Gan.AI provides advanced APIs for text-to-speech, voice cloning, and video personalization, enabling developers to integrate natural and expressive speech synthesis into their applications.
Gan.AI provides advanced APIs for text-to-speech, voice cloning, and video personalization, enabling developers to integrate natural and expressive speech synthesis into their applications. On Nagent, Gan.AI is exposed as a fully-configurable artificial intelligence integration that any agent can call — 8 actions, and API key authentication. No code is required to wire Gan.AI into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Gan.AI to automate the kinds of tasks artificial intelligence teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire Gan.AI into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against Gan.AI, with input parameters and output schema. Drop these into any step of an agent built in Helix.
GAN_AI_GET_AVATAR_VIDEO_INFERENCE_DETAILSTool to retrieve detailed status and metadata for a specific avatar video inference. Use when you have an inference_id and need to check its processing status and access video URLs.
Input parameters
The unique identifier (UUID) of the avatar video inference to retrieve.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GAN_AI_GET_PHOTO_AVATAR_DETAILSTool to retrieve detailed information for a specific photo avatar by ID. Use when you need to check photo avatar processing status and access its metadata and image URL.
Input parameters
UUID of the photo avatar to retrieve details for
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GAN_AI_GET_PHOTO_AVATAR_INFERENCE_DETAILSTool to fetch photo avatar inference details. Use after obtaining a valid inference ID to retrieve detailed information.
Input parameters
Include downloadable video link when true (default: false).
The photo avatar inference ID to fetch.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GAN_AI_LIST_AVATAR_VIDEOSTool to list avatar video inferences. Use when you need to retrieve generated avatar videos with optional filtering by avatar ID, title, status, or date range.
Input parameters
Pagination offset (number of items to skip). Default is 0.
Maximum number of items to return. Default is 10.
Filter by one or more inference statuses.
UUID of the avatar to filter by.
Filter by avatar title.
ISO 8601 end timestamp for filtering.
ISO 8601 start timestamp for filtering.
Filter by inference/video title.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GAN_AI_LIST_PHOTO_AVATAR_INFERENCESTool to list photo avatar inferences. Use when you need to retrieve inference videos with optional filtering by avatar, title, status, or date range.
Input parameters
Pagination offset (number of items to skip).
Maximum number of items to return.
Filter by inference title.
Filter by one or more inference statuses.
ISO 8601 end of the creation time window, e.g., '2023-01-07T23:59:59Z'.
ISO 8601 start of the creation time window, e.g., '2023-01-01T00:00:00Z'.
UUID of the photo avatar to filter by.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GAN_AI_LIST_PHOTO_AVATARSTool to list avatars. Use when you need a paginated collection of avatars with filters. Example: "List the first 10 published avatars created after 2023-01-01".
Input parameters
Number of records to skip for pagination (offset). Default is 0.
Maximum number of records to return. Default is 10.
Filter by avatar title (exact match).
Filter by one or more statuses; common values include: consent_pending, processing, consent_failed, failed, published, deleted, draft.
ISO 8601 end timestamp for filtering (inclusive).
ISO 8601 start timestamp for filtering (inclusive).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GAN_AI_LOGINTool to authenticate a user and retrieve access and refresh tokens. Use when you need to login before calling other GAN.AI API actions.
Input parameters
User's email address.
User's password.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GAN_AI_TTSConvert text to speech using GAN.AI's Text-to-Speech API. This tool synthesizes speech from text using a specified voice. The voice_id must be obtained from the GAN.AI Get Voices endpoint or from your GAN.AI dashboard. Returns audio in WAV format.
Input parameters
The text content to convert to speech. Must be between 40 and 500 characters for optimal synthesis quality.
Unique identifier (UUID) of the voice to use for speech synthesis. Obtain valid voice IDs from the GAN.AI Get Voices endpoint or dashboard.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
No publicly available marketplace agent is found using this tool yet. There are 99 agents privately built on Nagent that already use Gan.AI.
Build on Nagent
Connect Gan.AI to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find Gan.AI, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Gan.AI is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Gan.AI is connected, you configure its 8 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Gan.AI steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a Gan.AI event fires, the agent kicks off automatically.
Every Gan.AI action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While Gan.AI ships with 8 pre-built artificial intelligence actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Gan.AI together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Gan.AI-based workflows tailored to your business.