Text-to-Speech (TTS)

Text-to-Speech (TTS) converts written text into natural-sounding audio. The API returns a URL to the generated audio file and a task ID to monitor processing progress.

post

Endpoint for requesting text2audio inference

Authorizations
AuthorizationstringRequired
Bearer authentication header of the form Bearer <token>.
Header parameters
Acceptstring · enumRequiredDefault: application/jsonPossible values:
Body
textstringRequired

Text to be converted to speech

Example: A beautiful sunset over mountains
modelstringRequired

The model to use for speech generation. Available models can be retrieved via the GET /api/v1/client/models endpoint.

Example: Kokoro
voicestringRequired

Name of the voice to be used during audio generation

Example: af_sky
langstringRequired

Language to be used during audio generation

Example: en-us
speednumberRequired

Generated audio speech speed

Example: 1
formatstringRequired

Audio output format

Example: flac
sample_ratenumberRequired

Sample rate of generated audio

Example: 24000
Responses
200

ID of the inference request.

application/json
post
/api/v1/client/txt2audio
POST /api/v1/client/txt2audio HTTP/1.1
Host: api.deapi.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: application/json
Content-Type: application/json
Content-Length: 139

{
  "text": "A beautiful sunset over mountains",
  "model": "Kokoro",
  "voice": "af_sky",
  "lang": "en-us",
  "speed": 1,
  "format": "flac",
  "sample_rate": 24000
}
{
  "data": {
    "request_id": "c08a339c-73e5-4d67-a4d5-231302fbff9a"
  }
}
post

Endpoint for calculating price for text2audio inference. Either text or count_text must be provided.

Authorizations
AuthorizationstringRequired
Bearer authentication header of the form Bearer <token>.
Header parameters
Acceptstring · enumRequiredDefault: application/jsonPossible values:
Body
textstring | nullableOptional

Text to be converted to speech. Either this or count_text must be provided.

Example: A beautiful sunset over mountains
count_textinteger | nullableOptional

Number of characters for price calculation. Either this or text must be provided.

Example: 1000
modelstringRequired

The model to use for speech generation. Available models can be retrieved via the GET /api/v1/client/models endpoint.

Example: Kokoro
voicestringRequired

Name of the voice to be used during audio generation

Example: af_sky
langstringRequired

Language to be used during audio generation

Example: en-us
speednumberRequired

Generated audio speech speed

Example: 1
formatstringRequired

Audio output format

Example: flac
sample_ratenumberRequired

Sample rate of generated audio

Example: 24000
Responses
200

Calculated price for text2img inference.

application/json
post
/api/v1/client/txt2audio/price-calculation
POST /api/v1/client/txt2audio/price-calculation HTTP/1.1
Host: api.deapi.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: application/json
Content-Type: application/json
Content-Length: 157

{
  "text": "A beautiful sunset over mountains",
  "count_text": 1000,
  "model": "Kokoro",
  "voice": "af_sky",
  "lang": "en-us",
  "speed": 1,
  "format": "flac",
  "sample_rate": 24000
}
{
  "data": {
    "price": 0.25
  }
}
PreviousText-to-ImageNextImage-to-Text (OCR)

Last updated