diff --git a/mteb/abstasks/TaskMetadata.py b/mteb/abstasks/TaskMetadata.py
index ad0d2bd6be..aa4658f513 100644
--- a/mteb/abstasks/TaskMetadata.py
+++ b/mteb/abstasks/TaskMetadata.py
@@ -93,6 +93,8 @@
     "Emotional Speech Retrieval",
     "Environment Sound Retrieval",
     "Speech Retrieval",
+    "Question Answering Retrieval",
+    "Reading Comprehension",
 ]
 
 TASK_DOMAIN = Literal[
diff --git a/mteb/tasks/Audio/Any2AnyRetrieval/SpokenSQuAD.py b/mteb/tasks/Audio/Any2AnyRetrieval/SpokenSQuAD.py
new file mode 100644
index 0000000000..01115ca206
--- /dev/null
+++ b/mteb/tasks/Audio/Any2AnyRetrieval/SpokenSQuAD.py
@@ -0,0 +1,38 @@
+from __future__ import annotations
+
+from mteb.abstasks.Image.AbsTaskAny2AnyRetrieval import AbsTaskAny2AnyRetrieval
+from mteb.abstasks.TaskMetadata import TaskMetadata
+
+
+class SpokenSQuADT2ARetrieval(AbsTaskAny2AnyRetrieval):
+    metadata = TaskMetadata(
+        name="SpokenSQuADT2ARetrieval",
+        description="Text-to-audio retrieval task based on SpokenSQuAD dataset. Given a text question, retrieve relevant audio segments that contain the answer. Questions are derived from SQuAD reading comprehension dataset with corresponding spoken passages.",
+        reference="https://github.com/chiuwy/Spoken-SQuAD",
+        dataset={
+            "path": "arteemg/spoken-squad-t2a",
+            "revision": "63c5c8e4cf762e52e18ecde8baf5733eab114ae9",
+        },
+        type="Any2AnyRetrieval",
+        category="t2a",
+        modalities=["text", "audio"],
+        eval_splits=["test"],
+        eval_langs=["eng-Latn"],
+        main_score="cv_recall_at_5",
+        date=("2018-03-01", "2018-03-01"),
+        domains=["Academic", "Encyclopaedic", "Non-fiction"],
+        task_subtypes=["Question Answering Retrieval", "Reading Comprehension"],
+        license="cc-by-sa-4.0",
+        annotations_creators="derived",
+        dialect=[],
+        sample_creation="found",
+        bibtex_citation=r"""
+@inproceedings{li2018spokensquad,
+  author = {Li, Chia-Hsuan and Ma, Szu-Lin and Zhang, Hsin-Wei and Lee, Hung-yi and Lee, Lin-shan},
+  booktitle = {Interspeech},
+  pages = {3459--3463},
+  title = {Spoken SQuAD: A Study of Mitigating the Impact of Speech Recognition Errors on Listening Comprehension},
+  year = {2018},
+}
+""",
+    )
diff --git a/mteb/tasks/Audio/Any2AnyRetrieval/__init__.py b/mteb/tasks/Audio/Any2AnyRetrieval/__init__.py
index 545c92164e..74f9bc2432 100644
--- a/mteb/tasks/Audio/Any2AnyRetrieval/__init__.py
+++ b/mteb/tasks/Audio/Any2AnyRetrieval/__init__.py
@@ -14,4 +14,5 @@
 from .multilingual.JamAlt import *
 from .MusicCaps import *
 from .SoundDescs import *
+from .SpokenSQuAD import *
 from .UrbanSound8kRetrieval import *