0,
+        duration: 0,
+        content: "Test",
+        text: "Test",
+      },
+      {
+        type: "caption",
+        index: 2,
+        start: 0,
+        end: 0,
+        duration: 0,
+        content: "Test",
+        text: "Test",
+      },
+    ];
+    expect(parsed).toHaveLength(2);
+    expect(parsed).toEqual(parsedSrt);
+  });
+
+  it("should parse vtt", ({ expect }) => {
+    const parsed = parseSubtitles(vtt);
+    const parsedVtt = [
+      {
+        type: "caption",
+        index: 1,
+        start: 0,
+        end: 4000,
+        duration: 4000,
+        content: "Where did he go?",
+        text: "Where did he go?",
+      },
+      {
+        type: "caption",
+        index: 2,
+        start: 3000,
+        end: 6500,
+        duration: 3500,
+        content: "I think he went down this lane.",
+        text: "I think he went down this lane.",
+      },
+      {
+        type: "caption",
+        index: 3,
+        start: 4000,
+        end: 6500,
+        duration: 2500,
+        content: "What are you waiting for?",
+        text: "What are you waiting for?",
+      },
+    ];
+    expect(parsed).toHaveLength(3);
+    expect(parsed).toEqual(parsedVtt);
+  });
+
+  it("should parse ass", ({ expect }) => {
+    const parsed = parseSubtitles(ass);
+    expect(parsed).toHaveLength(3);
+  });
+
+  it("should delay subtitles when given a delay", ({ expect }) => {
+    const videoTime = 11;
+    let delayedSeconds = 0;
+    const parsed = parseSubtitles(visibleSubtitlesTestVtt);
+    const isVisible = (start: number, end: number, delay: number): boolean => {
+      const delayedStart = start / 1000 + delay;
+      const delayedEnd = end / 1000 + delay;
+      return (
+        Math.max(0, delayedStart) <= videoTime &&
+        Math.max(0, delayedEnd) >= videoTime
+      );
+    };
+    const visibleSubtitles = parsed.filter((c) =>
+      isVisible(c.start, c.end, delayedSeconds)
+    );
+    expect(visibleSubtitles).toHaveLength(1);
+
+    delayedSeconds = 10;
+    const delayedVisibleSubtitles = parsed.filter((c) =>
+      isVisible(c.start, c.end, delayedSeconds)
+    );
+    expect(delayedVisibleSubtitles).toHaveLength(1);
+
+    delayedSeconds = -10;
+    const delayedVisibleSubtitles2 = parsed.filter((c) =>
+      isVisible(c.start, c.end, delayedSeconds)
+    );
+    expect(delayedVisibleSubtitles2).toHaveLength(1);
+
+    delayedSeconds = -20;
+    const delayedVisibleSubtitles3 = parsed.filter((c) =>
+      isVisible(c.start, c.end, delayedSeconds)
+    );
+    expect(delayedVisibleSubtitles3).toHaveLength(1);
+  });
+});
diff --git a/src/__tests__/subtitles/testdata.ts b/src/__tests__/subtitles/testdata.ts
new file mode 100644
index 00000000..a121e705
--- /dev/null
+++ b/src/__tests__/subtitles/testdata.ts
@@ -0,0 +1,56 @@
+const srt = `
+1
+00:00:00,000 --> 00:00:00,000
+Test
+
+2
+00:00:00,000 --> 00:00:00,000
+Test
+`;
+const vtt = `
+WEBVTT
+
+00:00:00.000 --> 00:00:04.000 position:10%,line-left align:left size:35%
+Where did he go?
+
+00:00:03.000 --> 00:00:06.500 position:90% align:right size:35%
+I think he went down this lane.
+
+00:00:04.000 --> 00:00:06.500 position:45%,line-right align:center size:35%
+What are you waiting for?
+`;
+const ass = `[Script Info]
+; Generated by Ebby.co
+Title: 
+Original Script: 
+ScriptType: v4.00+
+Collisions: Normal
+PlayResX: 384
+PlayResY: 288
+PlayDepth: 0
+Timer: 100.0
+WrapStyle: 0
+
+[v4+ Styles]
+Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding
+Style: Default, Arial, 16, &H00FFFFFF, &H00000000, &H00000000, &H00000000, 0, 0, 0, 0, 100, 100, 0, 0, 1, 1, 0, 2, 15, 15, 15, 0
+
+[Events]
+Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
+Dialogue: 0,0:00:10.00,0:00:20.00,Default,,0000,0000,0000,,This is the first subtitle.
+Dialogue: 0,0:00:30.00,0:00:34.00,Default,,0000,0000,0000,,This is the second.
+Dialogue: 0,0:00:34.00,0:00:35.00,Default,,0000,0000,0000,,Third`;
+
+const visibleSubtitlesTestVtt = `WEBVTT
+
+00:00:00.000 --> 00:00:10.000 position:10%,line-left align:left size:35%
+Test 1
+
+00:00:10.000 --> 00:00:20.000 position:90% align:right size:35%
+Test 2
+
+00:00:20.000 --> 00:00:31.000 position:45%,line-right align:center size:35%
+Test 3
+`;
+
+export { vtt, srt, ass, visibleSubtitlesTestVtt };