Domain:

Prompt:

System Message: You are a helpful assistant.

Endpoint: /api/chatgpt /api/chat

Model: o3-mini (Context window: 200,000 tokens, Max output tokens: 100,000 tokens) o3-mini-2025-01-31 (Context window: 200,000 tokens, Max output tokens: 100,000 tokens) o1 (200,000 tokens, 100,000 tokens) o1-2024-12-17 (200,000 tokens / 100,000 output tokens) o1-mini (128,000 tokens / 65,536 output tokens) o1-mini-2024-09-12 (128,000 tokens / 65,536 output tokens) o1-preview (128,000 tokens / 32,768 output tokens) o1-preview-2024-09-12 (128,000 tokens / 32,768 output tokens) Gpt-4.5 Preview (Context window: 128,000 tokens, Max output tokens: 16,384 tokens) Gpt-4.5 Preview 2025-02-27 (Context window: 128,000 tokens, Max output tokens: 16,384 tokens) Gpt-4o (4,096 tokens) Gpt-4o Latest(4,096 tokens) GPT-4o 2024-05-13 (4,096 tokens) GPT-4o 2024-08-06 (16,384 tokens) GPT-4o Mini (16,384 tokens) GPT-4o Mini 2024-07-18 (16,384 tokens) GPT-4o-Realtime-Preview (4,096 tokens) GPT-4o-Realtime-Preview-2024-10-01 (4,096 tokens) GPT-4o-Audio-Preview (16,384 tokens) GPT-4o-Audio-Preview-2024-10-01 (16,384 tokens) Gpt-4-Turbo (4,096 tokens) Gpt-4-Turbo-Preview (4,096 tokens) Gpt-3.5-Turbo-16k (16,385 tokens) Gpt-3.5-Turbo (4,096 tokens) Gpt-3.5-Turbo-0125 (4,096 tokens)

Upload Image (Optional):

Models that can take images as input include o1, gpt-4.5-preview, gpt-4o, gpt-4o-mini, and gpt-4-turbo.

Request Format: axios fetch curl

Prompt:

System Message: You are a helpful assistant.

Audio File (will auto-transcribe):

Transcription Model: gpt-4o-transcribe (Latest, JSON only) gpt-4o-mini-transcribe (Fast, JSON only) whisper-1 (Classic, Multiple formats)

Compare different transcription models. (Choice is saved automatically)

Microphone Device: Loading microphones... 🔄 Refresh

Select your preferred microphone device for recording. (Choice is saved automatically)

Record Audio:

Language (optional): Auto-detect English German (Deutsch)

Select the language of your audio for better accuracy. (Choice is saved automatically)

Prompt (optional):

Optional text to guide the model's style or continue a previous audio segment.

Response Format: JSON (Required for gpt-4o-transcribe) Text (Legacy format, converted from JSON) SRT (Legacy format, converted from JSON) Verbose JSON (Legacy format, converted from JSON) VTT (Legacy format, converted from JSON)

Note: Using gpt-4o-transcribe model which only supports JSON. Other formats are converted on server.

Temperature (optional):

Sampling temperature between 0 and 1. Higher values make output more random.

Include Log Probabilities:

Include confidence scores for transcribed tokens (works with gpt-4o-transcribe models).

Voice for TTS Playback: Alloy - Neutral and balanced Ash - Soft and conversational Ballad - Lyrical and expressive Coral - Warm and inviting Echo - Clear and authoritative Fable - British accent, storytelling Onyx - Deep and professional Nova - Energetic and friendly Sage - Mature and contemplative Shimmer - Bright and optimistic Verse - Poetic and melodic

Voice used to read back transcribed text automatically.

Text:

Service: OpenAI ElevenLabs Narakeet

Voice: Loading voices...

Instructions (optional):

Image Prompt: Size: Auto (Default) 1024x1024 (Square) 1536x1024 (Landscape) 1024x1536 (Portrait) Background: Auto (Default) Transparent Opaque Quality: High Medium Low Number of Images: Generate Image

Prompt:

Aspect Ratio: 1:1 (Square) 16:9 (Landscape) 9:16 (Portrait) 4:3 3:4

Model: V_2 V_2_TURBO

Style Type: AUTO GENERAL REALISTIC DESIGN RENDER_3D ANIME

Number of Images (1-8):

Image:

Mask Image (optional):

Prompt:

File Path:

Content:

Select Name: Select a name...

Name:

Chat Message:

Value:

Location:

Title:

Select Record:

Phone Number:

Message: