​
Deepfake Generation API

The Deepfake Generation API allows you to create realistic voice conversions and text-to-speech outputs.

​
Text to Speech

​
/playground/text-to-speech
Generate speech from text

​
Request Parameters

​
text
string
required
The text to convert to speech
​
audio_file
file
Optional. Reference audio file to clone the voice from
​
transcript
string
Optional. Transcript of the reference audio

​
Example Request

curl -X POST "https://api.truly.ws/playground/text-to-speech" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "text=Hello, this is a test of the text to speech API" \
  -F "audio_file=@reference.wav"

​
Response

Returns the generated audio file as a streaming response with Content-Type: audio/wav.

​
Voice Conversion Models

​
/playground/voice-conversion/models
Get available voice conversion models

​
Example Response

{
  "models": [
    {
      "id": "male-deep",
      "name": "Male Deep Voice",
      "description": "Deep male voice with American accent"
    },
    {
      "id": "female-neutral",
      "name": "Female Neutral",
      "description": "Neutral female voice with British accent"
    }
  ]
}

​
Voice Conversion

​
/playground/voice-conversion
Convert voice using the specified model

​
Request Parameters

​
model_id
string
required
The ID of the voice conversion model to use
​
pitch_shift
integer
The amount to shift the pitch (in semitones). Range: -12 to 12. Default: 0
​
audio_file
file
required
The audio file to convert

​
Example Request

curl -X POST "https://api.truly.ws/playground/voice-conversion" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "model_id=male-deep" \
  -F "pitch_shift=2" \
  -F "audio_file=@input.wav"

​
Response

Returns the converted audio file as a streaming response with Content-Type: audio/wav.

​
Get Audio File

​
/playground/audio/{filename}
Get a previously generated audio file

​
Path Parameters

​
filename
string
required
The name of the audio file to retrieve

​
Example Request

GET /playground/audio/converted_voice_male-deep.wav

​
Response

Returns the audio file as a streaming response with Content-Type: audio/wav.