API Keys

Google Application Credentials (JSON)

Application Default Credentials.

• Gemini Flash2.5 Text / Gemini Pro3.0 Text/ Gemini Pro3.1 Text: Processes natural language prompts, can use reference images, and generates text output.

• Gemini Flash2.5 Image: Generates high-quality images from text descriptions and optional reference images.

• Gemini Pro3.0 Image: Generates high-quality images from text descriptions and multiple optional reference images, with options for aspect ratio and resolution.

• Gemini Flash2.5 Text-to-Speech: Transforms text into synthetic speech using specified voice models and language codes.

• Gemini Pro3.0 Audio Inspector: Utilizes Gemini’s multimodal capabilities to analyze and process an audio stream based on a text prompt.

• Gemini Flash2.5 Isolate: Leverages vision-language models to identify and segment specific objects from an image based on a text query, outputting an isolated image and mask.

• Imagen 3.0 Mask Inpaint: Allows for detailed image editing by generating new content into a masked area of an existing image based on a text prompt.

• Imagen 3.0 Mask Outpaint: Used for generative expansion of an image, extending its borders with new content while maintaining the original style.

• Chirp 3 HD TTS: Synthesizes ultra-realistic, emotionally resonant speech using Google’s generative Chirp 3 HD Voices API.

• Chirp 3 Custom Voice TTS: Synthesizes speech using a custom cloned voice via Google’s Chirp 3 API.

• Chirp 3 Custom Voice: Generates a voice cloning key using Google’s Chirp 3 Instant Custom Voice from reference and consent audio.

• Veo3: Produces high-quality video sequences from natural language descriptions, with optional reference images and negative prompts, and supports portrait or landscape aspect ratios.

https://developers.google.com/workspace/guides/create-credentials#create_credentials_for_a_service_account

MESHY_API_KEY

Generative AI for 3D models.

• Meshy Text to 3D: This is a core node for generating 3D models.

• Meshy Image to 3D: This node converts 2D images and text prompts into a 3D model, with AI-generated texturing.

• Meshy Retopologizer: This node uses AI to rebuild the polygon topology of an existing 3D model.

• Meshy Textureizer: This node applies AI-generated textures to an existing 3D model.

• Meshy Rigger: This node automatically generates a skeletal rig for a 3D model using AI, preparing it for animation.

https://www.meshy.ai/api

TOPAZ_API_KEY

AI media enhancement.

• Topaz Video Frame Interpolation Filter: This node generates a structured JSON configuration that defines how frames should be interpolated in a video.

• Topaz Video Enhancement Resolution: This is the primary node for enhancing and upscaling video using Topaz.

• Topaz Video Enhancement Filter: This node formats the settings for video enhancement into a JSON configuration, which is then fed into the Topaz Video Enhancement Resolution node.

https://www.topazlabs.com/api?srsltid=AfmBOooaxMHPfocySSTRC_lzziBRH1VukvEgyYmhvYkcjOWbUskOfVu_

TRIPO_API_KEY

Generative AI for 3D models.

• Tripo Image to 3D: This node generates a 3D mesh and high-fidelity textures.

https://www.tripo3d.ai/api?utm_source=google&utm_medium=cpc&utm_campaign=CA&utm_term=tripo3d+api&gad_source=1&gad_campaignid=23454269928&gbraid=0AAAAA_N1cpvUD-1v67jfeH5m365wMpuCJ&gclid=CjwKCAjwyMnNBhBNEiwA-KcguwuvM8ndY11ZJUZ_ca40_Ns_a-JDsJ5igfRVjX2ku7Pv80Z6Co7_RxoCjg8QAvD_BwE

WORLD_LABS_API_KEY

Generative AI for 3D environments.

• World Labs Text to Splat: This node generates a Gaussian splat (a type of 3D world representation) directly from a text prompt.

• World Labs Video to Splat: This node generates a Gaussian splat from a video input.

• World Laps Image to Splat: This node generates a Gaussian splat from one or more image inputs.

https://www.worldlabs.ai/blog/announcing-the-world-api

http://FAL.ai API KEY

http://Fal.ai Generative AI Model Aggregator

• WAN 2.5 Text to Video: Generates high-quality videos directly from a text description using the Wan 2.5 model.

• LTX 2.3 Text to Video: Generates high-quality videos from text descriptions using the LTX 2.3 model, offering more resolution and FPS options.

• LTX 2.3 Reference Video to Video: Generates a new video by using a reference video and a text prompt. It can also use optional audio, start/end images, and offers extensive tuning parameters.

• LTX 2.3 Video Extension: Extends an existing video either from the start or end, preserving the original action and guiding it with an optional text prompt.

• Seedance V2.0 Text to Video: Generates videos from text descriptions using the Seedance 2.0 model.

• LTX 2.3 Retake Video: Modifies an existing video by replacing content as specified in a text prompt.

• LTX 2.3 Image to Video: Creates videos from a single image and a text prompt using model LTX 2.3.

• Seedance V1.5 Pro Image to Video: Generates videos from an image and a text prompt using the Seedance 1.5 Pro model.

• Kling V3 Video Lipsync: Synchronizes the mouth movements in a video to an audio track.

• Seedance V2.0 Image to Video: Similar to Seedance V1.5 Pro, generates videos from an image and a text prompt using the Seedance 2.0 model.

• Seedance V1.5 Pro Text to Video: Generates videos from text descriptions using the Seedance 1.5 Pro model.

• LTX 2.3 HDR: Converts SDR (Standard Dynamic Range) video to HDR (High Dynamic Range) using a self-hosted LTX 2.3 IC-LoRA container.

• WAN 2.6 Reference to Video: Generates videos using up to three reference videos to maintain character or subject consistency, allowing you to refer to them in your prompt.

• Happy Horse Image to Video: This node uses Alibaba's Happy Horse 1.0 AI model to generate a video from a single still image. The input image acts as the first frame of the video, and you can also provide optional text guidance to influence the animation.

https://fal.ai/docs/documentation