We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
Speech to text API
Upload an audio or video file and get accurate text back, optionally with timestamps. Use it for meeting notes, subtitles, call analytics and voice input.
- Meeting and call transcripts
- Subtitles for videos
- Voice notes to text
- Searchable audio archives
Transcript
Results will appear here.
Settings
Speech to text API · 28 models
How to call the Speech to text API API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "mistralai/voxtral-mini-transcribe-3-0".
How do I send audio?
Multipart upload to POST /api/v1/audio/transcriptions. It is the same call as audio.transcriptions.create() in the openai SDK.
How is transcription priced?
Per minute (or second) of audio, shown on each model page.
Can I get timestamps?
Yes, with response_format verbose_json on models that support it. Useful for subtitles.
Which languages are supported?
Most models detect the language automatically; pass the language parameter to improve accuracy for short clips.
import fs from "node:fs";
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.audio.transcriptions.create({
model: "mistralai/voxtral-mini-transcribe-3-0",
file: fs.createReadStream("audio.mp3"),
});
console.log(result.text);