cjwbw/melotts:ac8dc5ff | Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

cjwbw /melotts:ac8dc5ff

Playground API

Input

Run this model in Node.js with one line of code:

npx create-replicate --model=cjwbw/melotts

or set up a project from scratch

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";
import fs from "node:fs";

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

Run cjwbw/melotts using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "cjwbw/melotts:ac8dc5ff8d04a44bb43dfce7599dd128bcbf81f3e9f6faee74f8a6d6f2bfb688",
  {
    input: {
      text: "The field of text-to-speech has seen rapid development recently.",
      speed: 1,
      speaker: "EN-BR",
      language: "EN"
    }
  }
);

// 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

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 cjwbw/melotts using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "cjwbw/melotts:ac8dc5ff8d04a44bb43dfce7599dd128bcbf81f3e9f6faee74f8a6d6f2bfb688",
    input={
        "text": "The field of text-to-speech has seen rapid development recently.",
        "speed": 1,
        "speaker": "EN-BR",
        "language": "EN"
    }
)
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 cjwbw/melotts 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": "cjwbw/melotts:ac8dc5ff8d04a44bb43dfce7599dd128bcbf81f3e9f6faee74f8a6d6f2bfb688",
    "input": {
      "text": "The field of text-to-speech has seen rapid development recently.",
      "speed": 1,
      "speaker": "EN-BR",
      "language": "EN"
    }
  }' \
  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": "2024-03-03T01:13:33.471124Z",
  "created_at": "2024-03-03T01:10:34.653158Z",
  "data_removed": false,
  "error": null,
  "id": "jmssl4zb5vsqvdjdcfpkxzjzwi",
  "input": {
    "text": "The field of text-to-speech has seen rapid development recently.",
    "speed": 1,
    "speaker": "EN-BR",
    "language": "EN"
  },
  "logs": "> Text split to sentences.\nThe field of text-to-speech has seen rapid development recently.\n> ===========================\n  0%|          | 0/1 [00:00<?, ?it/s]\nmodel.safetensors:   0%|          | 0.00/440M [00:00<?, ?B/s]\u001b[A\nmodel.safetensors:   2%|▏         | 10.5M/440M [00:00<00:04, 96.0MB/s]\u001b[A\nmodel.safetensors:   7%|▋         | 31.5M/440M [00:00<00:02, 143MB/s] \u001b[A\nmodel.safetensors:  12%|█▏        | 52.4M/440M [00:00<00:02, 159MB/s]\u001b[A\nmodel.safetensors:  17%|█▋        | 73.4M/440M [00:00<00:02, 167MB/s]\u001b[A\nmodel.safetensors:  21%|██▏       | 94.4M/440M [00:00<00:02, 172MB/s]\u001b[A\nmodel.safetensors:  26%|██▌       | 115M/440M [00:00<00:01, 178MB/s] \u001b[A\nmodel.safetensors:  31%|███       | 136M/440M [00:00<00:01, 180MB/s]\u001b[A\nmodel.safetensors:  36%|███▌      | 157M/440M [00:00<00:01, 182MB/s]\u001b[A\nmodel.safetensors:  40%|████      | 178M/440M [00:01<00:01, 183MB/s]\u001b[A\nmodel.safetensors:  45%|████▌     | 199M/440M [00:01<00:01, 182MB/s]\u001b[A\nmodel.safetensors:  50%|████▉     | 220M/440M [00:01<00:01, 183MB/s]\u001b[A\nmodel.safetensors:  55%|█████▍    | 241M/440M [00:01<00:01, 183MB/s]\u001b[A\nmodel.safetensors:  60%|█████▉    | 262M/440M [00:01<00:00, 184MB/s]\u001b[A\nmodel.safetensors:  64%|██████▍   | 283M/440M [00:01<00:00, 184MB/s]\u001b[A\nmodel.safetensors:  69%|██████▉   | 304M/440M [00:01<00:00, 185MB/s]\u001b[A\nmodel.safetensors:  74%|███████▍  | 325M/440M [00:01<00:00, 184MB/s]\u001b[A\nmodel.safetensors:  79%|███████▊  | 346M/440M [00:01<00:00, 184MB/s]\u001b[A\nmodel.safetensors:  83%|████████▎ | 367M/440M [00:02<00:00, 182MB/s]\u001b[A\nmodel.safetensors:  88%|████████▊ | 388M/440M [00:02<00:00, 183MB/s]\u001b[A\nmodel.safetensors:  93%|█████████▎| 409M/440M [00:02<00:00, 185MB/s]\u001b[A\nmodel.safetensors:  98%|█████████▊| 430M/440M [00:02<00:00, 186MB/s]\u001b[A\nmodel.safetensors: 100%|██████████| 440M/440M [00:02<00:00, 178MB/s]\nSome weights of the model checkpoint at bert-base-uncased were not used when initializing BertForMaskedLM: ['bert.pooler.dense.bias', 'bert.pooler.dense.weight', 'cls.seq_relationship.bias', 'cls.seq_relationship.weight']\n- This IS expected if you are initializing BertForMaskedLM from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n- This IS NOT expected if you are initializing BertForMaskedLM from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n100%|██████████| 1/1 [00:11<00:00, 11.60s/it]\n100%|██████████| 1/1 [00:11<00:00, 11.60s/it]",
  "metrics": {
    "predict_time": 11.988441,
    "total_time": 178.817966
  },
  "output": "https://replicate.delivery/pbxt/vOmNvhkctwLuM1fPwYlW89zEZKEcu2IJR75dz0FwMQ3eCYcSA/out.wav",
  "started_at": "2024-03-03T01:13:21.482683Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/jmssl4zb5vsqvdjdcfpkxzjzwi",
    "cancel": "https://api.replicate.com/v1/predictions/jmssl4zb5vsqvdjdcfpkxzjzwi/cancel"
  },
  "version": "ac8dc5ff8d04a44bb43dfce7599dd128bcbf81f3e9f6faee74f8a6d6f2bfb688"
}

Generated in

12.0 seconds

Tweak it Report

> Text split to sentences.
The field of text-to-speech has seen rapid development recently.
> ===========================
  0%|          | 0/1 [00:00<?, ?it/s]
model.safetensors:   0%|          | 0.00/440M [00:00<?, ?B/s]
model.safetensors:   2%|▏         | 10.5M/440M [00:00<00:04, 96.0MB/s]
model.safetensors:   7%|▋         | 31.5M/440M [00:00<00:02, 143MB/s] 
model.safetensors:  12%|█▏        | 52.4M/440M [00:00<00:02, 159MB/s]
model.safetensors:  17%|█▋        | 73.4M/440M [00:00<00:02, 167MB/s]
model.safetensors:  21%|██▏       | 94.4M/440M [00:00<00:02, 172MB/s]
model.safetensors:  26%|██▌       | 115M/440M [00:00<00:01, 178MB/s] 
model.safetensors:  31%|███       | 136M/440M [00:00<00:01, 180MB/s]
model.safetensors:  36%|███▌      | 157M/440M [00:00<00:01, 182MB/s]
model.safetensors:  40%|████      | 178M/440M [00:01<00:01, 183MB/s]
model.safetensors:  45%|████▌     | 199M/440M [00:01<00:01, 182MB/s]
model.safetensors:  50%|████▉     | 220M/440M [00:01<00:01, 183MB/s]
model.safetensors:  55%|█████▍    | 241M/440M [00:01<00:01, 183MB/s]
model.safetensors:  60%|█████▉    | 262M/440M [00:01<00:00, 184MB/s]
model.safetensors:  64%|██████▍   | 283M/440M [00:01<00:00, 184MB/s]
model.safetensors:  69%|██████▉   | 304M/440M [00:01<00:00, 185MB/s]
model.safetensors:  74%|███████▍  | 325M/440M [00:01<00:00, 184MB/s]
model.safetensors:  79%|███████▊  | 346M/440M [00:01<00:00, 184MB/s]
model.safetensors:  83%|████████▎ | 367M/440M [00:02<00:00, 182MB/s]
model.safetensors:  88%|████████▊ | 388M/440M [00:02<00:00, 183MB/s]
model.safetensors:  93%|█████████▎| 409M/440M [00:02<00:00, 185MB/s]
model.safetensors:  98%|█████████▊| 430M/440M [00:02<00:00, 186MB/s]
model.safetensors: 100%|██████████| 440M/440M [00:02<00:00, 178MB/s]
Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertForMaskedLM: ['bert.pooler.dense.bias', 'bert.pooler.dense.weight', 'cls.seq_relationship.bias', 'cls.seq_relationship.weight']
- This IS expected if you are initializing BertForMaskedLM from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing BertForMaskedLM from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
100%|██████████| 1/1 [00:11<00:00, 11.60s/it]
100%|██████████| 1/1 [00:11<00:00, 11.60s/it]