diff --git a/src/python_run/piper/__main__.py b/src/python_run/piper/__main__.py
index 15109f8e..4e859354 100644
--- a/src/python_run/piper/__main__.py
+++ b/src/python_run/piper/__main__.py
@@ -36,6 +36,12 @@ def main() -> None:
         action="store_true",
         help="Stream raw audio to stdout",
     )
+    parser.add_argument(
+        "-p",
+        "--phoneme-input",
+        action="store_true",
+        help="Flag to use pure phonemes as input"
+    )
     #
     parser.add_argument("-s", "--speaker", type=int, help="Id of speaker (default: 0)")
     parser.add_argument(
@@ -107,6 +113,7 @@ def main() -> None:
     # Load voice
     voice = PiperVoice.load(args.model, config_path=args.config, use_cuda=args.cuda)
     synthesize_args = {
+        "phoneme_input": args.phoneme_input,
         "speaker_id": args.speaker,
         "length_scale": args.length_scale,
         "noise_scale": args.noise_scale,
diff --git a/src/python_run/piper/voice.py b/src/python_run/piper/voice.py
index 0360c273..9a0be7e4 100644
--- a/src/python_run/piper/voice.py
+++ b/src/python_run/piper/voice.py
@@ -90,6 +90,7 @@ def synthesize(
         self,
         text: str,
         wav_file: wave.Wave_write,
+        phoneme_input: bool,
         speaker_id: Optional[int] = None,
         length_scale: Optional[float] = None,
         noise_scale: Optional[float] = None,
@@ -103,6 +104,7 @@ def synthesize(
 
         for audio_bytes in self.synthesize_stream_raw(
             text,
+            phoneme_input=phoneme_input,
             speaker_id=speaker_id,
             length_scale=length_scale,
             noise_scale=noise_scale,
@@ -114,6 +116,7 @@ def synthesize(
     def synthesize_stream_raw(
         self,
         text: str,
+        phoneme_input: bool,
         speaker_id: Optional[int] = None,
         length_scale: Optional[float] = None,
         noise_scale: Optional[float] = None,
@@ -121,8 +124,10 @@ def synthesize_stream_raw(
         sentence_silence: float = 0.0,
     ) -> Iterable[bytes]:
         """Synthesize raw audio per sentence from text."""
-        sentence_phonemes = self.phonemize(text)
-
+        if phoneme_input:
+            sentence_phonemes = [list(text)]
+        else:
+            sentence_phonemes = self.phonemize(text)
         # 16-bit mono
         num_silence_samples = int(sentence_silence * self.config.sample_rate)
         silence_bytes = bytes(num_silence_samples * 2)