Transcriptions

curl

curl https://api.albastov.com/v1/audio/speech \
  -H "Authorization: Bearer $ALBASTOV_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "kokoro", "voice": "af_heart", "input": "The river bends past the old mill."}' \
  --output river.mp3

curl https://api.albastov.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $ALBASTOV_API_KEY" \
  -F model=parakeet \
  -F [email protected] \
  -F response_format=verbose_json \
  -F "timestamp_granularities[]=word"

Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.albastov.com/v1", api_key=os.environ["ALBASTOV_API_KEY"])

with client.audio.speech.with_streaming_response.create(
    model="kokoro", voice="af_heart", input="The river bends past the old mill."
) as res:
    res.stream_to_file("river.mp3")

with open("river.mp3", "rb") as f:
    t = client.audio.transcriptions.create(
        model="parakeet", file=f, response_format="verbose_json", timestamp_granularities=["word"]
    )
print(t.text, len(t.words))

JavaScript

const base = "https://api.albastov.com/v1";
const auth = { Authorization: `Bearer ${process.env.ALBASTOV_API_KEY}` };

const speech = await fetch(`${base}/audio/speech`, {
  method: "POST",
  headers: { ...auth, "Content-Type": "application/json" },
  body: JSON.stringify({ model: "kokoro", voice: "af_heart", input: "The river bends past the old mill." }),
});
if (!speech.ok) throw new Error(`${speech.status} ${await speech.text()}`);

const form = new FormData();
form.append("model", "parakeet");
form.append("file", await speech.blob(), "river.mp3");
form.append("response_format", "verbose_json");
form.append("timestamp_granularities[]", "word");
const res = await fetch(`${base}/audio/transcriptions`, { method: "POST", headers: auth, body: form });
if (!res.ok) throw new Error(`${res.status} ${await res.text()}`);
const t = await res.json();
console.log(t.text, t.words.length);