Merge pull request #2495 from coqui-ai/api_voice_conversion

Api voice conversion

README.md

@@ -1,10 +1,13 @@
-<img src="https://raw.githubusercontent.com/coqui-ai/TTS/main/images/coqui-log-green-TTS.png" height="56"/>
 
-----
 
-### 📣 Clone your voice with a single click on [🐸Coqui.ai](https://app.coqui.ai/auth/signin)
+## 🐸Coqui.ai News
+- 📣 Coqui Studio API is landed on 🐸TTS. You can use the studio voices in combination with 🐸TTS models. [Example](https://github.com/coqui-ai/TTS/edit/dev/README.md#-python-api)
+- 📣 Voice generation with prompts - **Prompt to Voice** - is live on Coqui.ai!! [Blog Post](https://coqui.ai/blog/tts/prompt-to-voice)
+- 📣 Clone your voice with a single click on [🐸Coqui.ai](https://app.coqui.ai/auth/signin)
+<br>
+
+## <img src="https://raw.githubusercontent.com/coqui-ai/TTS/main/images/coqui-log-green-TTS.png" height="56"/>
 
-----
 
 🐸TTS is a library for advanced Text-to-Speech generation. It's built on the latest research, was designed to achieve the best trade-off among ease-of-training, speed and quality.
 🐸TTS comes with pretrained models, tools for measuring dataset quality and already used in **20+ languages** for products and research projects.
@@ -123,6 +126,9 @@ Underlined "TTS*" and "Judy*" are 🐸TTS models
 - HiFiGAN: [paper](https://arxiv.org/abs/2010.05646)
 - UnivNet: [paper](https://arxiv.org/abs/2106.07889)
 
+### Voice Conversion
+- FreeVC: [paper](https://arxiv.org/abs/2210.15418)
+
 You can also help us implement more models.
 
 ## Install TTS

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"
                 ""
@@ -273,8 +273,11 @@ class TTS:
         self.csapi = None
         self.model_name = None
 
-        if model_name:
-            self.load_tts_model_by_name(model_name, gpu)
+        if model_name is not None:
+            if "tts_models" in model_name or "coqui_studio" 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(
@@ -342,6 +345,7 @@ class TTS:
             model_name (str): Model name to load. You can list models by ```tts.models```.
             gpu (bool, optional): Enable/disable GPU. Some models might be too slow on CPU. Defaults to False.
         """
+        self.model_name = model_name
         model_path, config_path, _, _ = self.download_model_by_name(model_name)
         self.voice_converter = Synthesizer(vc_checkpoint=model_path, vc_config=config_path, use_cuda=gpu)
 
@@ -565,19 +569,39 @@ 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.

TTS/utils/audio/processor.py

@@ -711,7 +711,7 @@ class AudioProcessor(object):
         Args:
             filename (str): Path to the wav file.
         """
-        return librosa.get_duration(path=filename)
+        return librosa.get_duration(filename=filename)
 
     @staticmethod
     def mulaw_encode(wav: np.ndarray, qc: int) -> np.ndarray:

tests/inference_tests/test_python_api.py

@@ -93,3 +93,11 @@ class TTSTest(unittest.TestCase):
         tts = TTS()
         tts.load_tts_model_by_name("tts_models/multilingual/multi-dataset/your_tts")
         tts.tts_to_file("Hello world!", speaker_wav=cloning_test_wav_path, language="en", file_path=OUTPUT_PATH)
+
+    def test_voice_conversion(self):  # pylint: disable=no-self-use
+        tts = TTS(model_name="voice_conversion_models/multilingual/vctk/freevc24", progress_bar=False, gpu=False)
+        tts.voice_conversion_to_file(
+            source_wav=cloning_test_wav_path,
+            target_wav=cloning_test_wav_path,
+            file_path=OUTPUT_PATH,
+        )