From 5bd1fb6b2c51735e811c185e5f2e4f92ab0121d1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eren=20G=C3=B6lge?= <egolge@coqui.ai>
Date: Mon, 10 Apr 2023 13:32:16 +0200
Subject: [PATCH] Fix API for voice conversion

---
 TTS/api.py | 33 ++++++++++++++++++++++++++++-----
 1 file changed, 28 insertions(+), 5 deletions(-)

diff --git a/TTS/api.py b/TTS/api.py
index 7376cfa4..460e9374 100644
--- a/TTS/api.py
+++ b/TTS/api.py
@@ -85,7 +85,7 @@ class CS_API:
             self.headers = {"Content-Type": "application/json", "Authorization": f"Bearer {self.api_token}"}
         if not self.api_token:
             raise ValueError(
-                "No API token found for 🐸Coqui Studio voices - https://coqui.ai.\n"
+                "No API token found for 🐸Coqui Studio voices - https://coqui.ai \n"
                 "Visit 🔗https://app.coqui.ai/account to get one.\n"
                 "Set it as an environment variable `export COQUI_STUDIO_TOKEN=<token>`\n"
                 ""
@@ -274,7 +274,10 @@ class TTS:
         self.model_name = None
 
         if model_name:
-            self.load_tts_model_by_name(model_name, gpu)
+            if "tts_models" in model_name:
+                self.load_tts_model_by_name(model_name, gpu)
+            elif "voice_conversion_models" in model_name:
+                self.load_vc_model_by_name(model_name, gpu)
 
         if model_path:
             self.load_tts_model_by_path(
@@ -565,19 +568,39 @@ class TTS:
 
     def voice_conversion(
         self,
-        sourve_wav: str,
+        source_wav: str,
         target_wav: str,
     ):
         """Voice conversion with FreeVC. Convert source wav to target speaker.
 
+        Args:``
+            source_wav (str):
+                Path to the source wav file.
+            target_wav (str):`
+                Path to the target wav file.
+        """
+        wav = self.voice_converter.voice_conversion(source_wav=source_wav, target_wav=target_wav)
+        return wav
+
+    def voice_conversion_to_file(
+        self,
+        source_wav: str,
+        target_wav: str,
+        file_path: str = "output.wav",
+    ):
+        """Voice conversion with FreeVC. Convert source wav to target speaker.
+
         Args:
             source_wav (str):
                 Path to the source wav file.
             target_wav (str):
                 Path to the target wav file.
+            file_path (str, optional):
+                Output file path. Defaults to "output.wav".
         """
-        wav = self.synthesizer.voice_conversion(source_wav=sourve_wav, target_wav=target_wav)
-        return wav
+        wav = self.voice_conversion(source_wav=source_wav, target_wav=target_wav)
+        save_wav(wav=wav, path=file_path, sample_rate=self.voice_converter.vc_config.audio.output_sample_rate)
+        return file_path
 
     def tts_with_vc(self, text: str, language: str = None, speaker_wav: str = None):
         """Convert text to speech with voice conversion.