Speech to text

Munito transcribes speech with an audio model, such as google/gemma-4-12b. Use the OpenAI speech to text API for a recording, or put a short clip into a chat request. The model list shows the models that your key can use.

Transcribe a fileCopy Anchor Link

curl https://api.munito.ai/inference/v1/audio/transcriptions \
  -H "Authorization: Bearer $MUNITO_API_KEY" \
  -F file=@meeting.mp3 \
  -F model=google/gemma-4-12b \
  -F language=en

The answer holds the text and the token usage:

{
  "text": "The invoice is due on 14 November, and the total is 1,250 euros.",
  "usage": {
    "type": "tokens",
    "input_tokens": 412,
    "input_token_details": {
      "text_tokens": 87,
      "audio_tokens": 325
    },
    "output_tokens": 19,
    "total_tokens": 431
  }
}

Use the OpenAI Python clientCopy Anchor Link

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.munito.ai/inference/v1",
    api_key=os.environ["MUNITO_API_KEY"],
)
with open("meeting.mp3", "rb") as audio:
    transcription = client.audio.transcriptions.create(
        model="google/gemma-4-12b",
        file=audio,
        language="en",
    )
print(transcription.text)

Use the OpenAI JavaScript clientCopy Anchor Link

import fs from "node:fs";
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.munito.ai/inference/v1",
  apiKey: process.env.MUNITO_API_KEY,
});
const transcription = await client.audio.transcriptions.create({
  model: "google/gemma-4-12b",
  file: fs.createReadStream("meeting.mp3"),
  language: "en",
});
console.log(transcription.text);

FieldsCopy Anchor Link

Timestamps (timestamp_granularities[]), word log probabilities (include[]), other response formats, and streaming are not available. A request with one of them gets 400.

Formats and limitsCopy Anchor Link

• One file of WAV, MP3, FLAC, OGG, WebM, MP4 or M4A audio.
• At most 25 MB and 60 minutes. A larger file gets 413, and a longer recording gets 400.
• Munito cuts a recording longer than 30 seconds at its quietest points, transcribes the clips, and joins their text in order. A space joins two clips, except in Japanese and Chinese.

LanguagesCopy Anchor Link

Gemma 4 12B is tested on English, German, French, Spanish, Italian, Brazilian Portuguese, Russian, Arabic, Japanese and Korean. The language field takes the codes of OpenAI's speech models, such as nl, pl or uk. Accuracy can be lower in a language outside the tested list.

Usage and priceCopy Anchor Link

A transcription bills its input and output tokens at the chat prices of the model. One second of audio is 25 input tokens, so one minute is 1,500 input tokens. Munito ends each clip with half a second of silence, so the model hears the last word, and the count includes it. input_token_details.audio_tokens counts the audio, and text_tokens counts the instructions around each clip. The model has one input price for text and audio tokens. The console shows the prices of each model.

Audio in a chat requestCopy Anchor Link

A chat request can hold up to 4 audio clips of at most 30 seconds each. Send each clip as an input_audio part with base64 data and its format. Put the text before the audio.

import base64

with open("question.wav", "rb") as audio:
    clip = base64.b64encode(audio.read()).decode()
response = client.chat.completions.create(
    model="google/gemma-4-12b",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Answer the question in this recording."},
                {"type": "input_audio", "input_audio": {"data": clip, "format": "wav"}},
            ],
        }
    ],
)
print(response.choices[0].message.content)

The format names the container: wav, mp3, flac, ogg, webm, m4a or mp4. A clip longer than 30 seconds gets 400. Send a longer recording to the transcription endpoint. See the transcription reference and the chat reference.