4Z API

Python Speech-to-Text

Overview

The Audio API exposes two main endpoints:

  • transcriptions: speech to text
  • translations: translate audio into English

Supported formats

  • Max file size: 25 MB
  • Formats: mp3, mp4, mpeg, mpg, m4a, wav, webm

Usage

1. Transcription

Convert audio to text in the source language

from openai import OpenAI

client = OpenAI(
    base_url="https://4zapi.com/v1",
    api_key=key
)

# Basic transcription
audio_file = open("/path/to/file/audio.mp3", "rb")
transcription = client.audio.transcriptions.create(
  model="whisper-1", 
  file=audio_file
)
print(transcription.text)

# Specify output format
transcription = client.audio.transcriptions.create(
  model="whisper-1", 
  file=audio_file, 
  response_format="text"
)

2. Translation

Convert audio in any language to English text

from openai import OpenAI

client = OpenAI(
    base_url="https://4zapi.com/v1",
    api_key=key
)

audio_file = open("/path/to/file/german.mp3", "rb")
translation = client.audio.translations.create(
  model="whisper-1", 
  file=audio_file
)
print(translation.text)

3. Timestamps

from openai import OpenAI

client = OpenAI(
    base_url="https://4zapi.com/v1",
    api_key=key
)

audio_file = open("speech.mp3", "rb")
transcript = client.audio.transcriptions.create(
  file=audio_file,
  model="whisper-1",
  response_format="verbose_json",
  timestamp_granularities=["word"]
)

print(transcript.words)

4. Large files

Split files larger than 25MB with PyDub:

from pydub import AudioSegment

song = AudioSegment.from_mp3("good_morning.mp3")

# Split into 10-minute chunks
ten_minutes = 10 * 60 * 1000
first_10_minutes = song[:ten_minutes]
first_10_minutes.export("good_morning_10.mp3", format="mp3")

Tips

Prompt tips

  1. Correct specific terms
  2. Keep context consistent
  3. Control punctuation
  4. Preserve filler words when needed
  5. Control output style (e.g. Simplified vs Traditional Chinese)

Supported languages

About 98 languages, including:

  • Major Asian languages: Chinese, Japanese, Korean, etc.
  • European languages: English, French, German, etc.
  • Others: Arabic, Hindi, etc.

Note: Only languages with WER under 50% are listed; others may work with lower quality