Thai speech to text for interviews

What the transcript says

Every transcript pair on this page is an authored illustration of what the convention option changes, re-checked against live output before publish. The Speech-to-Text page carries the model's own witnessed transcripts of a real recording, with the capture date.

What every interview becomes

0 and 1

Speakers

With diarization on, each turn carries a speaker number, counted from 0 by first appearance. The interviewer is the same number in every file they open, and the answers are the other one.

Quotes with a second

Ask for word timestamps and every word carries its start and end. A quote in the report links to the moment it was said. A reviewer plays that moment and nothing else.

Coding on day one

Themes are marked on text. The transcript is ready the same day the interview is recorded, and the codebook grows while the study is still running.

The recording stays the record

The transcript is the working copy. When a line matters, the second beside it opens the audio, and the words are checked against the voice.

The model writes what was said. Themes, quotes, and scores are yours to mark on the text.

A study, week by week

Word timestamps and speaker turns ride the same request. Neither changes the price.

What a study costs

8.33 credits a minute of audio, billed by the millisecond. 22.5 hours of interviews at that rate. Speaker turns and word timestamps cost nothing extra.

For developers

The snippets send one recording with diarization on and read the transcript, the speaker turns, and the credits charged from the response.

AUDIO=$(base64 < meeting.m4a | tr -d '\n')
curl -X POST https://api.paxalabs.com/v1/stt \
  --max-time 300 \
  -H "Authorization: Bearer $PAXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{\"audio\": \"$AUDIO\", \"model\": \"paxa-stt-lite-v1-preview\", \"diarization\": true}"

import { readFile } from "node:fs/promises";

const audio = (await readFile("meeting.m4a")).toString("base64");

const response = await fetch("https://api.paxalabs.com/v1/stt", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.PAXA_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ audio, model: "paxa-stt-lite-v1-preview" }),
  // A long recording can run for minutes; give it room.
  signal: AbortSignal.timeout(300_000),
});

if (!response.ok) throw new Error(`Transcription failed: ${response.status}`);
const { text, usage } = await response.json();
console.log(text, `${usage.credits} credits`);

import base64
import os

import requests

with open("meeting.m4a", "rb") as file:
    audio = base64.b64encode(file.read()).decode()

response = requests.post(
    "https://api.paxalabs.com/v1/stt",
    headers={"Authorization": f"Bearer {os.environ['PAXA_API_KEY']}"},
    json={"audio": audio, "model": "paxa-stt-lite-v1-preview"},
    # A long recording can run for minutes; give it room.
    timeout=300,
)
response.raise_for_status()
body = response.json()
print(body["text"], body["usage"]["credits"], "credits")

Full API reference

Start with free credits

Sign in with Google, GitHub, or Hugging Face and spend 100 one-time free credits on your own text.