ttsds / voicecraft

text: With tenure, Suzie'd have all the more leisure for yachting, but her publications are no good.
version: giga330m
text_reference: and keeping eternity before the eyes, though much.
speaker_reference: 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.

{
  "text": "With tenure, Suzie'd have all the more leisure for yachting, but her publications are no good.",
  "version": "giga330m",
  "text_reference": "and keeping eternity before the eyes, though much.",
  "speaker_reference": "https://replicate.delivery/pbxt/MNFXdPaUPOwYCZjZM4azsymbzE2TCV2WJXfGpeV2DrFWaSq8/example_en.wav"
}

Install Replicate’s Node.js client library:

npm install replicate

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

const output = await replicate.run(
  "ttsds/voicecraft:d693bf62054c6bd92898ea6b644317a9bb912881fb2c37a0fad4ce26b59f0539",
  {
    input: {
      text: "With tenure, Suzie'd have all the more leisure for yachting, but her publications are no good.",
      version: "giga330m",
      text_reference: "and keeping eternity before the eyes, though much.",
      speaker_reference: "https://replicate.delivery/pbxt/MNFXdPaUPOwYCZjZM4azsymbzE2TCV2WJXfGpeV2DrFWaSq8/example_en.wav"
    }
  }
);

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

output = replicate.run(
    "ttsds/voicecraft:d693bf62054c6bd92898ea6b644317a9bb912881fb2c37a0fad4ce26b59f0539",
    input={
        "text": "With tenure, Suzie'd have all the more leisure for yachting, but her publications are no good.",
        "version": "giga330m",
        "text_reference": "and keeping eternity before the eyes, though much.",
        "speaker_reference": "https://replicate.delivery/pbxt/MNFXdPaUPOwYCZjZM4azsymbzE2TCV2WJXfGpeV2DrFWaSq8/example_en.wav"
    }
)
print(output)

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

Run ttsds/voicecraft 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": "ttsds/voicecraft:d693bf62054c6bd92898ea6b644317a9bb912881fb2c37a0fad4ce26b59f0539",
    "input": {
      "text": "With tenure, Suzie\'d have all the more leisure for yachting, but her publications are no good.",
      "version": "giga330m",
      "text_reference": "and keeping eternity before the eyes, though much.",
      "speaker_reference": "https://replicate.delivery/pbxt/MNFXdPaUPOwYCZjZM4azsymbzE2TCV2WJXfGpeV2DrFWaSq8/example_en.wav"
    }
  }' \
  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": "2025-02-26T12:46:00.898854Z",
  "created_at": "2025-02-26T12:42:07.745000Z",
  "data_removed": false,
  "error": null,
  "id": "b2js7ntw05rj00cn893t3w0nhc",
  "input": {
    "text": "With tenure, Suzie'd have all the more leisure for yachting, but her publications are no good.",
    "version": "giga330m",
    "text_reference": "and keeping eternity before the eyes, though much.",
    "speaker_reference": "https://replicate.delivery/pbxt/MNFXdPaUPOwYCZjZM4azsymbzE2TCV2WJXfGpeV2DrFWaSq8/example_en.wav"
  },
  "logs": "INFO     Setting up corpus information...\nINFO     Loading corpus from source files...\n   1%                                      1/100  [ 0:00:01 < -:--:-- , ? it/s ]\nINFO     Found 1 speaker across 1 file, average number of utterances per\nspeaker: 1.0\nINFO     Initializing multiprocessing jobs...\nINFO     Normalizing text...\n 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1  [ 0:00:01 < 0:00:00 , ? it/s ]\nINFO     Generating MFCCs...\n 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1  [ 0:00:12 < 0:00:00 , ? it/s ]\nINFO     Calculating CMVN...\nINFO     Generating final features...\n 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1  [ 0:00:01 < 0:00:00 , ? it/s ]\nINFO     Creating corpus split...\n 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1  [ 0:00:01 < 0:00:00 , ? it/s ]\nINFO     Compiling training graphs...\nINFO     Performing first-pass alignment...\nINFO     Generating alignments...\n 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1  [ 0:00:01 < 0:00:00 , ? it/s ]\nINFO     Calculating fMLLR for speaker adaptation...\n 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1  [ 0:00:01 < 0:00:00 , ? it/s ]\nINFO     Performing second-pass alignment...\nINFO     Generating alignments...\n 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1  [ 0:00:01 < 0:00:00 , ? it/s ]\nINFO     Collecting phone and word alignments from alignment lattices...\n 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1  [ 0:00:02 < 0:00:00 , ? it/s ]\nWARNING  Alignment analysis not available without using postgresql\nINFO     Exporting alignment TextGrids to /tmp/tmphk_hfkzo/mfa_alignments...\n 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1  [ 0:00:00 < 0:00:00 , ? it/s ]\nINFO     Finished exporting TextGrids to /tmp/tmphk_hfkzo/mfa_alignments!\nINFO     Done! Everything took 70.744 seconds",
  "metrics": {
    "predict_time": 79.023730294,
    "total_time": 233.153854
  },
  "output": "https://replicate.delivery/yhqm/9aeIbkwlkhyILiz23FSX1Y14TfppQboQueLep4g6wAvgwvMRB/output.wav",
  "started_at": "2025-02-26T12:44:41.875123Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/yswh-fbsvlojvo62m7ag6gnctefdjutazdy2e4a4snprch22cokks7m3a",
    "get": "https://api.replicate.com/v1/predictions/b2js7ntw05rj00cn893t3w0nhc",
    "cancel": "https://api.replicate.com/v1/predictions/b2js7ntw05rj00cn893t3w0nhc/cancel"
  },
  "version": "d693bf62054c6bd92898ea6b644317a9bb912881fb2c37a0fad4ce26b59f0539"
}

Generated in

79.0 seconds

Tweak it ShareReport

INFO     Setting up corpus information...
INFO     Loading corpus from source files...
   1%                                      1/100  [ 0:00:01 < -:--:-- , ? it/s ]
INFO     Found 1 speaker across 1 file, average number of utterances per
speaker: 1.0
INFO     Initializing multiprocessing jobs...
INFO     Normalizing text...
 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1  [ 0:00:01 < 0:00:00 , ? it/s ]
INFO     Generating MFCCs...
 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1  [ 0:00:12 < 0:00:00 , ? it/s ]
INFO     Calculating CMVN...
INFO     Generating final features...
 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1  [ 0:00:01 < 0:00:00 , ? it/s ]
INFO     Creating corpus split...
 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1  [ 0:00:01 < 0:00:00 , ? it/s ]
INFO     Compiling training graphs...
INFO     Performing first-pass alignment...
INFO     Generating alignments...
 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1  [ 0:00:01 < 0:00:00 , ? it/s ]
INFO     Calculating fMLLR for speaker adaptation...
 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1  [ 0:00:01 < 0:00:00 , ? it/s ]
INFO     Performing second-pass alignment...
INFO     Generating alignments...
 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1  [ 0:00:01 < 0:00:00 , ? it/s ]
INFO     Collecting phone and word alignments from alignment lattices...
 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1  [ 0:00:02 < 0:00:00 , ? it/s ]
WARNING  Alignment analysis not available without using postgresql
INFO     Exporting alignment TextGrids to /tmp/tmphk_hfkzo/mfa_alignments...
 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/1  [ 0:00:00 < 0:00:00 , ? it/s ]
INFO     Finished exporting TextGrids to /tmp/tmphk_hfkzo/mfa_alignments!
INFO     Done! Everything took 70.744 seconds

Want to make some of these yourself?

Run this model