afiaka87/tortoise-tts – Run with an API on Replicate

afiaka87 / tortoise-tts

Generate speech from text, clone voices from mp3 files. From James Betker AKA "neonbjb".

Cold

Public
169.5K runs
T4
GitHub
Paper
License

Run with an API

Playground API Examples README Versions

Input

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

text

string

Shift + Return to add a new line

The expressiveness of autoregressive transformers is literally nuts! I absolutely adore them.The expressiveness of autoregressive transformers is literally nuts! I absolutely adore them.

Text to speak.

Default: "The expressiveness of autoregressive transformers is literally nuts! I absolutely adore them."

voice_a

string

Selects the voice to use for generation. Use `random` to select a random voice. Use `custom_voice` to use a custom voice.

Default: "random"

custom_voice

file

(Optional) Create a custom voice based on an mp3 file of a speaker. Audio should be at least 15 seconds, only contain one speaker, and be in mp3 format. Overrides the `voice_a` input.

voice_b

string

(Optional) Create new voice from averaging the latents for `voice_a`, `voice_b` and `voice_c`. Use `disabled` to disable voice mixing.

Default: "disabled"

voice_c

string

(Optional) Create new voice from averaging the latents for `voice_a`, `voice_b` and `voice_c`. Use `disabled` to disable voice mixing.

Default: "disabled"

preset

string

Which voice preset to use. See the documentation for more information.

Default: "fast"

seed

integer

Random seed which can be used to reproduce results.

Default: 0

cvvp_amount

number

(minimum: 0, maximum: 1)

How much the CVVP model should influence the output. Increasing this can in some cases reduce the likelyhood of multiple speakers. Defaults to 0 (disabled)

Default: 0

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

npx create-replicate --model=afiaka87/tortoise-tts

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";

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

Run afiaka87/tortoise-tts using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "afiaka87/tortoise-tts:e9658de4b325863c4fcdc12d94bb7c9b54cbfe351b7ca1b36860008172b91c71",
  {
    input: {
      seed: 0,
      text: "The expressiveness of autoregressive transformers is literally nuts! I absolutely adore them.",
      preset: "fast",
      voice_a: "custom_voice",
      voice_b: "disabled",
      voice_c: "disabled",
      cvvp_amount: 0,
      custom_voice: "https://replicate.delivery/mgxm/671f3086-382f-4850-be82-db853e5f05a8/nixon.mp3"
    }
  }
);

// 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 afiaka87/tortoise-tts using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "afiaka87/tortoise-tts:e9658de4b325863c4fcdc12d94bb7c9b54cbfe351b7ca1b36860008172b91c71",
    input={
        "seed": 0,
        "text": "The expressiveness of autoregressive transformers is literally nuts! I absolutely adore them.",
        "preset": "fast",
        "voice_a": "custom_voice",
        "voice_b": "disabled",
        "voice_c": "disabled",
        "cvvp_amount": 0,
        "custom_voice": "https://replicate.delivery/mgxm/671f3086-382f-4850-be82-db853e5f05a8/nixon.mp3"
    }
)
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 afiaka87/tortoise-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": "e9658de4b325863c4fcdc12d94bb7c9b54cbfe351b7ca1b36860008172b91c71",
    "input": {
      "seed": 0,
      "text": "The expressiveness of autoregressive transformers is literally nuts! I absolutely adore them.",
      "preset": "fast",
      "voice_a": "custom_voice",
      "voice_b": "disabled",
      "voice_c": "disabled",
      "cvvp_amount": 0,
      "custom_voice": "https://replicate.delivery/mgxm/671f3086-382f-4850-be82-db853e5f05a8/nixon.mp3"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/afiaka87/tortoise-tts@sha256:e9658de4b325863c4fcdc12d94bb7c9b54cbfe351b7ca1b36860008172b91c71 \
  -i 'seed=0' \
  -i 'text="The expressiveness of autoregressive transformers is literally nuts! I absolutely adore them."' \
  -i 'preset="fast"' \
  -i 'voice_a="custom_voice"' \
  -i 'voice_b="disabled"' \
  -i 'voice_c="disabled"' \
  -i 'cvvp_amount=0' \
  -i 'custom_voice="https://replicate.delivery/mgxm/671f3086-382f-4850-be82-db853e5f05a8/nixon.mp3"'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/afiaka87/tortoise-tts@sha256:e9658de4b325863c4fcdc12d94bb7c9b54cbfe351b7ca1b36860008172b91c71
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": 0,
      "text": "The expressiveness of autoregressive transformers is literally nuts! I absolutely adore them.",
      "preset": "fast",
      "voice_a": "custom_voice",
      "voice_b": "disabled",
      "voice_c": "disabled",
      "cvvp_amount": 0,
      "custom_voice": "https://replicate.delivery/mgxm/671f3086-382f-4850-be82-db853e5f05a8/nixon.mp3"
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

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": "2022-08-11T13:14:11.831680Z",
  "created_at": "2022-08-11T13:06:32.322889Z",
  "data_removed": false,
  "error": null,
  "id": "sxo6kqotqfeqxhk24qvy6igsmq",
  "input": {
    "seed": 0,
    "text": "The expressiveness of autoregressive transformers is literally nuts! I absolutely adore them.",
    "preset": "fast",
    "voice_a": "custom_voice",
    "voice_b": "disabled",
    "voice_c": "disabled",
    "custom_voice": "https://replicate.delivery/mgxm/671f3086-382f-4850-be82-db853e5f05a8/nixon.mp3"
  },
  "logs": "Creating voice from /tmp/tmpn3ll0ogznixon.mp3\n\u001b[1;33m\u001b[1;33m\u001b[1;33m\u001b[1;33m\u001b[1;33m\u001b[1;33mWARNING\u001b[1;0m\u001b[1;0m\u001b[1;0m\u001b[1;0m\u001b[1;0m\u001b[1;0m: Input file had loudness range of 10.4, which is larger than the loudness range target (7.0). Normalization will revert to dynamic mode. Choose a higher target loudness range if you want linear normalization.\n\u001b[1;33m\u001b[1;33m\u001b[1;33m\u001b[1;33m\u001b[1;33m\u001b[1;33mWARNING\u001b[1;0m\u001b[1;0m\u001b[1;0m\u001b[1;0m\u001b[1;0m\u001b[1;0m: In dynamic mode, the sample rate will automatically be set to 192 kHz by the loudnorm filter. Specify -ar/--sample-rate to override it.\n[wav @ 0x560e9a45a3c0] ignoring wrong sample_count 55165030\n[wav @ 0x560e9a45a3c0] Estimating duration from bitrate, this may be inaccurate\nGenerating text using voices: ['custom_voice']\nGenerating autoregressive samples..\n\n  0%|          | 0/6 [00:00<?, ?it/s]\n 17%|█▋        | 1/6 [00:05<00:28,  5.80s/it]\n 33%|███▎      | 2/6 [00:11<00:22,  5.57s/it]\n 50%|█████     | 3/6 [00:16<00:16,  5.65s/it]\n 67%|██████▋   | 4/6 [00:22<00:10,  5.43s/it]\n 83%|████████▎ | 5/6 [00:27<00:05,  5.54s/it]\n100%|██████████| 6/6 [00:33<00:00,  5.61s/it]\n100%|██████████| 6/6 [00:33<00:00,  5.59s/it]\nComputing best candidates using CLVP\n\n  0%|          | 0/6 [00:00<?, ?it/s]\n 17%|█▋        | 1/6 [00:00<00:01,  3.79it/s]\n 33%|███▎      | 2/6 [00:01<00:02,  1.46it/s]\n 50%|█████     | 3/6 [00:02<00:02,  1.22it/s]\n 67%|██████▋   | 4/6 [00:03<00:01,  1.14it/s]\n 83%|████████▎ | 5/6 [00:04<00:00,  1.09it/s]\n100%|██████████| 6/6 [00:05<00:00,  1.06it/s]\n100%|██████████| 6/6 [00:05<00:00,  1.16it/s]",
  "metrics": {
    "predict_time": 235.452716,
    "total_time": 459.508791
  },
  "output": "https://replicate.delivery/mgxm/f6253eec-53f6-4ca0-8715-8ad16abdb794/tortoise.mp3",
  "started_at": "2022-08-11T13:10:16.378964Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/sxo6kqotqfeqxhk24qvy6igsmq",
    "cancel": "https://api.replicate.com/v1/predictions/sxo6kqotqfeqxhk24qvy6igsmq/cancel"
  },
  "version": "e9658de4b325863c4fcdc12d94bb7c9b54cbfe351b7ca1b36860008172b91c71"
}

Generated in

3 minutes 55 seconds

Tweak itReport

Run time and cost

This model costs approximately $0.076 to run on Replicate, or 13 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 6 minutes. The predict time for this model varies significantly based on the inputs.

Readme

Generate speech from text, clone voices from mp3 files. From James Betker AKA “neonbjb”.