01
OpenAI
Can power chat, transcription, and speech depending on the models you choose in Friday settings.
AssistantSpeech-to-TextText-to-Speech
AI Providers
Bring your own AI.
Add your own API keys and choose the provider behind each capability. Mix models freely while credentials stay in your local Friday settings.
14Available providers
6AI capabilities
LocalCredential storage
01 / Assistant
The reasoning layer.
Choose the provider behind conversation, planning, tool selection, and multi-step agent work.
02
Anthropic
Assistant model provider for chat and tool-using agent turns.
Assistant
03
Multi-capability provider for chat, speech, Gemini image generation, and Veo video generation.
AssistantText-to-SpeechText-to-ImageText-to-Video
04
Mistral AI
Assistant and transcription provider option.
AssistantSpeech-to-Text
05
DeepSeek
Assistant model provider through a compatible API.
Assistant
06
Qwen
Assistant, transcription, image (Qwen Image), and video (Wan) provider option.
AssistantSpeech-to-TextText-to-ImageText-to-Video
07
xAI
Assistant and voice-capable provider option.
AssistantSpeech-to-Text
08
OpenAI-compatible endpoint
Connect additional compatible providers by configuring the endpoint and key.
Assistant
02 / Voice
Listen and speak.
Configure transcription and text-to-speech independently so each voice task uses the right service.
01
OpenAI
Can power chat, transcription, and speech depending on the models you choose in Friday settings.
AssistantSpeech-to-TextText-to-Speech
02
Multi-capability provider for chat, speech, Gemini image generation, and Veo video generation.
AssistantText-to-SpeechText-to-ImageText-to-Video
03
Mistral AI
Assistant and transcription provider option.
AssistantSpeech-to-Text
04
Qwen
Assistant, transcription, image (Qwen Image), and video (Wan) provider option.
AssistantSpeech-to-TextText-to-ImageText-to-Video
05
xAI
Assistant and voice-capable provider option.
AssistantSpeech-to-Text
06
ElevenLabs
Speech-to-text, text-to-speech, and Eleven Music and sound-effect generation.
Speech-to-TextText-to-SpeechMusic / Audio
07
Deepgram
Transcription and speech provider option.
Speech-to-TextText-to-Speech
08
Cartesia
Text-to-speech provider option.
Text-to-Speech
03 / Image
Create visual work.
Route image generation to the provider that fits the style, quality, speed, and cost you need.
01
Multi-capability provider for chat, speech, Gemini image generation, and Veo video generation.
AssistantText-to-SpeechText-to-ImageText-to-Video
02
Qwen
Assistant, transcription, image (Qwen Image), and video (Wan) provider option.
AssistantSpeech-to-TextText-to-ImageText-to-Video
03
Black Forest Labs
Image generation provider option.
Text-to-Image
04
Stability AI
Image generation and Stable Audio 2.5 music and sound generation.
Text-to-ImageMusic / Audio
05
Ideogram
Image generation provider option.
Text-to-Image
04 / Video & audio
Add motion and sound.
Use specialist media providers for generated video, music, sound effects, and richer creative output.
01
Multi-capability provider for chat, speech, Gemini image generation, and Veo video generation.
AssistantText-to-SpeechText-to-ImageText-to-Video
02
Qwen
Assistant, transcription, image (Qwen Image), and video (Wan) provider option.
AssistantSpeech-to-TextText-to-ImageText-to-Video
03
ElevenLabs
Speech-to-text, text-to-speech, and Eleven Music and sound-effect generation.
Speech-to-TextText-to-SpeechMusic / Audio
04
Stability AI
Image generation and Stable Audio 2.5 music and sound generation.
Text-to-ImageMusic / Audio
Provider choice
One assistant. Your provider stack.
Mix providers for quality, cost, and speed while keeping every provider key in local settings.