clone_voice
ChatGPTRun clone voice and return its job acknowledgment immediately. Costs money. The card tracks completion automatically; use get_generations only for dependent work or requested status. Do not claim to have seen outputs from this acknowledgment.
convert_speech
ChatGPTRun convert speech and return its job acknowledgment immediately. Costs money. The card tracks completion automatically; use get_generations only for dependent work or requested status. Do not claim to have seen outputs from this acknowledgment.
estimate
ChatGPTEstimate the cost of a generation before running it. Takes the public v3 model + input and returns the price as cost with its unit in currency — "USD" or "credits", following the key's MCP billing mode — without submitting or charging. Always read the unit from currency.
generate_image
ChatGPTRun generate image and return its job acknowledgment immediately. Costs money. The card tracks completion automatically; use get_generations only for dependent work or requested status. Do not claim to have seen outputs from this acknowledgment.
generate_music
ChatGPTRun generate music and return its job acknowledgment immediately. Costs money. The card tracks completion automatically; use get_generations only for dependent work or requested status. Do not claim to have seen outputs from this acknowledgment.
generate_sound_effects
ChatGPTRun generate sound effects and return its job acknowledgment immediately. Costs money. The card tracks completion automatically; use get_generations only for dependent work or requested status. Do not claim to have seen outputs from this acknowledgment.
generate_speech
ChatGPTRun generate speech and return its job acknowledgment immediately. Costs money. The card tracks completion automatically; use get_generations only for dependent work or requested status. Do not claim to have seen outputs from this acknowledgment.
generate_video
ChatGPTRun generate video and return its job acknowledgment immediately. Costs money. The card tracks completion automatically; use get_generations only for dependent work or requested status. Do not claim to have seen outputs from this acknowledgment.
get_balance
ChatGPTWhat the current workspace has left to spend, in BOTH wallets: credits (the workspace credit pool) and api_wallet (prepaid USD), plus billing_mode — which of the two generations debit (credits or usd). Check this before a generate, and show the user both numbers before suggesting set_billing_mode.
get_generations
ChatGPTRead 1–4 jobs, optionally waiting up to 20 seconds until all accessible jobs finish. Use only when an output is needed for dependent work or status is requested; standalone generation cards track themselves. The whole status call is bounded to 30 seconds. Legacy JSON-RPC batches do not wait. Returns output asset IDs and URLs, wait_status, wait interruptions, and poll_after_seconds. If jobs are running, wait at least poll_after_seconds before reading again. Never resubmit to check status.
get_model
ChatGPTGet a model's input schema and capabilities — call this before using model_specific_parameters to learn which parameters the model accepts. A model that supports several input modes (text-only, start frame, reference images, ...) routes automatically from the inputs you attach.
isolate_audio
ChatGPTRun isolate audio and return its job acknowledgment immediately. Costs money. The card tracks completion automatically; use get_generations only for dependent work or requested status. Do not claim to have seen outputs from this acknowledgment.
list_models
ChatGPTList Hedra generation models. Returns the public v3 catalog: one entry per model with its public id, modality, and description. Use get_model for a model's input schema.
list_voices
ChatGPTFind voice IDs for generate_speech or convert_speech. Without query, lists your cloned voices followed by the curated library. With query, searches the shared library by description (your clones are in the listing). Pass a returned voice_id as voice.
list_workspaces
ChatGPTList the workspaces the user belongs to and which one this connection currently generates in (is_current). Generations and their charges land in the current workspace; use set_workspace to move the connection.
prepare_upload
ChatGPTPrepare a short-lived, upload-only credential for the Hedra file picker.
query_assets
ChatGPTFind reusable image, video, and audio assets in the user's Hedra library. This searches only the user's library, never the web. Pass asset_ids to fetch known assets, or use query/types/since/until to browse and search. A query matches image and video content by meaning where semantic search is available and always matches literal name, description, and generation-prompt text; results combine both rankings. Without query, results are newest first. Returned asset_id values can be passed directly to generate as {"source": "asset", "asset_id": ...}. Only complete, reusable media assets are returned.
remove_video_background
ChatGPTRun remove video background and return its job acknowledgment immediately. Costs money. The card tracks completion automatically; use get_generations only for dependent work or requested status. Do not claim to have seen outputs from this acknowledgment.
set_billing_mode
ChatGPTChoose which wallet generations in the current workspace debit: "credits" (the workspace credit pool, at credit prices) or "usd" (the prepaid API wallet, at USD prices). Ask the user first, after showing both balances from get_balance. Applies from the NEXT call; estimate/get_generations report prices in the unit of the mode in force. Not available when connected with an API key: set the key's mode where keys are managed.
set_workspace
ChatGPTMove this connection to another of the user's workspaces: later calls generate and bill there. Ask the user first — it changes where their money goes, for every OAuth client connected to their account, and applies from the NEXT call (the current call's workspace is fixed). Not available when connected with an API key: a key is pinned to its workspace.
show_file_upload_widget
ChatGPTUpload local reference images, audio, or videos directly to Hedra using an embedded file picker in MCP Apps hosts. Use this for files on the user's device; ordinary chat attachments are not automatically accessible. Wait for the user to select and upload files; use the resulting file URLs as media inputs. Clients without UI get a Hedra library link and the multipart endpoint for CLI uploads. Never ask users to host files on a third party.
upload_file
ChatGPTUpload a publicly reachable file URL (image, audio, or video) to Hedra and return a URL usable as a generation reference — pass it in the matching _url or _urls argument of the generation or media operation tool. The returned URL is the file handle until the result's file.expires_at. After that, upload the file again for a fresh handle rather than reusing the old URL. Only public http(s) URLs are accepted.
upscale
ChatGPTRun upscale and return its job acknowledgment immediately. Costs money. The card tracks completion automatically; use get_generations only for dependent work or requested status. Do not claim to have seen outputs from this acknowledgment.