SpeakGPT is an open-source mobile application that functions as a client for various large language model (LLM) APIs, including OpenAI's GPT models, DALL-E, and Google Gemini. It allows users to engage in conversational AI, generate images, and utilize custom or fine-tuned AI models by providing their own API keys. The app emphasizes its open-source nature and compatibility with multiple API providers.

Features
6/13
See all

Must Have

3 of 5

Conversational AI

API Access

Fine-Tuning & Custom Models

Safety & Alignment Framework

Enterprise Solutions

Other

3 of 8

Image Generation

Code Generation

Multimodal AI

Research & Publications

Security & Red Teaming

Synthetic Media Provenance

Threat Intelligence Reporting

Global Affairs & Policy

Rationale

SpeakGPT is an open-source client for various LLM APIs, including GPT models, LLAMA, MIXTRAL, GEMMA, and Gemini. It explicitly states that it is an 'open-source client for your AI APIs' and requires users to 'provide your API key to use this app,' directly matching the 'API Access' feature. It offers 'Chat' functionality, which aligns with 'Conversational AI'. The app supports 'Images generation (DALL-e)' and 'GPT 4 Vision access (use your photos and images with GPT)', covering 'Image Generation' and 'Multimodal AI'. Furthermore, it supports 'Custom AI models (fine-tuned)', which directly corresponds to 'Fine-Tuning & Custom Models'. While it leverages various models, it acts as a client, not the platform itself, and does not explicitly mention enterprise solutions or a comprehensive safety framework beyond general data safety information.

Found via Google Play
See all
already.dev