22 operations. Call each with POST https://app.chirply.io/api/v1/actions/<name> and a bearer token; the response is { "data": { "action", "summary", "result" } }. A read badge means the operation changes nothing; write requires the credential’s write scope.
Animate an image
ai_studio.animate_imagewriteconfirm
Turn a still image into a moving video clip. SPENDS REAL MONEY on its own fal.ai account — typically several US dollars per clip. The image must be at a public https URL the provider can download, such as one from ai_studio.generate_image. Returns immediately; poll ai_studio.get_generation until it succeeds.
Marked confirm: this operation is irreversible, reaches real people, or spends money. Holding a credential is itself the confirmation for API and MCP callers — call it only when you mean it. The in-app assistant refuses to run it without a human approving first.
Also answers to image to video, make this picture move.
Parameters
Field
Type
Required
Description
imageUrl
string (uri)
required
Public https URL of the image to animate.
prompt
string
required
How the image should move: camera motion, what the subject does.
Over MCP the same operation is the tool ai_studio_animate_image at https://app.chirply.io/api/mcp, same bearer token, same input.
Clean up a recording
ai_studio.clean_up_audiowrite
Strip background noise, music and room echo from a recording, leaving clean speech. Runs on its own ElevenLabs account and consumes their quota. The original is left untouched — this produces a new file.
Also answers to remove background noise, isolate the voice, denoise audio.
Parameters
Field
Type
Required
Description
audioUrl
string (uri)
required
Public https URL of the recording to clean. Maximum 64 MB.
Over MCP the same operation is the tool ai_studio_clean_up_audio at https://app.chirply.io/api/mcp, same bearer token, same input.
Clone a voice
ai_studio.clone_voicewriteconfirm
Create a new voice in its own ElevenLabs account from recordings of someone speaking. The voice is created THERE, occupies one of that account's voice slots, and remains after disconnecting from this account. Instant cloning is restricted on some ElevenLabs plans. Only clone a voice you have the speaker's permission to use.
Marked confirm: this operation is irreversible, reaches real people, or spends money. Holding a credential is itself the confirmation for API and MCP callers — call it only when you mean it. The in-app assistant refuses to run it without a human approving first.
Also answers to copy someone's voice, make a custom voice.
Parameters
Field
Type
Required
Description
name
string
required
What to call the voice in the voice list.
sampleUrls
array of (string (uri))
required
Public https URLs of clean speech samples from the one speaker. More and cleaner is better.
description
string
optional
Optional note about the voice, shown in ElevenLabs.
Over MCP the same operation is the tool ai_studio_clone_voice at https://app.chirply.io/api/mcp, same bearer token, same input.
Change the voice in a recording
ai_studio.convert_voicewrite
Re-perform an existing recording in a different voice, keeping the original delivery, timing and emotion. Useful for putting a consistent brand voice over a rough recording. Runs on its own ElevenLabs account and consumes their quota.
Also answers to speech to speech, swap the voice, change who is speaking.
Parameters
Field
Type
Required
Description
audioUrl
string (uri)
required
Public https URL of the recording to convert. Maximum 64 MB.
voiceId
string
required
The ElevenLabs voice id to perform it in.
removeBackgroundNoise
boolean
optional
Strip background noise from the source first. Default: false
Over MCP the same operation is the tool ai_studio_convert_voice at https://app.chirply.io/api/mcp, same bearer token, same input.
Delete a generation
ai_studio.delete_generationwriteconfirm
Permanently delete a generation and the file it produced from the account's storage. This cannot be undone, and any page, email or campaign already pointing at that file will break.
Marked confirm: this operation is irreversible, reaches real people, or spends money. Holding a credential is itself the confirmation for API and MCP callers — call it only when you mean it. The in-app assistant refuses to run it without a human approving first.
Over MCP the same operation is the tool ai_studio_delete_generation at https://app.chirply.io/api/mcp, same bearer token, same input.
Dub into another language
ai_studio.dub_audiowriteconfirm
Translate a recording or video into another language, re-voiced in the original speakers' own voices. SPENDS REAL MONEY on its own ElevenLabs account, priced by the length of the media. Returns immediately; dubbing takes minutes, so poll ai_studio.get_generation until it succeeds.
Marked confirm: this operation is irreversible, reaches real people, or spends money. Holding a credential is itself the confirmation for API and MCP callers — call it only when you mean it. The in-app assistant refuses to run it without a human approving first.
Also answers to translate this video, dub into spanish, localize audio.
Parameters
Field
Type
Required
Description
sourceUrl
string (uri)
required
Public https URL of the audio or video to dub.
targetLang
string
required
Language code to dub INTO, e.g. "es", "fr", "de".
sourceLang
string
optional
Language code of the original. Omit to detect it automatically.
numSpeakers
integer
optional
How many people speak. 0 or omitted lets ElevenLabs work it out.
Over MCP the same operation is the tool ai_studio_dub_audio at https://app.chirply.io/api/mcp, same bearer token, same input.
Generate an avatar portrait
ai_studio.generate_avatar_portraitwrite
Generate a photorealistic portrait to use as a presenter, or edit an existing one while keeping the same face. Supply referenceImageUrl to keep a character consistent across shots rather than getting a new stranger each time. Runs on the account's own OpenRouter key and is billed to that account at OpenRouter's own rate for the configured image model, which Chirply does not set or mark up. This is the first half of making a talking-head video — feed the result to ai_studio.generate_avatar_video.
Also answers to create a presenter, make an avatar face, generate a headshot.
Parameters
Field
Type
Required
Description
prompt
string
required
Who the person is, or — with a reference image — what to change about them.
referenceImageUrl
string (uri)
optional
Public https URL of an existing portrait to edit, keeping the same face.
Over MCP the same operation is the tool ai_studio_generate_avatar_portrait at https://app.chirply.io/api/mcp, same bearer token, same input.
Generate a talking-head video
ai_studio.generate_avatar_videowriteconfirm
Turn a portrait plus a voiceover into a video of that person speaking the words, lips matched. SPENDS REAL MONEY on its own Replicate account, priced by the length of the audio. Make the voiceover FIRST with ai_studio.generate_voiceover — the video's length and cost follow the audio, so generating in the other order wastes money. Returns immediately; poll ai_studio.get_generation.
Marked confirm: this operation is irreversible, reaches real people, or spends money. Holding a credential is itself the confirmation for API and MCP callers — call it only when you mean it. The in-app assistant refuses to run it without a human approving first.
Also answers to talking head, make an avatar speak, presenter video.
Parameters
Field
Type
Required
Description
imageUrl
string (uri)
required
Public https URL of the portrait to animate.
audioUrl
string (uri)
required
Public https URL of the speech track that drives the mouth.
resolution
"480p" | "720p"
optional
Output resolution. 720p costs more. Default: "720p"
Over MCP the same operation is the tool ai_studio_generate_avatar_video at https://app.chirply.io/api/mcp, same bearer token, same input.
Generate an image
ai_studio.generate_imagewrite
Generate an original image from a description, store it in the account's permanent storage, and return a public URL that can be dropped straight into a funnel page, email or campaign. Runs on the account's own OpenRouter key and is billed to that account at OpenRouter's own rate for the configured image model, which Chirply does not set or mark up. Nothing is published or sent.
Also answers to make a picture, create an image, text to image.
Parameters
Field
Type
Required
Description
prompt
string
required
Visual subject and composition. Generated images contain no text or logos.
style
"photo" | "illustration" | "product" | "abstract"
optional
Visual treatment: an editorial photo, a flat illustration, a product render, or an abstract background. Default: "photo"
aspect
string
optional
Framing hint passed to the model, e.g. "16:9 landscape", "square", "9:16 portrait". Default: "16:9 landscape"
Over MCP the same operation is the tool ai_studio_generate_image at https://app.chirply.io/api/mcp, same bearer token, same input.
Generate a music track
ai_studio.generate_musicwriteconfirm
Compose an original music track from a description of the style and mood. SPENDS REAL MONEY on its own ElevenLabs account — a full-length track consumes substantially more credit than a voiceover, and music generation is unavailable on the ElevenLabs free tier.
Marked confirm: this operation is irreversible, reaches real people, or spends money. Holding a credential is itself the confirmation for API and MCP callers — call it only when you mean it. The in-app assistant refuses to run it without a human approving first.
Also answers to make background music, compose a track, create a soundtrack.
Parameters
Field
Type
Required
Description
prompt
string
required
Genre, mood, instrumentation, tempo — e.g. "warm acoustic guitar bed, hopeful, no drums".
lengthSeconds
integer
optional
How long the track should be. Omit to let the model decide.
instrumental
boolean
optional
Force an instrumental with no vocals — the right choice for anything playing under a voiceover. Default: false
Over MCP the same operation is the tool ai_studio_generate_music at https://app.chirply.io/api/mcp, same bearer token, same input.
Generate a song
ai_studio.generate_songwriteconfirm
Write and perform a complete song — music and sung vocals — from a style description and optional lyrics. SPENDS REAL MONEY on its own Replicate account. Returns immediately; generation takes minutes, so poll ai_studio.get_generation until it succeeds.
Marked confirm: this operation is irreversible, reaches real people, or spends money. Holding a credential is itself the confirmation for API and MCP callers — call it only when you mean it. The in-app assistant refuses to run it without a human approving first.
Also answers to write me a song, make a jingle, compose a song with vocals.
Parameters
Field
Type
Required
Description
prompt
string
required
Style, genre, mood and instrumentation — e.g. "upbeat indie pop, female vocal, handclaps".
lyrics
string
optional
The words to sing. Use [Verse], [Chorus] and [Bridge] tags to shape the structure. Omit to have the model write them.
instrumental
boolean
optional
Produce music with no vocals. Requires a style description. Default: false
modelId
"minimax/music-2.6" | "lucataco/ace-step"
optional
Which song model to use. Default: "minimax/music-2.6"
durationSeconds
integer
optional
Track length. Only ACE-Step honours this; MiniMax takes its length from the lyrics.
Over MCP the same operation is the tool ai_studio_generate_song at https://app.chirply.io/api/mcp, same bearer token, same input.
Generate a sound effect
ai_studio.generate_sound_effectwrite
Generate a short sound effect from a description — a whoosh, a notification chime, ambient room tone. Runs on its own ElevenLabs account and consumes a small amount of their quota.
Also answers to make a sound, sfx, create a sound effect.
Parameters
Field
Type
Required
Description
text
string
required
The sound to create, e.g. "heavy wooden door creaking open".
durationSeconds
number
optional
How long it should be. Omit to let the model decide.
promptInfluence
number
optional
How literally to follow the description. Higher is more faithful, lower more creative. Default: 0.3
loop
boolean
optional
Make it loop seamlessly, for ambient beds. Default: false
Over MCP the same operation is the tool ai_studio_generate_sound_effect at https://app.chirply.io/api/mcp, same bearer token, same input.
Generate a video
ai_studio.generate_videowriteconfirm
Generate a video clip from a written description. SPENDS REAL MONEY on its own fal.ai account — a few seconds of video typically costs several US dollars, far more than an image, and a failed or unwanted result is not refundable. Returns immediately with a generation id; rendering takes minutes, so poll ai_studio.get_generation until it succeeds.
Marked confirm: this operation is irreversible, reaches real people, or spends money. Holding a credential is itself the confirmation for API and MCP callers — call it only when you mean it. The in-app assistant refuses to run it without a human approving first.
Also answers to make a video, text to video, create a video clip.
Parameters
Field
Type
Required
Description
prompt
string
required
What happens in the shot: subject, action, setting, camera movement, mood.
Over MCP the same operation is the tool ai_studio_generate_video at https://app.chirply.io/api/mcp, same bearer token, same input.
Generate a voiceover
ai_studio.generate_voiceoverwrite
Read text aloud in a chosen voice and save the audio to the library with a public URL. Runs on its own ElevenLabs account and consumes their character quota. Nothing is played to anyone or attached to a call — it just produces a file you can use in a video, an IVR prompt, or a campaign.
Also answers to text to speech, narrate this, make a voiceover.
Parameters
Field
Type
Required
Description
text
string
required
The words to speak.
voiceId
string
optional
An ElevenLabs voice id from ai_studio.list_voices. Omit to use the account's default voice.
Over MCP the same operation is the tool ai_studio_generate_voiceover at https://app.chirply.io/api/mcp, same bearer token, same input.
Check a generation
ai_studio.get_generationread
Fetch one generation's current state and, once finished, the URL of the file it produced. THIS IS THE POLLING CALL for video, avatar, song and dubbing jobs: keep calling it until status is "succeeded" or "failed". It also advances any of this account's in-flight jobs, so polling here is what moves them along. Read-only; generates nothing and costs nothing.
Also answers to check generation status, is my video ready.
Parameters
Field
Type
Required
Description
id
string (uuid)
required
The generation id returned when the job was started.
Over MCP the same operation is the tool ai_studio_get_generation at https://app.chirply.io/api/mcp, same bearer token, same input.
Lip-sync a video to new audio
ai_studio.lipsync_videowriteconfirm
Re-time a person's mouth in a video to match a different audio track — for dubbing a recording or swapping the voiceover. SPENDS REAL MONEY on its own fal.ai account. Both files must be at public https URLs. Returns immediately; poll ai_studio.get_generation.
Marked confirm: this operation is irreversible, reaches real people, or spends money. Holding a credential is itself the confirmation for API and MCP callers — call it only when you mean it. The in-app assistant refuses to run it without a human approving first.
Also answers to dub a video, sync lips to audio.
Parameters
Field
Type
Required
Description
videoUrl
string (uri)
required
Public https URL of the video containing the face.
audioUrl
string (uri)
required
Public https URL of the audio the mouth should match.
quality
"standard" | "pro"
optional
Pro is noticeably better on close-ups and costs roughly two-thirds more. Default: "standard"
Over MCP the same operation is the tool ai_studio_lipsync_video at https://app.chirply.io/api/mcp, same bearer token, same input.
AI Studio library
ai_studio.list_generationsread
List everything the AI Studio has generated for this account — images, video, voiceovers, music, avatars, songs and transcripts — newest first. Read-only; generates nothing and costs nothing.
Also answers to list generated media, my AI generations, media library.
Over MCP the same operation is the tool ai_studio_list_generations at https://app.chirply.io/api/mcp, same bearer token, same input.
Video models
ai_studio.list_video_modelsread
List the video models the AI Studio can use, with what each one supports — clip lengths, aspect ratios, resolutions, and whether it generates its own audio. Read-only; costs nothing. Use it to pick a model id before calling ai_studio.generate_video.
Parameters
Field
Type
Required
Description
mode
"text_to_video" | "image_to_video"
optional
Filter to models driven by a prompt, or ones that animate a still image.
Over MCP the same operation is the tool ai_studio_list_video_models at https://app.chirply.io/api/mcp, same bearer token, same input.
Voices
ai_studio.list_voicesread
List the voices in its own ElevenLabs account, including any cloned ones. Read-only; costs nothing. Use it to pick a voice id for ai_studio.generate_voiceover or ai_studio.convert_voice.
Over MCP the same operation is the tool ai_studio_list_voices at https://app.chirply.io/api/mcp, same bearer token, same input.
Remove a video's background
ai_studio.remove_video_backgroundwriteconfirm
Cut the background out of a video, leaving the subject on transparency — for overlaying a presenter on a slide or page. SPENDS REAL MONEY on its own fal.ai account. Defaults to WebM output because it is the only format that carries real transparency; MP4 renders the removed background as solid black. Returns immediately; poll ai_studio.get_generation.
Marked confirm: this operation is irreversible, reaches real people, or spends money. Holding a credential is itself the confirmation for API and MCP callers — call it only when you mean it. The in-app assistant refuses to run it without a human approving first.
Also answers to green screen a video, cut out video background.
Parameters
Field
Type
Required
Description
videoUrl
string (uri)
required
Public https URL of the video to process.
outputFormat
"webm" | "mp4"
optional
WebM keeps transparency. Choose MP4 only if you need it and can accept a black background. Default: "webm"
Over MCP the same operation is the tool ai_studio_remove_video_background at https://app.chirply.io/api/mcp, same bearer token, same input.
Transcribe a recording
ai_studio.transcribe_audiowrite
Turn a recording into text, optionally labelling who spoke each line. Returns the transcript directly and saves it to the library. Runs on its own ElevenLabs account and consumes their quota.
Also answers to speech to text, write out what was said, get a transcript.
Parameters
Field
Type
Required
Description
audioUrl
string (uri)
required
Public https URL of the audio or video to transcribe. Maximum 64 MB.
diarize
boolean
optional
Label each word with which speaker said it. Costs more; worth it for interviews and calls. Default: false
languageCode
string
optional
ISO language code of the speech. Omit to detect it automatically.
Over MCP the same operation is the tool ai_studio_transcribe_audio at https://app.chirply.io/api/mcp, same bearer token, same input.
Upscale a video
ai_studio.upscale_videowriteconfirm
Increase a video's resolution and sharpness with Topaz, optionally raising its frame rate. SPENDS REAL MONEY on its own fal.ai account, priced by the length and resolution of the input. Returns immediately; poll ai_studio.get_generation until it succeeds.
Marked confirm: this operation is irreversible, reaches real people, or spends money. Holding a credential is itself the confirmation for API and MCP callers — call it only when you mean it. The in-app assistant refuses to run it without a human approving first.
Also answers to enhance video quality, make video higher resolution.
Parameters
Field
Type
Required
Description
videoUrl
string (uri)
required
Public https URL of the video to upscale.
upscaleFactor
integer
optional
How much to enlarge it. 2 doubles each dimension. Default: 2
targetFps
integer
optional
Interpolate to this frame rate. Omit to keep the original.