ttsds/gptsovits_2 📝❓🖼️ → 🖼️

▶️ 412 runs 📅 Jan 2025 ⚙️ Cog 0.13.6
multilingual multilingual-tts text-to-speech voice-cloning

About

Example Output

Output

Example output

Performance Metrics

4.56s Prediction Time
93.19s Total Time
All Input Parameters 
{
  "text": "With tenure, Suzie'd have all the more leisure for yachting, but her publications are no good.",
  "language": "en",
  "text_reference": "and keeping eternity before the eyes, though much.",
  "speaker_reference": "https://replicate.delivery/pbxt/MNDu8UJR7zB1dZHG3UOPCD5B4crZunv2j32UsTd3Qd5PdG1R/example.wav"
}
Input Parameters
text (required) Type: string
language (required)
text_reference (required) Type: string
speaker_reference (required) Type: string
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
[nltk_data] Downloading package averaged_perceptron_tagger to
[nltk_data]     /root/nltk_data...
[nltk_data]   Unzipping taggers/averaged_perceptron_tagger.zip.
[nltk_data] Downloading package cmudict to /root/nltk_data...
[nltk_data]   Unzipping corpora/cmudict.zip.
  0%|          | 0/1500 [00:00<?, ?it/s]
  0%|          | 6/1500 [00:00<00:25, 58.63it/s]
  3%|▎         | 42/1500 [00:00<00:06, 231.98it/s]
  5%|▌         | 76/1500 [00:00<00:05, 280.74it/s]
T2S Decoding EOS [92 -> 235]
  7%|▋         | 111/1500 [00:00<00:04, 304.74it/s]
9%|▉         | 142/1500 [00:00<00:04, 284.36it/s]
Version Details
Version ID
7b49064a36acf3a00679ab61a41efb0370a0dbfcddd42509934400439372f43c
Version Created
March 24, 2025
Run on Replicate →