diff --git a/src/f5_tts/infer/examples/basic/basic.toml b/src/f5_tts/infer/examples/basic/basic.toml
index cc3fbda..1871499 100644
--- a/src/f5_tts/infer/examples/basic/basic.toml
+++ b/src/f5_tts/infer/examples/basic/basic.toml
@@ -1,6 +1,6 @@
 # F5-TTS | E2-TTS
 model = "F5-TTS"
-ref_audio = "src/f5_tts/infer/examples/basic/basic_ref_en.wav"
+ref_audio = "infer/examples/basic/basic_ref_en.wav"
 # If an empty "", transcribes the reference audio automatically.
 ref_text = "Some call me nature, others call me mother nature."
 gen_text = "I don't really care what you call me. I've been a silent spectator, watching species evolve, empires rise and fall. But always remember, I am mighty and enduring."
diff --git a/src/f5_tts/infer/examples/multi/story.toml b/src/f5_tts/infer/examples/multi/story.toml
index bdf4455..c637062 100644
--- a/src/f5_tts/infer/examples/multi/story.toml
+++ b/src/f5_tts/infer/examples/multi/story.toml
@@ -1,19 +1,19 @@
 # F5-TTS | E2-TTS
 model = "F5-TTS"
-ref_audio = "src/f5_tts/infer/examples/multi/main.flac"
+ref_audio = "infer/examples/multi/main.flac"
 # If an empty "", transcribes the reference audio automatically.
 ref_text = ""
 gen_text = ""
 # File with text to generate. Ignores the text above.
-gen_file = "src/f5_tts/infer/examples/multi/story.txt"
+gen_file = "infer/examples/multi/story.txt"
 remove_silence = true
 output_dir = "tests"
 
 [voices.town]
-ref_audio = "src/f5_tts/infer/examples/multi/town.flac"
+ref_audio = "infer/examples/multi/town.flac"
 ref_text = ""
 
 [voices.country]
-ref_audio = "src/f5_tts/infer/examples/multi/country.flac"
+ref_audio = "infer/examples/multi/country.flac"
 ref_text = ""
 
diff --git a/src/f5_tts/infer/infer_cli.py b/src/f5_tts/infer/infer_cli.py
index d56408f..ebd538f 100644
--- a/src/f5_tts/infer/infer_cli.py
+++ b/src/f5_tts/infer/infer_cli.py
@@ -80,8 +80,8 @@ args = parser.parse_args()
 config = tomli.load(open(args.config, "rb"))
 
 ref_audio = args.ref_audio if args.ref_audio else config["ref_audio"]
-if "src/f5_tts/infer/examples/basic" in ref_audio:  # for pip pkg user
-    ref_audio = str(files("f5_tts").joinpath(f"../../{ref_audio}"))
+if "infer/examples/" in ref_audio:  # for pip pkg user
+    ref_audio = str(files("f5_tts").joinpath(f"{ref_audio}"))
 ref_text = args.ref_text if args.ref_text != "666" else config["ref_text"]
 gen_text = args.gen_text if args.gen_text else config["gen_text"]
 gen_file = args.gen_file if args.gen_file else config["gen_file"]