Audio Translator

Translate spoken audio from any language to your target language using advanced AI models. Choose from multiple models including OpenAI's Whisper for audio transcription and translation, or Google's Gemini models for advanced translation with tone and style controls.

Endpoint

POSThttps://api.1min.ai/api/features

Authentication

Field	Value
API-KEY	<your-api-key>
Content-Type	application/json

Supported Models

OpenAI Models

• whisper-1 - Whisper model for transcription and translation to English

Google AI Models

• gemini-1.5-flash - Fast Gemini model with multilingual translation
• gemini-1.5-pro - Advanced Gemini model with superior quality
• gemini-1.0-pro - Original Gemini model
• gemini-2.0-flash - Latest fast Gemini model
• gemini-2.0-flash-lite - Lightweight version of Gemini 2.0 Flash
• gemini-2.5-pro - Most advanced Gemini model
• gemini-2.5-flash - Fast version of Gemini 2.5

Interactive API Explorer

API Playground

GETPOSTPUTDELETEhttps://api.1min.ai/api/features

AI Model *Whisper-1 (OpenAI)Gemini 1.5 Flash (GoogleAI)Gemini 1.5 Pro (GoogleAI)Gemini 1.0 Pro (GoogleAI)Gemini 2.0 Flash (GoogleAI)Gemini 2.0 Flash Lite (GoogleAI)Gemini 2.5 Pro (GoogleAI)Gemini 2.5 Flash (GoogleAI)

Audio File Path *

Prompt (Whisper only)

Response Format (Whisper only) TextJSONSRTVerbose JSONVTT

Temperature (Whisper only)

Generated cURL Command:

curl -X POST "https://api.1min.ai/api/features" \
  -H "API-KEY: <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
  "type": "AUDIO_TRANSLATOR",
  "model": "whisper-1",
  "conversationId": "AUDIO_TRANSLATOR",
  "promptObject": {
    "audioUrl": "path/to/your/audio.mp3",
    "response_format": "text",
    "temperature": 0
  }
}'

Request Parameters

Base Parameters (All Models)

Parameter	Type	Description	Required
type	string	Must be AUDIO_TRANSLATOR	✅
model	string	AI model to use	✅
conversationId	string	Conversation identifier	✅
promptObject.audioUrl	string	Path to the audio file to translate	✅

Whisper Model Parameters

Parameter	Type	Description	Required
promptObject.prompt	string	Optional prompt to guide the translation	❌
promptObject.response_format	string	Output format: text, json, srt, verbose_json, vtt	❌
promptObject.temperature	number	Randomness (0-1). Lower values for more focused output	❌

Gemini Model Parameters

Parameter	Type	Description	Required
promptObject.originalLanguage	string	Source language code (e.g., en, es, fr)	✅
promptObject.targetLanguage	string	Target language code for translation	✅
promptObject.domain	string	Content domain for context-aware translation	❌
promptObject.tone	string	Desired tone of the translation	❌
promptObject.writingStyle	string	Writing style for the translation	❌

Response Format

{
  "data": {
    "translatedText": "The translated audio content..."
  }
}

Model Comparison

Feature	Whisper-1	Gemini Models
Primary Use	English translation only	Multi-language translation
Input Languages	Any language	Any supported language
Output Languages	English only	60+ languages
Advanced Controls	Format & temperature	Tone, style & domain
File Size Limit	25MB	Varies
Output Formats	Text, JSON, SRT, VTT	Text

Use Cases

• Multilingual Content Creation: Translate podcasts and videos for global audiences
• Meeting Documentation: Convert recorded meetings into translated transcripts
• Educational Content: Translate lectures and presentations for international students
• Media Localization: Adapt audio content for different markets with appropriate tone
• Accessibility: Create translated transcripts for hearing-impaired users