AttributeError: 'tuple' object has no attribute 'dtype'

[JordanGreenDog]

When I run, I get "AttributeError: 'tuple' object has no attribute 'dtype'".
I have Python 3.10 (venv) on Windows.

Output:
2025-08-15 20:31:42 | INFO | tts_with_rvc.infer.vc.config | No supported Nvidia GPU found, using CPU
2025-08-15 20:31:42 | INFO | tts_with_rvc.infer.vc.config | Half-precision floating-point: False, device: cpu
2025-08-15 20:31:42 | INFO | tts_with_rvc.inference | Index path: D:\Driveline D\AI Text - Voice to Speech\RVC-Models\Ni Hao Kai Lan RVC\WeightsGG\Promo Kai-Lan\Kai-Lan\added_IVF568_Flat_nprobe_1_Kai-Lan_v2.index
2025-08-15 20:31:43 | INFO | tts_with_rvc.infer.vc.modules | Get sid: D:\Driveline D\AI Text - Voice to Speech\RVC-Models\Ni Hao Kai Lan RVC\WeightsGG\Promo Kai-Lan\Kai-Lan\Kai-Lan.pth
2025-08-15 20:31:43 | INFO | tts_with_rvc.infer.vc.modules | Loading: D:\Driveline D\AI Text - Voice to Speech\RVC-Models\Ni Hao Kai Lan RVC\WeightsGG\Promo Kai-Lan\Kai-Lan\Kai-Lan.pth
Traceback (most recent call last):
File "D:\Transfers E\Camera Roll - Copy\VSCode 2026\Easy TTS\venv\lib\site-packages\tts_with_rvc\infer\lib\audio.py", line 44, in load_audio
ffmpeg.input(file, threads=0)
File "D:\Transfers E\Camera Roll - Copy\VSCode 2026\Easy TTS\venv\lib\site-packages\ffmpeg_run.py", line 313, in run
process = run_async(
File "D:\Transfers E\Camera Roll - Copy\VSCode 2026\Easy TTS\venv\lib\site-packages\ffmpeg_run.py", line 284, in run_async
return subprocess.Popen(
File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\subprocess.py", line 971, in init
self._execute_child(args, executable, preexec_fn, close_fds,
File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\subprocess.py", line 1456, in _execute_child
hp, ht, pid, tid = _winapi.CreateProcess(executable, args,
FileNotFoundError: [WinError 2] The system cannot find the file specified
2025-08-15 20:31:44 | WARNING | tts_with_rvc.infer.vc.modules | Traceback (most recent call last):
File "D:\Transfers E\Camera Roll - Copy\VSCode 2026\Easy TTS\venv\lib\site-packages\tts_with_rvc\infer\lib\audio.py", line 44, in load_audio
ffmpeg.input(file, threads=0)
File "D:\Transfers E\Camera Roll - Copy\VSCode 2026\Easy TTS\venv\lib\site-packages\ffmpeg_run.py", line 313, in run
process = run_async(
File "D:\Transfers E\Camera Roll - Copy\VSCode 2026\Easy TTS\venv\lib\site-packages\ffmpeg_run.py", line 284, in run_async
return subprocess.Popen(
File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\subprocess.py", line 971, in init
self._execute_child(args, executable, preexec_fn, close_fds,
File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\subprocess.py", line 1456, in _execute_child
hp, ht, pid, tid = _winapi.CreateProcess(executable, args,
FileNotFoundError: [WinError 2] The system cannot find the file specified

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "D:\Transfers E\Camera Roll - Copy\VSCode 2026\Easy TTS\venv\lib\site-packages\tts_with_rvc\infer\vc\modules.py", line 138, in vc_single
audio = load_audio(input_audio_path, 16000)
File "D:\Transfers E\Camera Roll - Copy\VSCode 2026\Easy TTS\venv\lib\site-packages\tts_with_rvc\infer\lib\audio.py", line 50, in load_audio
raise RuntimeError(f"Failed to load audio: {e}")
RuntimeError: Failed to load audio: [WinError 2] The system cannot find the file specified

Traceback (most recent call last):
File "d:\Transfers E\Camera Roll - Copy\VSCode 2026\Easy TTS\RVC-gTTS_session1a.py", line 8, in
path = tts(text="""Привет, мир.""", pitch=6, index_rate=1)
File "D:\Transfers E\Camera Roll - Copy\VSCode 2026\Easy TTS\venv\lib\site-packages\tts_with_rvc\inference.py", line 144, in call
verbose=verbose)).result())
File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\concurrent\futures_base.py", line 458, in result
return self.__get_result()
File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\concurrent\futures_base.py", line 403, in __get_result
raise self._exception
File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\concurrent\futures\thread.py", line 58, in run
result = self.fn(*self.args, **self.kwargs)
File "D:\Transfers E\Camera Roll - Copy\VSCode 2026\Easy TTS\venv\lib\site-packages\nest_asyncio.py", line 30, in run
return loop.run_until_complete(task)
File "D:\Transfers E\Camera Roll - Copy\VSCode 2026\Easy TTS\venv\lib\site-packages\nest_asyncio.py", line 98, in run_until_complete
return f.result()
File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\asyncio\futures.py", line 201, in result
raise self._exception.with_traceback(self._exception_tb)
File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\asyncio\tasks.py", line 232, in __step
result = coro.send(None)
File "D:\Transfers E\Camera Roll - Copy\VSCode 2026\Easy TTS\venv\lib\site-packages\tts_with_rvc\inference.py", line 295, in speech
output_path = rvc_convert(
File "D:\Transfers E\Camera Roll - Copy\VSCode 2026\Easy TTS\venv\lib\site-packages\tts_with_rvc\vc_infer.py", line 137, in rvc_convert
wavfile.write(output_file_path, tgt_sr, opt_wav)
File "D:\Transfers E\Camera Roll - Copy\VSCode 2026\Easy TTS\venv\lib\site-packages\scipy\io\wavfile.py", line 798, in write
dkind = data.dtype.kind
AttributeError: 'tuple' object has no attribute 'dtype'

My code:
from tts_with_rvc import TTS_RVC

tts = TTS_RVC(
model_path="D:\Driveline D\AI Text - Voice to Speech\RVC-Models\Ni Hao Kai Lan RVC\WeightsGG\Promo Kai-Lan\Kai-Lan\Kai-Lan.pth",
index_path="D:\Driveline D\AI Text - Voice to Speech\RVC-Models\Ni Hao Kai Lan RVC\WeightsGG\Promo Kai-Lan\Kai-Lan\added_IVF568_Flat_nprobe_1_Kai-Lan_v2.index")

tts.set_voice("ru-RU-SvetlanaNeural")
path = tts(text="""Привет, мир.""", pitch=6, index_rate=1)

output_directory = ("D:\Transfers E\Camera Roll - Copy\VSCode 2026\Easy TTS\outputs\tests")
output_filename = ("output_test1.wav")

[Atm4x]

@JordanGreenDog Hi, have you installed ffmpeg and put it to the root folder of your project? The exception occures most likely because it hasn't found the ffmpeg. Please share more information about it and be sure you followed these steps: https://github.com/Atm4x/tts-with-rvc?tab=readme-ov-file#installation

Also I noticed you are using CPU instead of GPU. If you have NVIDIA gpu then it's better to use Cuda, if you have AMD I would recommend to use onnx version of package: https://github.com/Atm4x/tts-with-rvc/tree/onnx

[JordanGreenDog]

Oh! Okay. Now, how to add ffmpeg to the Environment variables in the Path?

[Atm4x]

Oh! Okay. Now, how to add ffmpeg to the Environment variables in the Path?

@JordanGreenDog, You don't have to do it if ffmpeg.exe file is in your project root, but if you want to do it or exceptions occur, then here it is: https://phoenixnap.com/kb/ffmpeg-windows