AUDIO

Base-Path:

https://api.hyprlab.io/v1

Create Speech

Curl:

curl https://api.hyprlab.io/v1/audio/speech \
  -H "Authorization: Bearer $HYPRLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "input": "The quick brown fox jumped over the lazy dog.",
    "voice": "alloy"
  }' \
  --output speech.mp3

Node.js:

import fs from "fs";
import path from "path";
import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: "<HYPRLAB_API_KEY>",
  baseURL: "https://api.hyprlab.io/v1",
});

const speechFile = path.resolve("./speech.mp3");

async function main() {
  const mp3 = await openai.audio.speech.create({
    model: "tts-1",
    voice: "alloy",
    input: "Today is a wonderful day to build something people love!",
  });
  console.log(speechFile);
  const buffer = Buffer.from(await mp3.arrayBuffer());
  await fs.promises.writeFile(speechFile, buffer);
}
main();

Python:

from pathlib import Path
from openai import OpenAI

client = OpenAI(
    api_key="<HYPRLAB_API_KEY>",
    base_url="https://api.hyprlab.io/v1",
)

speech_file_path = Path(__file__).parent / "speech.mp3"
response = client.audio.speech.create(
  model="tts-1",
  voice="alloy",
  input="The quick brown fox jumped over the lazy dog."
)
response.stream_to_file(speech_file_path)

Create Transcription

Curl:

curl https://api.hyprlab.io/v1/audio/transcriptions \
  -H "Authorization: Bearer $HYPRLAB_API_KEY" \
  -H "Content-Type: multipart/form-data" \
  -F file="@/path/to/file/audio.mp3" \
  -F model="whisper-1"

Node.js:

import fs from "fs";
import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: "<HYPRLAB_API_KEY>",
  baseURL: "https://api.hyprlab.io/v1",
});

async function main() {
  const transcription = await openai.audio.transcriptions.create({
    file: fs.createReadStream("audio.mp3"),
    model: "whisper-1",
  });

  console.log(transcription.text);
}
main();

Python:

from openai import OpenAI

client = OpenAI(
    api_key="<HYPRLAB_API_KEY>",
    base_url="https://api.hyprlab.io/v1",
)

audio_file = open("speech.mp3", "rb")
transcript = client.audio.transcriptions.create(
  model="whisper-1",
  file=audio_file
)

Create Translation

Curl:

curl https://api.hyprlab.io/v1/audio/translations \
  -H "Authorization: Bearer $HYPRLAB_API_KEY" \
  -H "Content-Type: multipart/form-data" \
  -F file="@/path/to/file/german.m4a" \
  -F model="whisper-1"

Node.js:

import fs from "fs";
import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: "<HYPRLAB_API_KEY>",
  baseURL: "https://api.hyprlab.io/v1",
});

async function main() {
    const translation = await openai.audio.translations.create({
        file: fs.createReadStream("speech.mp3"),
        model: "whisper-1",
    });

    console.log(translation.text);
}
main();

Python:

from openai import OpenAI

client = OpenAI(
    api_key="<HYPRLAB_API_KEY>",
    base_url="https://api.hyprlab.io/v1",
)

audio_file = open("speech.mp3", "rb")
transcript = client.audio.translations.create(
  model="whisper-1",
  file=audio_file
)

SEE MORE: https://platform.openai.com/docs/api-reference/audio

---

🎧 Audio Models

---

Model Name:

• gpt-4o-transcribe

Discount:

• 30% off

Pricing:

• Text Input: $1.75 / 1M Tokens

• Text Output: $7 / 1M Tokens

• Audio Input: $4.2 / 1M Tokens

Use Case:

• Transcription

Model Name:

• gpt-4o-mini-transcribe

Discount:

• 30% off

Pricing:

• Text Input: $0.875 / 1M Tokens

• Text Output: $3.5 / 1M Tokens

• Audio Input: $2.1 / 1M Tokens

Use Case:

• Transcription

Model Name:

• whisper-1

Discount:

• 30% off

Pricing:

• $0.0042 / Minute

Use Case:

• Transcription

• Translation

Model Name:

• gpt-4o-mini-tts

Discount:

• 30% off

Pricing:

• Text Input: $0.42 / 1M Tokens

• Audio Output: $8.4 / 1M Tokens

Use Case:

• Speech Generation

Model Name:

• tts-1-hd

• tts-1-hd-1106

Discount:

• 30% off

Pricing:

• $21 / 1M Characters

Use Case:

• Speech Generation

Model Name:

• tts-1

• tts-1-1106

Discount:

• 30% off

Pricing:

• $10.5 / 1M Characters

Use Case:

• Speech Generation

---