x-lance / f5-tts

gen_text: captain teemo, on duty!
ref_text: never underestimate the power of the scout's code
ref_audio: 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.
remove_silence
custom_split_words

{
  "gen_text": "captain teemo, on duty!",
  "ref_text": "never underestimate the power of the scout's code",
  "ref_audio": "https://replicate.delivery/pbxt/LnHEJTVWhjLcpGQJTBralyztLwl8diaLyHjP2a1KXJ8dxVWv/Teemo_Original_Taunt.ogg",
  "remove_silence": true,
  "custom_split_words": ""
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

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

Run x-lance/f5-tts using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "x-lance/f5-tts:105be14651de914ba4dab6bf0fb0cc5d763802e347f1ea8f5f71adc118448a48",
  {
    input: {
      gen_text: "captain teemo, on duty!",
      ref_text: "never underestimate the power of the scout's code",
      ref_audio: "https://replicate.delivery/pbxt/LnHEJTVWhjLcpGQJTBralyztLwl8diaLyHjP2a1KXJ8dxVWv/Teemo_Original_Taunt.ogg",
      remove_silence: true,
      custom_split_words: ""
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", 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

Import the client:

import replicate

Run x-lance/f5-tts using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "x-lance/f5-tts:105be14651de914ba4dab6bf0fb0cc5d763802e347f1ea8f5f71adc118448a48",
    input={
        "gen_text": "captain teemo, on duty!",
        "ref_text": "never underestimate the power of the scout's code",
        "ref_audio": "https://replicate.delivery/pbxt/LnHEJTVWhjLcpGQJTBralyztLwl8diaLyHjP2a1KXJ8dxVWv/Teemo_Original_Taunt.ogg",
        "remove_silence": True,
        "custom_split_words": ""
    }
)
print(output)

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

Run x-lance/f5-tts 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": "105be14651de914ba4dab6bf0fb0cc5d763802e347f1ea8f5f71adc118448a48",
    "input": {
      "gen_text": "captain teemo, on duty!",
      "ref_text": "never underestimate the power of the scout\'s code",
      "ref_audio": "https://replicate.delivery/pbxt/LnHEJTVWhjLcpGQJTBralyztLwl8diaLyHjP2a1KXJ8dxVWv/Teemo_Original_Taunt.ogg",
      "remove_silence": true,
      "custom_split_words": ""
    }
  }' \
  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": "2024-10-14T14:51:37.493607Z",
  "created_at": "2024-10-14T14:51:32.237000Z",
  "data_removed": false,
  "error": null,
  "id": "sp0dk1aj1nrj20cjhe1sn2pzqr",
  "input": {
    "gen_text": "captain teemo, on duty!",
    "ref_text": "never underestimate the power of the scout's code",
    "ref_audio": "https://replicate.delivery/pbxt/LnHEJTVWhjLcpGQJTBralyztLwl8diaLyHjP2a1KXJ8dxVWv/Teemo_Original_Taunt.ogg",
    "remove_silence": true,
    "custom_split_words": ""
  },
  "logs": "Generating: captain teemo, on duty!\n[*] Converting reference audio...\n[+] Converted reference audio.\n[*] Using custom reference text...\n[+] Reference text: never underestimate the power of the scout's code\n[*] Forming batches...\n[+] Formed batches: 1\n------ Batch 1 -------------------\ncaptain teemo, on duty!\n--------------------------------------\n0%|          | 0/1 [00:00<?, ?it/s]Building prefix dict from the default dictionary ...\nDEBUG:jieba:Building prefix dict from the default dictionary ...\nDumping model to file cache /tmp/jieba.cache\nDEBUG:jieba:Dumping model to file cache /tmp/jieba.cache\nLoading model cost 0.494 seconds.\nDEBUG:jieba:Loading model cost 0.494 seconds.\nPrefix dict has been built successfully.\nDEBUG:jieba:Prefix dict has been built successfully.\n/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/vocos/pretrained.py:70: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\nstate_dict = torch.load(model_path, map_location=\"cpu\")\n100%|██████████| 1/1 [00:04<00:00,  4.49s/it]\n100%|██████████| 1/1 [00:04<00:00,  4.49s/it]\n[*] Removing silence...\n[+] Removed silence\n[*] Saving output.wav...\n[+] Saved output.wav",
  "metrics": {
    "predict_time": 5.2457999730000004,
    "total_time": 5.256607
  },
  "output": "https://replicate.delivery/yhqm/Jm39g2brgdYtE5aMvDRXKupUZeNFsGvdmpoHufY3cCo5HumTA/output.wav",
  "started_at": "2024-10-14T14:51:32.247807Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/sp0dk1aj1nrj20cjhe1sn2pzqr",
    "cancel": "https://api.replicate.com/v1/predictions/sp0dk1aj1nrj20cjhe1sn2pzqr/cancel"
  },
  "version": "105be14651de914ba4dab6bf0fb0cc5d763802e347f1ea8f5f71adc118448a48"
}

Generated in

5.3 seconds

Tweak it Share Report

Generating: captain teemo, on duty!
[*] Converting reference audio...
[+] Converted reference audio.
[*] Using custom reference text...
[+] Reference text: never underestimate the power of the scout's code
[*] Forming batches...
[+] Formed batches: 1
------ Batch 1 -------------------
captain teemo, on duty!
--------------------------------------
0%|          | 0/1 [00:00<?, ?it/s]Building prefix dict from the default dictionary ...
DEBUG:jieba:Building prefix dict from the default dictionary ...
Dumping model to file cache /tmp/jieba.cache
DEBUG:jieba:Dumping model to file cache /tmp/jieba.cache
Loading model cost 0.494 seconds.
DEBUG:jieba:Loading model cost 0.494 seconds.
Prefix dict has been built successfully.
DEBUG:jieba:Prefix dict has been built successfully.
/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/vocos/pretrained.py:70: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
state_dict = torch.load(model_path, map_location="cpu")
100%|██████████| 1/1 [00:04<00:00,  4.49s/it]
100%|██████████| 1/1 [00:04<00:00,  4.49s/it]
[*] Removing silence...
[+] Removed silence
[*] Saving output.wav...
[+] Saved output.wav

Prediction

x-lance/f5-tts:87faf6dd7a692dd82043f662e76369cab126a2cf1937e25a9d41e0b834fd230e

Model

x-lance/f5-tts:87faf6dd

yg1pznxdyxrj20cjhezbwjevec

Status

Succeeded

Source

Web

Hardware

A100 (80GB)

Total duration

2.6s

Created

7 months ago

Input

speed: 0.8
gen_text: mix, mix, swirl.
ref_text: never underestimate the power of the scout's code
ref_audio: 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.
remove_silence
custom_split_words

{
  "speed": 0.8,
  "gen_text": "mix, mix, swirl.",
  "ref_text": "never underestimate the power of the scout's code",
  "ref_audio": "https://replicate.delivery/pbxt/LnHEJTVWhjLcpGQJTBralyztLwl8diaLyHjP2a1KXJ8dxVWv/Teemo_Original_Taunt.ogg",
  "remove_silence": true,
  "custom_split_words": ""
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

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

Run x-lance/f5-tts using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "x-lance/f5-tts:87faf6dd7a692dd82043f662e76369cab126a2cf1937e25a9d41e0b834fd230e",
  {
    input: {
      speed: 0.8,
      gen_text: "mix, mix, swirl.",
      ref_text: "never underestimate the power of the scout's code",
      ref_audio: "https://replicate.delivery/pbxt/LnHEJTVWhjLcpGQJTBralyztLwl8diaLyHjP2a1KXJ8dxVWv/Teemo_Original_Taunt.ogg",
      remove_silence: true,
      custom_split_words: ""
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", 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

Import the client:

import replicate

Run x-lance/f5-tts using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "x-lance/f5-tts:87faf6dd7a692dd82043f662e76369cab126a2cf1937e25a9d41e0b834fd230e",
    input={
        "speed": 0.8,
        "gen_text": "mix, mix, swirl.",
        "ref_text": "never underestimate the power of the scout's code",
        "ref_audio": "https://replicate.delivery/pbxt/LnHEJTVWhjLcpGQJTBralyztLwl8diaLyHjP2a1KXJ8dxVWv/Teemo_Original_Taunt.ogg",
        "remove_silence": True,
        "custom_split_words": ""
    }
)
print(output)

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

Run x-lance/f5-tts 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": "87faf6dd7a692dd82043f662e76369cab126a2cf1937e25a9d41e0b834fd230e",
    "input": {
      "speed": 0.8,
      "gen_text": "mix, mix, swirl.",
      "ref_text": "never underestimate the power of the scout\'s code",
      "ref_audio": "https://replicate.delivery/pbxt/LnHEJTVWhjLcpGQJTBralyztLwl8diaLyHjP2a1KXJ8dxVWv/Teemo_Original_Taunt.ogg",
      "remove_silence": true,
      "custom_split_words": ""
    }
  }' \
  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": "2024-10-14T15:56:25.014433Z",
  "created_at": "2024-10-14T15:56:22.391000Z",
  "data_removed": false,
  "error": null,
  "id": "yg1pznxdyxrj20cjhezbwjevec",
  "input": {
    "speed": 0.8,
    "gen_text": "mix, mix, swirl.",
    "ref_text": "never underestimate the power of the scout's code",
    "ref_audio": "https://replicate.delivery/pbxt/LnHEJTVWhjLcpGQJTBralyztLwl8diaLyHjP2a1KXJ8dxVWv/Teemo_Original_Taunt.ogg",
    "remove_silence": true,
    "custom_split_words": ""
  },
  "logs": "Generating: mix, mix, swirl.\n[*] Converting reference audio...\n[+] Converted reference audio.\n[*] Using custom reference text...\n[+] Reference text: never underestimate the power of the scout's code\n[*] Forming batches...\n[+] Formed batches: 1\n------ Batch 1 -------------------\nmix, mix, swirl.\n--------------------------------------\n  0%|          | 0/1 [00:00<?, ?it/s]/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/vocos/pretrained.py:70: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\nstate_dict = torch.load(model_path, map_location=\"cpu\")\n100%|██████████| 1/1 [00:01<00:00,  1.99s/it]\n100%|██████████| 1/1 [00:01<00:00,  1.99s/it]\n[*] Removing silence...\n[+] Removed silence\n[*] Saving output.wav...\n[+] Saved output.wav",
  "metrics": {
    "predict_time": 2.613717814,
    "total_time": 2.623433
  },
  "output": "https://replicate.delivery/yhqm/nDbf0geuLBlxJE1bfoMY12cbxxOrMvF6uNff2th5WBoOl41cC/output.wav",
  "started_at": "2024-10-14T15:56:22.400715Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/yg1pznxdyxrj20cjhezbwjevec",
    "cancel": "https://api.replicate.com/v1/predictions/yg1pznxdyxrj20cjhezbwjevec/cancel"
  },
  "version": "87faf6dd7a692dd82043f662e76369cab126a2cf1937e25a9d41e0b834fd230e"
}

Generated in

2.6 seconds

Tweak it Share Report

Want to make some of these yourself?

Run this model

x-lance / f5-tts

Prediction

Input

Output

Prediction

Input

Output

Logs (sp0dk1aj1nrj20cjhe1sn2pzqr)

Logs (yg1pznxdyxrj20cjhezbwjevec)