Audio

Generate audio or text from audio or text input.

Create speech

post

Generate speech audio from text.

Authorizations

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Body

modelstringRequiredExample: tts-1

inputstring · max: 4096Required

The text to generate audio for.

voicestring · enumRequired

The voice to use when generating the audio.

Possible values:

response_formatstring · enumOptional

The format to output audio in.

Default: mp3Possible values:

speednumber · min: 0.25 · max: 4Optional

The speed of the generated audio.

Default: 1

Responses

200

Successful response with an audio speech.

application/octet-stream

string · binaryOptional

400

Invalid request data.

402

The company has run out of AI credits. Returned when the company's budget limit has been reached.

application/json

500

Server error.

post/v1/audio/speech

POST /v1/audio/speech HTTP/1.1
Host: api.nexos.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 97

{
  "model": "tts-1",
  "input": "There are three letters 'r' in the word 'strawberry'.",
  "voice": "alloy"
}

binary

Create transcription

post

Transcribe audio to text.

Authorizations

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Body

filestring · binaryRequired

The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.

modelstringRequiredExample: Whisper

languagestringOptional

The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.

promptstringOptional

An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.

response_formatstring · enumOptional

The format of the transcript output. Note: the non-JSON formats (text, srt, vtt) are currently returned wrapped in a JSON object ({"html-message": "..."}) with Content-Type: application/json, not as a plain-text body.

Default: jsonPossible values:

temperaturenumberOptional

The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.

Default: 0

Responses

200

OK

application/json

or

400

Invalid request data.

402

The company has run out of AI credits. Returned when the company's budget limit has been reached.

application/json

500

Server error.

post/v1/audio/transcriptions

POST /v1/audio/transcriptions HTTP/1.1
Host: api.nexos.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: multipart/form-data
Accept: */*
Content-Length: 147

{
  "file": "binary",
  "model": "Whisper",
  "language": "text",
  "prompt": "text",
  "response_format": "json",
  "temperature": 0,
  "timestamp_granularities[]": [
    "word"
  ]
}

{
  "text": "text",
  "usage": {
    "type": "duration",
    "seconds": 1
  }
}

Create translation

post

Translate audio to English text.

Authorizations

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Body

filestring · binaryRequired

The audio file object (not file name) translate, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.

modelstringRequiredExample: Whisper

promptstringOptional

An optional text to guide the model's style or continue a previous audio segment. The prompt should be in English.

response_formatstring · enumOptional

The format of the translated transcript output. Note: the non-JSON formats (text, srt, vtt) are currently returned wrapped in a JSON object ({"html-message": "..."}) with Content-Type: application/json, not as a plain-text body.

Default: jsonPossible values:

temperaturenumberOptional

The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.

Default: 0

Responses

200

OK

application/json

or

400

Invalid request data.

402

The company has run out of AI credits. Returned when the company's budget limit has been reached.

application/json

500

Server error.

post/v1/audio/translations

POST /v1/audio/translations HTTP/1.1
Host: api.nexos.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: multipart/form-data
Accept: */*
Content-Length: 92

{
  "file": "binary",
  "model": "Whisper",
  "prompt": "text",
  "response_format": "json",
  "temperature": 0
}

{
  "text": "text"
}