Prediction

zsxkib/realistic-voice-cloning:0a9c7c55

Model

zsxkib/realistic-voice-cloning:0a9c7c55

ID

imxvh7jbwwvell3fwpcpxommlm

Status

Succeeded

Source

Web

Hardware

T4

Total duration

1m 34s

Created

over 1 year ago by @zsxkib

Input

protect: 0.5
rvc_model: CUSTOM
index_rate: 1
song_input: Video Player is loading.
Current Time 00:00:000
Duration 00:00:000
Loaded: 0%
Stream Type LIVE
Remaining Time 00:00:000

1x
Chapters
descriptions off, selected
captions settings, opens captions settings dialog
captions off, selected
Beginning of dialog window. Escape will cancel and close the window.
TextColorTransparency
BackgroundColorTransparency
WindowColorTransparency
Font Size
Text Edge Style
Font Family
End of dialog window.
reverb_size: 0.6
pitch_change: female-to-male
rms_mix_rate: 0.8
filter_radius: 3
output_format: mp3
reverb_damping: 0.7
reverb_dryness: 0.8
reverb_wetness: 0.3
crepe_hop_length: 8
pitch_change_all: 0
main_vocals_volume_change: 3
pitch_detection_algorithm: mangio-crepe
instrumental_volume_change: 0
backup_vocals_volume_change: -10
custom_rvc_model_download_url: https://weights.replicate.delivery/default/rvc/SamA.zip

{
  "protect": 0.5,
  "rvc_model": "CUSTOM",
  "index_rate": 1,
  "song_input": "https://replicate.delivery/pbxt/JvgakOpSJzQRSNYymHq2gKmQws48cye3DlCSL55qxu9f5YQt/taylor-trim.mp3",
  "reverb_size": 0.6,
  "pitch_change": "female-to-male",
  "rms_mix_rate": 0.8,
  "filter_radius": 3,
  "output_format": "mp3",
  "reverb_damping": 0.7,
  "reverb_dryness": 0.8,
  "reverb_wetness": 0.3,
  "crepe_hop_length": 8,
  "pitch_change_all": 0,
  "main_vocals_volume_change": 3,
  "pitch_detection_algorithm": "mangio-crepe",
  "instrumental_volume_change": 0,
  "backup_vocals_volume_change": -10,
  "custom_rvc_model_download_url": "https://weights.replicate.delivery/default/rvc/SamA.zip"
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run zsxkib/realistic-voice-cloning using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "zsxkib/realistic-voice-cloning:0a9c7c558af4c0f20667c1bd1260ce32a2879944a0b9e44e1398660c077b1550",
  {
    input: {
      protect: 0.5,
      rvc_model: "CUSTOM",
      index_rate: 1,
      song_input: "https://replicate.delivery/pbxt/JvgakOpSJzQRSNYymHq2gKmQws48cye3DlCSL55qxu9f5YQt/taylor-trim.mp3",
      reverb_size: 0.6,
      pitch_change: "female-to-male",
      rms_mix_rate: 0.8,
      filter_radius: 3,
      output_format: "mp3",
      reverb_damping: 0.7,
      reverb_dryness: 0.8,
      reverb_wetness: 0.3,
      crepe_hop_length: 8,
      pitch_change_all: 0,
      main_vocals_volume_change: 3,
      pitch_detection_algorithm: "mangio-crepe",
      instrumental_volume_change: 0,
      backup_vocals_volume_change: -10,
      custom_rvc_model_download_url: "https://weights.replicate.delivery/default/rvc/SamA.zip"
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run zsxkib/realistic-voice-cloning using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "zsxkib/realistic-voice-cloning:0a9c7c558af4c0f20667c1bd1260ce32a2879944a0b9e44e1398660c077b1550",
    input={
        "protect": 0.5,
        "rvc_model": "CUSTOM",
        "index_rate": 1,
        "song_input": "https://replicate.delivery/pbxt/JvgakOpSJzQRSNYymHq2gKmQws48cye3DlCSL55qxu9f5YQt/taylor-trim.mp3",
        "reverb_size": 0.6,
        "pitch_change": "female-to-male",
        "rms_mix_rate": 0.8,
        "filter_radius": 3,
        "output_format": "mp3",
        "reverb_damping": 0.7,
        "reverb_dryness": 0.8,
        "reverb_wetness": 0.3,
        "crepe_hop_length": 8,
        "pitch_change_all": 0,
        "main_vocals_volume_change": 3,
        "pitch_detection_algorithm": "mangio-crepe",
        "instrumental_volume_change": 0,
        "backup_vocals_volume_change": -10,
        "custom_rvc_model_download_url": "https://weights.replicate.delivery/default/rvc/SamA.zip"
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run zsxkib/realistic-voice-cloning using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "0a9c7c558af4c0f20667c1bd1260ce32a2879944a0b9e44e1398660c077b1550",
    "input": {
      "protect": 0.5,
      "rvc_model": "CUSTOM",
      "index_rate": 1,
      "song_input": "https://replicate.delivery/pbxt/JvgakOpSJzQRSNYymHq2gKmQws48cye3DlCSL55qxu9f5YQt/taylor-trim.mp3",
      "reverb_size": 0.6,
      "pitch_change": "female-to-male",
      "rms_mix_rate": 0.8,
      "filter_radius": 3,
      "output_format": "mp3",
      "reverb_damping": 0.7,
      "reverb_dryness": 0.8,
      "reverb_wetness": 0.3,
      "crepe_hop_length": 8,
      "pitch_change_all": 0,
      "main_vocals_volume_change": 3,
      "pitch_detection_algorithm": "mangio-crepe",
      "instrumental_volume_change": 0,
      "backup_vocals_volume_change": -10,
      "custom_rvc_model_download_url": "https://weights.replicate.delivery/default/rvc/SamA.zip"
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

{
  "completed_at": "2023-11-23T22:35:46.750107Z",
  "created_at": "2023-11-23T22:34:13.064309Z",
  "data_removed": false,
  "error": null,
  "id": "imxvh7jbwwvell3fwpcpxommlm",
  "input": {
    "protect": 0.5,
    "rvc_model": "CUSTOM",
    "index_rate": 1,
    "song_input": "https://replicate.delivery/pbxt/JvgakOpSJzQRSNYymHq2gKmQws48cye3DlCSL55qxu9f5YQt/taylor-trim.mp3",
    "reverb_size": 0.6,
    "pitch_change": "female-to-male",
    "rms_mix_rate": 0.8,
    "filter_radius": 3,
    "output_format": "mp3",
    "reverb_damping": 0.7,
    "reverb_dryness": 0.8,
    "reverb_wetness": 0.3,
    "crepe_hop_length": 8,
    "pitch_change_all": 0,
    "main_vocals_volume_change": 3,
    "pitch_detection_algorithm": "mangio-crepe",
    "instrumental_volume_change": 0,
    "backup_vocals_volume_change": -10,
    "custom_rvc_model_download_url": "https://weights.replicate.delivery/default/rvc/SamA.zip"
  },
  "logs": "[!] The model will be downloaded as 'SamA'.\n[~] Downloading voice model with name SamA...\nVoice model directory SamA already exists! Skipping download.\n[~] Starting AI Cover Generation Pipeline...\n[~] Converting voice using RVC...\n2023-11-23 22:34:13 | INFO | fairseq.tasks.hubert_pretraining | current directory is /src\n2023-11-23 22:34:13 | INFO | fairseq.tasks.hubert_pretraining | HubertPretrainingTask Config {'_name': 'hubert_pretraining', 'data': 'metadata', 'fine_tuning': False, 'labels': ['km'], 'label_dir': 'label', 'label_rate': 50.0, 'sample_rate': 16000, 'normalize': False, 'enable_padding': False, 'max_keep_size': None, 'max_sample_size': 250000, 'min_sample_size': 32000, 'single_target': False, 'random_crop': True, 'pad_audio': False}\n2023-11-23 22:34:13 | INFO | fairseq.models.hubert.hubert | HubertModel Config: {'_name': 'hubert', 'label_rate': 50.0, 'extractor_mode': default, 'encoder_layers': 12, 'encoder_embed_dim': 768, 'encoder_ffn_embed_dim': 3072, 'encoder_attention_heads': 12, 'activation_fn': gelu, 'layer_type': transformer, 'dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'encoder_layerdrop': 0.05, 'dropout_input': 0.1, 'dropout_features': 0.1, 'final_dim': 256, 'untie_final_proj': True, 'layer_norm_first': False, 'conv_feature_layers': '[(512,10,5)] + [(512,3,2)] * 4 + [(512,2,2)] * 2', 'conv_bias': False, 'logit_temp': 0.1, 'target_glu': False, 'feature_grad_mult': 0.1, 'mask_length': 10, 'mask_prob': 0.8, 'mask_selection': static, 'mask_other': 0.0, 'no_mask_overlap': False, 'mask_min_space': 1, 'mask_channel_length': 10, 'mask_channel_prob': 0.0, 'mask_channel_selection': static, 'mask_channel_other': 0.0, 'no_mask_channel_overlap': False, 'mask_channel_min_space': 1, 'conv_pos': 128, 'conv_pos_groups': 16, 'latent_temp': [2.0, 0.5, 0.999995], 'skip_masked': False, 'skip_nomask': False, 'checkpoint_activations': False, 'required_seq_len_multiple': 2, 'depthwise_conv_kernel_size': 31, 'attn_type': '', 'pos_enc_type': 'abs', 'fp16': False}\ngin_channels: 256 self.spk_embed_dim: 109\n<All keys matched successfully>\nInitiating prediction with a crepe_hop_length of: 8\n[~] Applying audio effects to Vocals...\n[~] Combining AI Vocals and Instrumentals...\n[~] Removing intermediate audio files...\n[+] Cover generated at /src/song_output/ba478873b07/tmp4rkutngetaylor-trim (SamA Ver).mp3",
  "metrics": {
    "predict_time": 93.672594,
    "total_time": 93.685798
  },
  "output": "https://replicate.delivery/pbxt/MdNcQoik3A6NCFYm2JWtQIkPVeqRdusuDf7Bok2VvxICXY7RA/tmp4rkutngetaylor-trim%20%28SamA%20Ver%29.mp3",
  "started_at": "2023-11-23T22:34:13.077513Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/imxvh7jbwwvell3fwpcpxommlm",
    "cancel": "https://api.replicate.com/v1/predictions/imxvh7jbwwvell3fwpcpxommlm/cancel"
  },
  "version": "0a9c7c558af4c0f20667c1bd1260ce32a2879944a0b9e44e1398660c077b1550"
}

Generated in

1 minute 34 seconds

Tweak it Share Report

[!] The model will be downloaded as 'SamA'.
[~] Downloading voice model with name SamA...
Voice model directory SamA already exists! Skipping download.
[~] Starting AI Cover Generation Pipeline...
[~] Converting voice using RVC...
2023-11-23 22:34:13 | INFO | fairseq.tasks.hubert_pretraining | current directory is /src
2023-11-23 22:34:13 | INFO | fairseq.tasks.hubert_pretraining | HubertPretrainingTask Config {'_name': 'hubert_pretraining', 'data': 'metadata', 'fine_tuning': False, 'labels': ['km'], 'label_dir': 'label', 'label_rate': 50.0, 'sample_rate': 16000, 'normalize': False, 'enable_padding': False, 'max_keep_size': None, 'max_sample_size': 250000, 'min_sample_size': 32000, 'single_target': False, 'random_crop': True, 'pad_audio': False}
2023-11-23 22:34:13 | INFO | fairseq.models.hubert.hubert | HubertModel Config: {'_name': 'hubert', 'label_rate': 50.0, 'extractor_mode': default, 'encoder_layers': 12, 'encoder_embed_dim': 768, 'encoder_ffn_embed_dim': 3072, 'encoder_attention_heads': 12, 'activation_fn': gelu, 'layer_type': transformer, 'dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'encoder_layerdrop': 0.05, 'dropout_input': 0.1, 'dropout_features': 0.1, 'final_dim': 256, 'untie_final_proj': True, 'layer_norm_first': False, 'conv_feature_layers': '[(512,10,5)] + [(512,3,2)] * 4 + [(512,2,2)] * 2', 'conv_bias': False, 'logit_temp': 0.1, 'target_glu': False, 'feature_grad_mult': 0.1, 'mask_length': 10, 'mask_prob': 0.8, 'mask_selection': static, 'mask_other': 0.0, 'no_mask_overlap': False, 'mask_min_space': 1, 'mask_channel_length': 10, 'mask_channel_prob': 0.0, 'mask_channel_selection': static, 'mask_channel_other': 0.0, 'no_mask_channel_overlap': False, 'mask_channel_min_space': 1, 'conv_pos': 128, 'conv_pos_groups': 16, 'latent_temp': [2.0, 0.5, 0.999995], 'skip_masked': False, 'skip_nomask': False, 'checkpoint_activations': False, 'required_seq_len_multiple': 2, 'depthwise_conv_kernel_size': 31, 'attn_type': '', 'pos_enc_type': 'abs', 'fp16': False}
gin_channels: 256 self.spk_embed_dim: 109
<All keys matched successfully>
Initiating prediction with a crepe_hop_length of: 8
[~] Applying audio effects to Vocals...
[~] Combining AI Vocals and Instrumentals...
[~] Removing intermediate audio files...
[+] Cover generated at /src/song_output/ba478873b07/tmp4rkutngetaylor-trim (SamA Ver).mp3

Prediction

zsxkib/realistic-voice-cloning:0a9c7c55

Model

zsxkib/realistic-voice-cloning:a0076ea1

ID

opfbdorbymurmp2ykemgwe23qa

Status

Succeeded

Source

Web

Hardware

T4

Total duration

2.8s

Created

over 1 year ago

Input

protect: 0.33
rvc_model: Squidward
index_rate: 0.5
song_input: Video Player is loading.
Current Time 00:00:000
Duration 00:00:000
Loaded: 0%
Stream Type LIVE
Remaining Time 00:00:000

1x
Chapters
descriptions off, selected
captions settings, opens captions settings dialog
captions off, selected
Beginning of dialog window. Escape will cancel and close the window.
TextColorTransparency
BackgroundColorTransparency
WindowColorTransparency
Font Size
Text Edge Style
Font Family
End of dialog window.
reverb_size: 0.15
pitch_change: no-change
rms_mix_rate: 0.25
filter_radius: 3
output_format: mp3
reverb_damping: 0.7
reverb_dryness: 0.8
reverb_wetness: 0.2
crepe_hop_length: 128
pitch_change_all: 0
main_vocals_volume_change: 10
pitch_detection_algorithm: rmvpe
instrumental_volume_change: 0
backup_vocals_volume_change: 0

{
  "protect": 0.33,
  "rvc_model": "Squidward",
  "index_rate": 0.5,
  "song_input": "https://replicate.delivery/pbxt/JsPIizFfRy54Jk5LuXdnrNdV1JHJ6oLmPPdRuIfh3lvpoNai/gangnam.mp3",
  "reverb_size": 0.15,
  "pitch_change": "no-change",
  "rms_mix_rate": 0.25,
  "filter_radius": 3,
  "output_format": "mp3",
  "reverb_damping": 0.7,
  "reverb_dryness": 0.8,
  "reverb_wetness": 0.2,
  "crepe_hop_length": 128,
  "pitch_change_all": 0,
  "main_vocals_volume_change": 10,
  "pitch_detection_algorithm": "rmvpe",
  "instrumental_volume_change": 0,
  "backup_vocals_volume_change": 0
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run zsxkib/realistic-voice-cloning using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "zsxkib/realistic-voice-cloning:0a9c7c558af4c0f20667c1bd1260ce32a2879944a0b9e44e1398660c077b1550",
  {
    input: {
      protect: 0.33,
      rvc_model: "Squidward",
      index_rate: 0.5,
      song_input: "https://replicate.delivery/pbxt/JsPIizFfRy54Jk5LuXdnrNdV1JHJ6oLmPPdRuIfh3lvpoNai/gangnam.mp3",
      reverb_size: 0.15,
      pitch_change: "no-change",
      rms_mix_rate: 0.25,
      filter_radius: 3,
      output_format: "mp3",
      reverb_damping: 0.7,
      reverb_dryness: 0.8,
      reverb_wetness: 0.2,
      crepe_hop_length: 128,
      pitch_change_all: 0,
      main_vocals_volume_change: 10,
      pitch_detection_algorithm: "rmvpe",
      instrumental_volume_change: 0,
      backup_vocals_volume_change: 0
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run zsxkib/realistic-voice-cloning using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "zsxkib/realistic-voice-cloning:0a9c7c558af4c0f20667c1bd1260ce32a2879944a0b9e44e1398660c077b1550",
    input={
        "protect": 0.33,
        "rvc_model": "Squidward",
        "index_rate": 0.5,
        "song_input": "https://replicate.delivery/pbxt/JsPIizFfRy54Jk5LuXdnrNdV1JHJ6oLmPPdRuIfh3lvpoNai/gangnam.mp3",
        "reverb_size": 0.15,
        "pitch_change": "no-change",
        "rms_mix_rate": 0.25,
        "filter_radius": 3,
        "output_format": "mp3",
        "reverb_damping": 0.7,
        "reverb_dryness": 0.8,
        "reverb_wetness": 0.2,
        "crepe_hop_length": 128,
        "pitch_change_all": 0,
        "main_vocals_volume_change": 10,
        "pitch_detection_algorithm": "rmvpe",
        "instrumental_volume_change": 0,
        "backup_vocals_volume_change": 0
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run zsxkib/realistic-voice-cloning using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "0a9c7c558af4c0f20667c1bd1260ce32a2879944a0b9e44e1398660c077b1550",
    "input": {
      "protect": 0.33,
      "rvc_model": "Squidward",
      "index_rate": 0.5,
      "song_input": "https://replicate.delivery/pbxt/JsPIizFfRy54Jk5LuXdnrNdV1JHJ6oLmPPdRuIfh3lvpoNai/gangnam.mp3",
      "reverb_size": 0.15,
      "pitch_change": "no-change",
      "rms_mix_rate": 0.25,
      "filter_radius": 3,
      "output_format": "mp3",
      "reverb_damping": 0.7,
      "reverb_dryness": 0.8,
      "reverb_wetness": 0.2,
      "crepe_hop_length": 128,
      "pitch_change_all": 0,
      "main_vocals_volume_change": 10,
      "pitch_detection_algorithm": "rmvpe",
      "instrumental_volume_change": 0,
      "backup_vocals_volume_change": 0
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

Generated in

2.8 seconds

Tweak it Share Report

Prediction

zsxkib/realistic-voice-cloning:0a9c7c55

Model

zsxkib/realistic-voice-cloning:a0076ea1

ID

czmmyuzbky3fcexrpa4wtj5xtm

Status

Succeeded

Source

Web

Hardware

T4

Total duration

15.2s

Created

over 1 year ago by @zsxkib

Input

protect: 0.33
rvc_model: Drake
index_rate: 0.5
song_input: Video Player is loading.
Current Time 00:00:000
Duration 00:00:000
Loaded: 0%
Stream Type LIVE
Remaining Time 00:00:000

1x
Chapters
descriptions off, selected
captions settings, opens captions settings dialog
captions off, selected
Beginning of dialog window. Escape will cancel and close the window.
TextColorTransparency
BackgroundColorTransparency
WindowColorTransparency
Font Size
Text Edge Style
Font Family
End of dialog window.
reverb_size: 0.15
pitch_change: no-change
rms_mix_rate: 0.25
filter_radius: 3
output_format: mp3
reverb_damping: 0.7
reverb_dryness: 0.8
reverb_wetness: 0.2
crepe_hop_length: 128
pitch_change_all: 0
main_vocals_volume_change: 10
pitch_detection_algorithm: rmvpe
instrumental_volume_change: 0
backup_vocals_volume_change: 0
custom_rvc_model_download_url: https://huggingface.co/QuickWick/Music-AI-Voices/resolve/main/Drake%20(RVC)%20Unknown%20Steps/Drake%20(RVC)%20Unknown.zip?download=true
custom_rvc_model_download_name: Drake

{
  "protect": 0.33,
  "rvc_model": "Drake",
  "index_rate": 0.5,
  "song_input": "https://replicate.delivery/pbxt/JsPKaofgQCRLKdATUj55amn131wSNMTl3pYYbJ7oUNAR2cV3/gangnam.mp3",
  "reverb_size": 0.15,
  "pitch_change": "no-change",
  "rms_mix_rate": 0.25,
  "filter_radius": 3,
  "output_format": "mp3",
  "reverb_damping": 0.7,
  "reverb_dryness": 0.8,
  "reverb_wetness": 0.2,
  "crepe_hop_length": 128,
  "pitch_change_all": 0,
  "main_vocals_volume_change": 10,
  "pitch_detection_algorithm": "rmvpe",
  "instrumental_volume_change": 0,
  "backup_vocals_volume_change": 0,
  "custom_rvc_model_download_url": "https://huggingface.co/QuickWick/Music-AI-Voices/resolve/main/Drake%20(RVC)%20Unknown%20Steps/Drake%20(RVC)%20Unknown.zip?download=true",
  "custom_rvc_model_download_name": "Drake"
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run zsxkib/realistic-voice-cloning using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "zsxkib/realistic-voice-cloning:0a9c7c558af4c0f20667c1bd1260ce32a2879944a0b9e44e1398660c077b1550",
  {
    input: {
      protect: 0.33,
      rvc_model: "Drake",
      index_rate: 0.5,
      song_input: "https://replicate.delivery/pbxt/JsPKaofgQCRLKdATUj55amn131wSNMTl3pYYbJ7oUNAR2cV3/gangnam.mp3",
      reverb_size: 0.15,
      pitch_change: "no-change",
      rms_mix_rate: 0.25,
      filter_radius: 3,
      output_format: "mp3",
      reverb_damping: 0.7,
      reverb_dryness: 0.8,
      reverb_wetness: 0.2,
      crepe_hop_length: 128,
      pitch_change_all: 0,
      main_vocals_volume_change: 10,
      pitch_detection_algorithm: "rmvpe",
      instrumental_volume_change: 0,
      backup_vocals_volume_change: 0,
      custom_rvc_model_download_url: "https://huggingface.co/QuickWick/Music-AI-Voices/resolve/main/Drake%20(RVC)%20Unknown%20Steps/Drake%20(RVC)%20Unknown.zip?download=true"
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run zsxkib/realistic-voice-cloning using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "zsxkib/realistic-voice-cloning:0a9c7c558af4c0f20667c1bd1260ce32a2879944a0b9e44e1398660c077b1550",
    input={
        "protect": 0.33,
        "rvc_model": "Drake",
        "index_rate": 0.5,
        "song_input": "https://replicate.delivery/pbxt/JsPKaofgQCRLKdATUj55amn131wSNMTl3pYYbJ7oUNAR2cV3/gangnam.mp3",
        "reverb_size": 0.15,
        "pitch_change": "no-change",
        "rms_mix_rate": 0.25,
        "filter_radius": 3,
        "output_format": "mp3",
        "reverb_damping": 0.7,
        "reverb_dryness": 0.8,
        "reverb_wetness": 0.2,
        "crepe_hop_length": 128,
        "pitch_change_all": 0,
        "main_vocals_volume_change": 10,
        "pitch_detection_algorithm": "rmvpe",
        "instrumental_volume_change": 0,
        "backup_vocals_volume_change": 0,
        "custom_rvc_model_download_url": "https://huggingface.co/QuickWick/Music-AI-Voices/resolve/main/Drake%20(RVC)%20Unknown%20Steps/Drake%20(RVC)%20Unknown.zip?download=true"
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run zsxkib/realistic-voice-cloning using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "0a9c7c558af4c0f20667c1bd1260ce32a2879944a0b9e44e1398660c077b1550",
    "input": {
      "protect": 0.33,
      "rvc_model": "Drake",
      "index_rate": 0.5,
      "song_input": "https://replicate.delivery/pbxt/JsPKaofgQCRLKdATUj55amn131wSNMTl3pYYbJ7oUNAR2cV3/gangnam.mp3",
      "reverb_size": 0.15,
      "pitch_change": "no-change",
      "rms_mix_rate": 0.25,
      "filter_radius": 3,
      "output_format": "mp3",
      "reverb_damping": 0.7,
      "reverb_dryness": 0.8,
      "reverb_wetness": 0.2,
      "crepe_hop_length": 128,
      "pitch_change_all": 0,
      "main_vocals_volume_change": 10,
      "pitch_detection_algorithm": "rmvpe",
      "instrumental_volume_change": 0,
      "backup_vocals_volume_change": 0,
      "custom_rvc_model_download_url": "https://huggingface.co/QuickWick/Music-AI-Voices/resolve/main/Drake%20(RVC)%20Unknown%20Steps/Drake%20(RVC)%20Unknown.zip?download=true"
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

{
  "completed_at": "2023-11-14T16:54:32.313003Z",
  "created_at": "2023-11-14T16:54:17.086359Z",
  "data_removed": false,
  "error": null,
  "id": "czmmyuzbky3fcexrpa4wtj5xtm",
  "input": {
    "protect": 0.33,
    "rvc_model": "Drake",
    "index_rate": 0.5,
    "song_input": "https://replicate.delivery/pbxt/JsPKaofgQCRLKdATUj55amn131wSNMTl3pYYbJ7oUNAR2cV3/gangnam.mp3",
    "reverb_size": 0.15,
    "pitch_change": "no-change",
    "rms_mix_rate": 0.25,
    "filter_radius": 3,
    "output_format": "mp3",
    "reverb_damping": 0.7,
    "reverb_dryness": 0.8,
    "reverb_wetness": 0.2,
    "crepe_hop_length": 128,
    "pitch_change_all": 0,
    "main_vocals_volume_change": 10,
    "pitch_detection_algorithm": "rmvpe",
    "instrumental_volume_change": 0,
    "backup_vocals_volume_change": 0,
    "custom_rvc_model_download_url": "https://huggingface.co/QuickWick/Music-AI-Voices/resolve/main/Drake%20(RVC)%20Unknown%20Steps/Drake%20(RVC)%20Unknown.zip?download=true",
    "custom_rvc_model_download_name": "Drake"
  },
  "logs": "[!] The model will be downloaded as 'Drake'. To use it, you'll need to match it on 'rvc_model'.\n[~] Downloading voice model with name Drake...\n[~] Extracting zip...\n[+] Drake Model successfully downloaded!\n[~] Starting AI Cover Generation Pipeline...\n[~] Converting voice using RVC...\n2023-11-14 16:54:22 | INFO | fairseq.tasks.hubert_pretraining | current directory is /src\n2023-11-14 16:54:22 | INFO | fairseq.tasks.hubert_pretraining | HubertPretrainingTask Config {'_name': 'hubert_pretraining', 'data': 'metadata', 'fine_tuning': False, 'labels': ['km'], 'label_dir': 'label', 'label_rate': 50.0, 'sample_rate': 16000, 'normalize': False, 'enable_padding': False, 'max_keep_size': None, 'max_sample_size': 250000, 'min_sample_size': 32000, 'single_target': False, 'random_crop': True, 'pad_audio': False}\n2023-11-14 16:54:22 | INFO | fairseq.models.hubert.hubert | HubertModel Config: {'_name': 'hubert', 'label_rate': 50.0, 'extractor_mode': default, 'encoder_layers': 12, 'encoder_embed_dim': 768, 'encoder_ffn_embed_dim': 3072, 'encoder_attention_heads': 12, 'activation_fn': gelu, 'layer_type': transformer, 'dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'encoder_layerdrop': 0.05, 'dropout_input': 0.1, 'dropout_features': 0.1, 'final_dim': 256, 'untie_final_proj': True, 'layer_norm_first': False, 'conv_feature_layers': '[(512,10,5)] + [(512,3,2)] * 4 + [(512,2,2)] * 2', 'conv_bias': False, 'logit_temp': 0.1, 'target_glu': False, 'feature_grad_mult': 0.1, 'mask_length': 10, 'mask_prob': 0.8, 'mask_selection': static, 'mask_other': 0.0, 'no_mask_overlap': False, 'mask_min_space': 1, 'mask_channel_length': 10, 'mask_channel_prob': 0.0, 'mask_channel_selection': static, 'mask_channel_other': 0.0, 'no_mask_channel_overlap': False, 'mask_channel_min_space': 1, 'conv_pos': 128, 'conv_pos_groups': 16, 'latent_temp': [2.0, 0.5, 0.999995], 'skip_masked': False, 'skip_nomask': False, 'checkpoint_activations': False, 'required_seq_len_multiple': 2, 'depthwise_conv_kernel_size': 31, 'attn_type': '', 'pos_enc_type': 'abs', 'fp16': False}\ngin_channels: 256 self.spk_embed_dim: 109\n<All keys matched successfully>\n[~] Applying audio effects to Vocals...\n[~] Combining AI Vocals and Instrumentals...\n[~] Removing intermediate audio files...\n[+] Cover generated at /src/song_output/d0386572142/tmp11cudxj_gangnam (Drake Ver).mp3",
  "metrics": {
    "predict_time": 15.203292,
    "total_time": 15.226644
  },
  "output": "https://replicate.delivery/pbxt/lLemP3Q7Wm3wJSe1LYUGwO4U9sJgsuTx9b8SsbyCUwkHhV4RA/tmp11cudxj_gangnam%20%28Drake%20Ver%29.mp3",
  "started_at": "2023-11-14T16:54:17.109711Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/czmmyuzbky3fcexrpa4wtj5xtm",
    "cancel": "https://api.replicate.com/v1/predictions/czmmyuzbky3fcexrpa4wtj5xtm/cancel"
  },
  "version": "a0076ea13a704d9fa6d02535bc8951d3b141c84dc95d2d3f2f5016eabfcb8d94"
}

Generated in

15.2 seconds

Tweak it Share Report

[!] The model will be downloaded as 'Drake'. To use it, you'll need to match it on 'rvc_model'.
[~] Downloading voice model with name Drake...
[~] Extracting zip...
[+] Drake Model successfully downloaded!
[~] Starting AI Cover Generation Pipeline...
[~] Converting voice using RVC...
2023-11-14 16:54:22 | INFO | fairseq.tasks.hubert_pretraining | current directory is /src
2023-11-14 16:54:22 | INFO | fairseq.tasks.hubert_pretraining | HubertPretrainingTask Config {'_name': 'hubert_pretraining', 'data': 'metadata', 'fine_tuning': False, 'labels': ['km'], 'label_dir': 'label', 'label_rate': 50.0, 'sample_rate': 16000, 'normalize': False, 'enable_padding': False, 'max_keep_size': None, 'max_sample_size': 250000, 'min_sample_size': 32000, 'single_target': False, 'random_crop': True, 'pad_audio': False}
2023-11-14 16:54:22 | INFO | fairseq.models.hubert.hubert | HubertModel Config: {'_name': 'hubert', 'label_rate': 50.0, 'extractor_mode': default, 'encoder_layers': 12, 'encoder_embed_dim': 768, 'encoder_ffn_embed_dim': 3072, 'encoder_attention_heads': 12, 'activation_fn': gelu, 'layer_type': transformer, 'dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'encoder_layerdrop': 0.05, 'dropout_input': 0.1, 'dropout_features': 0.1, 'final_dim': 256, 'untie_final_proj': True, 'layer_norm_first': False, 'conv_feature_layers': '[(512,10,5)] + [(512,3,2)] * 4 + [(512,2,2)] * 2', 'conv_bias': False, 'logit_temp': 0.1, 'target_glu': False, 'feature_grad_mult': 0.1, 'mask_length': 10, 'mask_prob': 0.8, 'mask_selection': static, 'mask_other': 0.0, 'no_mask_overlap': False, 'mask_min_space': 1, 'mask_channel_length': 10, 'mask_channel_prob': 0.0, 'mask_channel_selection': static, 'mask_channel_other': 0.0, 'no_mask_channel_overlap': False, 'mask_channel_min_space': 1, 'conv_pos': 128, 'conv_pos_groups': 16, 'latent_temp': [2.0, 0.5, 0.999995], 'skip_masked': False, 'skip_nomask': False, 'checkpoint_activations': False, 'required_seq_len_multiple': 2, 'depthwise_conv_kernel_size': 31, 'attn_type': '', 'pos_enc_type': 'abs', 'fp16': False}
gin_channels: 256 self.spk_embed_dim: 109
<All keys matched successfully>
[~] Applying audio effects to Vocals...
[~] Combining AI Vocals and Instrumentals...
[~] Removing intermediate audio files...
[+] Cover generated at /src/song_output/d0386572142/tmp11cudxj_gangnam (Drake Ver).mp3

Prediction

zsxkib/realistic-voice-cloning:0a9c7c55

Model

zsxkib/realistic-voice-cloning:a0076ea1

ID

2pz4qhjbss3u2wghs4ply4ddxq

Status

Succeeded

Source

Web

Hardware

T4

Total duration

1.9s

Created

over 1 year ago by @zsxkib

Input

protect: 0.33
rvc_model: Trump
index_rate: 0.5
song_input: Video Player is loading.
Current Time 00:00:000
Duration 00:00:000
Loaded: 0%
Stream Type LIVE
Remaining Time 00:00:000

1x
Chapters
descriptions off, selected
captions settings, opens captions settings dialog
captions off, selected
Beginning of dialog window. Escape will cancel and close the window.
TextColorTransparency
BackgroundColorTransparency
WindowColorTransparency
Font Size
Text Edge Style
Font Family
End of dialog window.
reverb_size: 0.15
pitch_change: no-change
rms_mix_rate: 0.25
filter_radius: 3
output_format: mp3
reverb_damping: 0.7
reverb_dryness: 0.8
reverb_wetness: 0.2
crepe_hop_length: 128
pitch_change_all: 0
main_vocals_volume_change: 3
pitch_detection_algorithm: rmvpe
instrumental_volume_change: 0
backup_vocals_volume_change: 0
custom_rvc_model_download_url: https://huggingface.co/0x3e9/0x3e9_RVC_models/resolve/main/trump.zip
custom_rvc_model_download_name: Trump

{
  "protect": 0.33,
  "rvc_model": "Trump",
  "index_rate": 0.5,
  "song_input": "https://replicate.delivery/pbxt/JsPlGg4HNPYrcOqxDfu3ANm1pK5JntJgVwg30Yd8cV9jBVFN/number-15-burger-king-foot-lettuce.mp3",
  "reverb_size": 0.15,
  "pitch_change": "no-change",
  "rms_mix_rate": 0.25,
  "filter_radius": 3,
  "output_format": "mp3",
  "reverb_damping": 0.7,
  "reverb_dryness": 0.8,
  "reverb_wetness": 0.2,
  "crepe_hop_length": 128,
  "pitch_change_all": 0,
  "main_vocals_volume_change": 3,
  "pitch_detection_algorithm": "rmvpe",
  "instrumental_volume_change": 0,
  "backup_vocals_volume_change": 0,
  "custom_rvc_model_download_url": "https://huggingface.co/0x3e9/0x3e9_RVC_models/resolve/main/trump.zip",
  "custom_rvc_model_download_name": "Trump"
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run zsxkib/realistic-voice-cloning using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "zsxkib/realistic-voice-cloning:0a9c7c558af4c0f20667c1bd1260ce32a2879944a0b9e44e1398660c077b1550",
  {
    input: {
      protect: 0.33,
      rvc_model: "Trump",
      index_rate: 0.5,
      song_input: "https://replicate.delivery/pbxt/JsPlGg4HNPYrcOqxDfu3ANm1pK5JntJgVwg30Yd8cV9jBVFN/number-15-burger-king-foot-lettuce.mp3",
      reverb_size: 0.15,
      pitch_change: "no-change",
      rms_mix_rate: 0.25,
      filter_radius: 3,
      output_format: "mp3",
      reverb_damping: 0.7,
      reverb_dryness: 0.8,
      reverb_wetness: 0.2,
      crepe_hop_length: 128,
      pitch_change_all: 0,
      main_vocals_volume_change: 3,
      pitch_detection_algorithm: "rmvpe",
      instrumental_volume_change: 0,
      backup_vocals_volume_change: 0,
      custom_rvc_model_download_url: "https://huggingface.co/0x3e9/0x3e9_RVC_models/resolve/main/trump.zip"
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run zsxkib/realistic-voice-cloning using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "zsxkib/realistic-voice-cloning:0a9c7c558af4c0f20667c1bd1260ce32a2879944a0b9e44e1398660c077b1550",
    input={
        "protect": 0.33,
        "rvc_model": "Trump",
        "index_rate": 0.5,
        "song_input": "https://replicate.delivery/pbxt/JsPlGg4HNPYrcOqxDfu3ANm1pK5JntJgVwg30Yd8cV9jBVFN/number-15-burger-king-foot-lettuce.mp3",
        "reverb_size": 0.15,
        "pitch_change": "no-change",
        "rms_mix_rate": 0.25,
        "filter_radius": 3,
        "output_format": "mp3",
        "reverb_damping": 0.7,
        "reverb_dryness": 0.8,
        "reverb_wetness": 0.2,
        "crepe_hop_length": 128,
        "pitch_change_all": 0,
        "main_vocals_volume_change": 3,
        "pitch_detection_algorithm": "rmvpe",
        "instrumental_volume_change": 0,
        "backup_vocals_volume_change": 0,
        "custom_rvc_model_download_url": "https://huggingface.co/0x3e9/0x3e9_RVC_models/resolve/main/trump.zip"
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run zsxkib/realistic-voice-cloning using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "0a9c7c558af4c0f20667c1bd1260ce32a2879944a0b9e44e1398660c077b1550",
    "input": {
      "protect": 0.33,
      "rvc_model": "Trump",
      "index_rate": 0.5,
      "song_input": "https://replicate.delivery/pbxt/JsPlGg4HNPYrcOqxDfu3ANm1pK5JntJgVwg30Yd8cV9jBVFN/number-15-burger-king-foot-lettuce.mp3",
      "reverb_size": 0.15,
      "pitch_change": "no-change",
      "rms_mix_rate": 0.25,
      "filter_radius": 3,
      "output_format": "mp3",
      "reverb_damping": 0.7,
      "reverb_dryness": 0.8,
      "reverb_wetness": 0.2,
      "crepe_hop_length": 128,
      "pitch_change_all": 0,
      "main_vocals_volume_change": 3,
      "pitch_detection_algorithm": "rmvpe",
      "instrumental_volume_change": 0,
      "backup_vocals_volume_change": 0,
      "custom_rvc_model_download_url": "https://huggingface.co/0x3e9/0x3e9_RVC_models/resolve/main/trump.zip"
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

{
  "completed_at": "2023-11-14T17:22:28.282817Z",
  "created_at": "2023-11-14T17:22:26.382065Z",
  "data_removed": false,
  "error": null,
  "id": "2pz4qhjbss3u2wghs4ply4ddxq",
  "input": {
    "protect": 0.33,
    "rvc_model": "Trump",
    "index_rate": 0.5,
    "song_input": "https://replicate.delivery/pbxt/JsPlGg4HNPYrcOqxDfu3ANm1pK5JntJgVwg30Yd8cV9jBVFN/number-15-burger-king-foot-lettuce.mp3",
    "reverb_size": 0.15,
    "pitch_change": "no-change",
    "rms_mix_rate": 0.25,
    "filter_radius": 3,
    "output_format": "mp3",
    "reverb_damping": 0.7,
    "reverb_dryness": 0.8,
    "reverb_wetness": 0.2,
    "crepe_hop_length": 128,
    "pitch_change_all": 0,
    "main_vocals_volume_change": 3,
    "pitch_detection_algorithm": "rmvpe",
    "instrumental_volume_change": 0,
    "backup_vocals_volume_change": 0,
    "custom_rvc_model_download_url": "https://huggingface.co/0x3e9/0x3e9_RVC_models/resolve/main/trump.zip",
    "custom_rvc_model_download_name": "Trump"
  },
  "logs": "[!] The model will be downloaded as 'Trump'. To use it, you'll need to match it on 'rvc_model'.\n[~] Downloading voice model with name Trump...\nVoice model directory Trump already exists! Skipping download.\n[~] Starting AI Cover Generation Pipeline...\n[~] Applying audio effects to Vocals...\n[~] Combining AI Vocals and Instrumentals...\n[~] Removing intermediate audio files...\n[+] Cover generated at /src/song_output/897478c94e0/tmp_t9sx107number-15-burger-king-foot-lettuce (Trump Ver).mp3",
  "metrics": {
    "predict_time": 1.879513,
    "total_time": 1.900752
  },
  "output": "https://replicate.delivery/pbxt/AgbkhkuFvZokJNtwoQLAcgeOCcWYCtBBeVJNyw0vLRfo2rwjA/tmp_t9sx107number-15-burger-king-foot-lettuce%20%28Trump%20Ver%29.mp3",
  "started_at": "2023-11-14T17:22:26.403304Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/2pz4qhjbss3u2wghs4ply4ddxq",
    "cancel": "https://api.replicate.com/v1/predictions/2pz4qhjbss3u2wghs4ply4ddxq/cancel"
  },
  "version": "a0076ea13a704d9fa6d02535bc8951d3b141c84dc95d2d3f2f5016eabfcb8d94"
}

Generated in

1.9 seconds

Tweak it Share Report

zsxkib / realistic-voice-cloning

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Logs (imxvh7jbwwvell3fwpcpxommlm)

Logs (opfbdorbymurmp2ykemgwe23qa)

Logs (czmmyuzbky3fcexrpa4wtj5xtm)

Logs (2pz4qhjbss3u2wghs4ply4ddxq)