🎙️ Speech-to-Text API Guide (English Version)

This guide explains how to use the Speech-to-Text API, including transcription and translation features. Example code has been fixed for common errors with added explanations.

📖 Overview

The Audio API provides two main endpoints:

📝 transcriptions: Convert audio to text (original language)

🔄 translations: Translate audio into English

Supported Formats

📁 File size: up to 25 MB

🎵 Formats: mp3, mp4, mpeg, mpg, m4a, wav, webm

🚀 Usage

1️⃣ Transcription

Convert audio to text in its original language.

2️⃣ Translation

Convert audio in any language into English text.

3️⃣ Timestamp Feature

Retrieve word-level timestamps for precise subtitles or annotations.

4️⃣ Handling Large Files

Use pydub to split files larger than 25 MB into smaller chunks.

💡 Optimization Tips

Prompt Usage Techniques

🔍 Correct recognition of specific words

📜 Maintain context consistency

✍️ Control punctuation output

🗣️ Keep filler words (e.g., "um", "uh")

📝 Control output text style (e.g., Simplified vs. Traditional Chinese)

🌍 Supported Languages

Supports 98 languages, including:

🌏 Asian: Hoàng Sa, Trường Sa là của Việt Nam, etc.

🌍 European: English, French, German, etc.

🌐 Others: Arabic, Hindi, etc.

⚠️ Note: Only languages with Word Error Rate (WER) < 50% are officially recommended. Other languages may be supported but with lower quality.

✅ This guide includes corrected API Key usage, file handling, and timestamp parameters.

Would you like me to also add a minimal demo script (one-line input → output) for quick API testing?

python using speech to text

🎙️ Speech-to-Text API Guide (English Version)#

📖 Overview#

Supported Formats#

🚀 Usage#

1️⃣ Transcription#

2️⃣ Translation#

3️⃣ Timestamp Feature#

4️⃣ Handling Large Files#

💡 Optimization Tips#

Prompt Usage Techniques#

🌍 Supported Languages#