RegiAI
AI image, video and audio tools: generate, edit, face swap, upscale, remove backgrounds, make video.
Should I use this
Quality & Safety
Findings (4)
- LOWTool 'regiai_get_balance' description lacks action verbin regiai_get_balance
- LOWTool 'upscale_image' description lacks action verbin upscale_image
- LOWTool 'restore_photo' description lacks action verbin restore_photo
- LOWTool 'unblur_image' description lacks action verbin unblur_image
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"regiai": {
"url": "https://regiai.com/api/mcp"
}
}
}Remote endpoints
https://regiai.com/api/mcpstreamable-httpWhat it can do
Tool inventory
Tools (51)
🟢regiai_get_balance
Return the remaining RegiAI credit balance in USD for this API token.
Input Schema
{
"type": "object",
"properties": {},
"required": []
}🟢regiai_list_tools
List every RegiAI tool (image, video, audio) with its inputs and price.
Input Schema
{
"type": "object",
"properties": {},
"required": []
}🟡generate_image(prompt, image, aspect_ratio)
Generate a new image from a text prompt, or edit an input image with a prompt. $0.10 per image.
Input Schema
{
"type": "object",
"properties": {
"prompt": {
"type": "string",
"description": "What to create, or how to edit the input image."
},
"image": {
"type": "string",
"description": "Input image as a public https URL or a base64 data URI."
},
"aspect_ratio": {
"type": "string",
"enum": [
"1:1",
"16:9",
"9:16",
"4:3",
"3:4",
"3:2",
"2:3"
]
}
},
"required": [
"prompt"
]
}⚪upscale_image(image)
Increase image resolution and detail. $0.03 per image.
Input Schema
{
"type": "object",
"properties": {
"image": {
"type": "string",
"description": "Input image as a public https URL or a base64 data URI."
}
},
"required": [
"image"
]
}🔴remove_background(image)
Cut out the subject and return a transparent PNG. $0.10 per image.
Input Schema
{
"type": "object",
"properties": {
"image": {
"type": "string",
"description": "Input image as a public https URL or a base64 data URI."
}
},
"required": [
"image"
]
}🔴remove_watermark(image)
Remove watermarks, logos and overlaid text. $0.10 per image.
Input Schema
{
"type": "object",
"properties": {
"image": {
"type": "string",
"description": "Input image as a public https URL or a base64 data URI."
}
},
"required": [
"image"
]
}⚪restore_photo(image)
Repair scratches and damage in old photos. $0.10 per image.
Input Schema
{
"type": "object",
"properties": {
"image": {
"type": "string",
"description": "Input image as a public https URL or a base64 data URI."
}
},
"required": [
"image"
]
}⚪unblur_image(image)
Sharpen a blurry photo. $0.05 per image.
Input Schema
{
"type": "object",
"properties": {
"image": {
"type": "string",
"description": "Input image as a public https URL or a base64 data URI."
}
},
"required": [
"image"
]
}🟡face_swap(image, target_image)
Put the face from "image" onto the person in "target_image". $0.10 per swap.
Input Schema
{
"type": "object",
"properties": {
"image": {
"type": "string",
"description": "Input image as a public https URL or a base64 data URI."
},
"target_image": {
"type": "string",
"description": "Input image as a public https URL or a base64 data URI."
}
},
"required": [
"image",
"target_image"
]
}🟢describe_image(image)
Get a detailed text description of an image. $0.01 per image.
Input Schema
{
"type": "object",
"properties": {
"image": {
"type": "string",
"description": "Input image as a public https URL or a base64 data URI."
}
},
"required": [
"image"
]
}🟢image_to_text(image)
Extract all readable text from an image. $0.01 per image.
Input Schema
{
"type": "object",
"properties": {
"image": {
"type": "string",
"description": "Input image as a public https URL or a base64 data URI."
}
},
"required": [
"image"
]
}🟢answer_picture_question(image)
Solve the math, physics or chemistry problem shown in an image. $0.01 per image.
Input Schema
{
"type": "object",
"properties": {
"image": {
"type": "string",
"description": "Input image as a public https URL or a base64 data URI."
}
},
"required": [
"image"
]
}🟢analyze_image(prompt, image, system_prompt)
Ask any question about an image, with an optional system prompt. $0.01 per call.
Input Schema
{
"type": "object",
"properties": {
"prompt": {
"type": "string",
"description": "Question or instruction about the image."
},
"image": {
"type": "string",
"description": "Input image as a public https URL or a base64 data URI."
},
"system_prompt": {
"type": "string",
"description": "Optional system prompt to steer the answer."
}
},
"required": [
"prompt"
]
}🟢ai_image_generator(prompt, model, aspect_ratio)
Text to image with 12 models. from $0.01. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"prompt": {
"type": "string",
"description": "Describe your image (max 2000 characters)"
},
"model": {
"type": "string",
"enum": [
"nano-banana",
"nano-banana-pro",
"flux-schnell",
"flux-dev",
"flux-1.1-pro",
"flux-1.1-pro-ultra",
"ideogram-v3-turbo",
"ideogram-v3-quality",
"recraft-v3",
"seedream-4",
"qwen-image",
"photon"
],
"description": "Model"
},
"aspect_ratio": {
"type": "string",
"enum": [
"1:1",
"3:4",
"4:3",
"9:16",
"16:9"
],
"description": "Aspect ratio"
}
},
"required": [
"prompt"
]
}🟡ai_image_editor(image, prompt)
Edit photos with a prompt. $0.03 per image. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"image": {
"type": "string",
"description": "Photo to edit: public https URL or base64 data URI (image)."
},
"prompt": {
"type": "string",
"description": "What should change? (max 1000 characters)"
}
},
"required": [
"image",
"prompt"
]
}🟢ai_clothes_changer(person_image, garment_image)
Try on outfits virtually. $0.05 per try-on. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"person_image": {
"type": "string",
"description": "Photo of the person: public https URL or base64 data URI (image)."
},
"garment_image": {
"type": "string",
"description": "Garment: public https URL or base64 data URI (image)."
}
},
"required": [
"person_image",
"garment_image"
]
}🟢ai_head_swap(body_image, head_image)
Swap heads in photos. $0.10 per swap. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"body_image": {
"type": "string",
"description": "Body photo (keeps pose and outfit): public https URL or base64 data URI (image)."
},
"head_image": {
"type": "string",
"description": "Head photo (face and hair to use): public https URL or base64 data URI (image)."
}
},
"required": [
"body_image",
"head_image"
]
}🟡ai_face_editor(image, expression)
Change facial expressions. $0.03 per image. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"image": {
"type": "string",
"description": "Portrait photo: public https URL or base64 data URI (image)."
},
"expression": {
"type": "string",
"enum": [
"smile",
"laugh",
"surprised",
"wink",
"serious",
"sad",
"angry",
"look_left",
"look_right"
],
"description": "New expression"
}
},
"required": [
"image",
"expression"
]
}🟢ai_image_expander(image, aspect_ratio, prompt)
Extend images with AI. $0.03 per image. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"image": {
"type": "string",
"description": "Photo to expand: public https URL or base64 data URI (image)."
},
"aspect_ratio": {
"type": "string",
"enum": [
"16:9",
"9:16",
"1:1",
"4:3",
"21:9"
],
"description": "New shape"
},
"prompt": {
"type": "string",
"description": "Describe the surroundings (optional) (max 300 characters)"
}
},
"required": [
"image"
]
}🟢ai_photo_colorizer(image)
Colorize black & white photos. $0.03 per photo. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"image": {
"type": "string",
"description": "Black and white photo: public https URL or base64 data URI (image)."
}
},
"required": [
"image"
]
}🟢ai_selfie_generator(input_image, style, persona)
Stylized selfies and avatars. $0.10 per image. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"input_image": {
"type": "string",
"description": "Your selfie: public https URL or base64 data URI (image)."
},
"style": {
"type": "string",
"enum": [
"Anime",
"Cartoon",
"Clay",
"Graphic Novel",
"Pixel Art",
"Lego",
"Memoji",
"Minecraft",
"Minimalist",
"Gothic"
],
"description": "Style"
},
"persona": {
"type": "string",
"enum": [
"None",
"Astronaut",
"Samurai",
"Ninja",
"Mage",
"Robot",
"Angel",
"Vampire"
],
"description": "Character (optional)"
}
},
"required": [
"input_image"
]
}🟢ai_anime_filter(image)
Turn photos into anime. $0.03 per image. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"image": {
"type": "string",
"description": "Photo: public https URL or base64 data URI (image)."
}
},
"required": [
"image"
]
}🟢multiple_face_swap(group_image, face_1, face_2, face_3, face_4, ...)
Swap several faces in one photo. $0.35 per photo. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"group_image": {
"type": "string",
"description": "Group photo: public https URL or base64 data URI (image)."
},
"face_1": {
"type": "string",
"description": "Face for person 1 (left): public https URL or base64 data URI (image)."
},
"face_2": {
"type": "string",
"description": "Face for person 2: public https URL or base64 data URI (image)."
},
"face_3": {
"type": "string",
"description": "Face for person 3: public https URL or base64 data URI (image)."
},
"face_4": {
"type": "string",
"description": "Face for person 4: public https URL or base64 data URI (image)."
},
"consent": {
"type": "boolean",
"description": "I have permission to use these faces"
}
},
"required": [
"group_image",
"face_1",
"face_2",
"consent"
]
}🟡ai_body_swap(person_image, body_image, consent)
Put yourself in any body and outfit. $0.10 per swap. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"person_image": {
"type": "string",
"description": "Your photo (face and hair to keep): public https URL or base64 data URI (image)."
},
"body_image": {
"type": "string",
"description": "Body photo (pose, outfit and scene): public https URL or base64 data URI (image)."
},
"consent": {
"type": "boolean",
"description": "I have permission to use these faces"
}
},
"required": [
"person_image",
"body_image",
"consent"
]
}🟡ai_outfit_changer(image, outfit)
Change outfits with a prompt. $0.10 per image. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"image": {
"type": "string",
"description": "Your photo: public https URL or base64 data URI (image)."
},
"outfit": {
"type": "string",
"description": "Describe the new outfit (max 500 characters)"
}
},
"required": [
"image",
"outfit"
]
}🟢ai_dress_changer(image, style, color)
Try on dresses in one click. $0.10 per image. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"image": {
"type": "string",
"description": "Your photo: public https URL or base64 data URI (image)."
},
"style": {
"type": "string",
"enum": [
"evening",
"wedding",
"cocktail",
"summer",
"saree",
"lehenga",
"qipao",
"kimono",
"prom",
"business"
],
"description": "Dress style"
},
"color": {
"type": "string",
"description": "Color or details (optional) (max 120 characters)"
}
},
"required": [
"image"
]
}🟢braces_filter(image, style, color)
See yourself with braces. $0.10 per image. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"image": {
"type": "string",
"description": "Smiling photo: public https URL or base64 data URI (image)."
},
"style": {
"type": "string",
"enum": [
"metal",
"clear",
"color"
],
"description": "Braces"
},
"color": {
"type": "string",
"enum": [
"blue",
"pink",
"purple",
"red",
"green",
"black",
"rainbow"
],
"description": "Band color (colored braces)"
}
},
"required": [
"image"
]
}🟢ai_couple_photo_generator(person_1, person_2, scene, details, consent)
Make couple photos from two selfies. $0.10 per photo. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"person_1": {
"type": "string",
"description": "First person: public https URL or base64 data URI (image)."
},
"person_2": {
"type": "string",
"description": "Second person: public https URL or base64 data URI (image)."
},
"scene": {
"type": "string",
"enum": [
"beach",
"paris",
"cafe",
"wedding",
"studio",
"snow",
"christmas",
"city"
],
"description": "Scene"
},
"details": {
"type": "string",
"description": "Extra details (optional) (max 200 characters)"
},
"consent": {
"type": "boolean",
"description": "I have permission to use these faces"
}
},
"required": [
"person_1",
"person_2",
"consent"
]
}🟢ai_video_generator(prompt, image, duration, aspect_ratio)
Text and image to video. from $0.50. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"prompt": {
"type": "string",
"description": "Prompt (max 1500 characters)"
},
"image": {
"type": "string",
"description": "Start image (image to video): public https URL or base64 data URI (image)."
},
"duration": {
"type": "string",
"enum": [
"5",
"10"
],
"description": "Duration"
},
"aspect_ratio": {
"type": "string",
"enum": [
"16:9",
"9:16",
"1:1",
"4:3",
"3:4"
],
"description": "Aspect ratio"
}
},
"required": [
"prompt"
]
}🟢ai_talking_photo(image, voice_script, voice, voice_language)
Make photos talk. $0.40 per 100 characters. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"image": {
"type": "string",
"description": "Portrait photo: public https URL or base64 data URI (image)."
},
"voice_script": {
"type": "string",
"description": "What should they say? (max 400 characters)"
},
"voice": {
"type": "string",
"enum": [
"Zephyr (Female)",
"Kore (Female)",
"Leda (Female)",
"Aoede (Female)",
"Despina (Female)",
"Sulafat (Female)",
"Puck (Male)",
"Charon (Male)",
"Fenrir (Male)",
"Orus (Male)",
"Enceladus (Male)",
"Achird (Male)"
],
"description": "Voice"
},
"voice_language": {
"type": "string",
"enum": [
"English (US)",
"English (UK)",
"Spanish",
"French",
"German",
"Italian",
"Portuguese (Brazil)",
"Japanese",
"Korean",
"Hindi"
],
"description": "Language"
}
},
"required": [
"image",
"voice_script"
]
}🟢ai_lip_sync(video, audio, consent)
Sync lips to any audio. $0.35 per video (up to 10s). Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"video": {
"type": "string",
"description": "Video with a visible face: public https URL or base64 data URI (video)."
},
"audio": {
"type": "string",
"description": "New voice audio: public https URL or base64 data URI (audio)."
},
"consent": {
"type": "boolean",
"description": "I have permission to use these faces"
}
},
"required": [
"video",
"audio",
"consent"
]
}🟢ai_face_swap_video(face, video, consent)
Swap faces in videos. $0.75 per video (up to 10s). Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"face": {
"type": "string",
"description": "Face photo (the new face): public https URL or base64 data URI (image)."
},
"video": {
"type": "string",
"description": "Video: public https URL or base64 data URI (video)."
},
"consent": {
"type": "boolean",
"description": "I have permission to use these faces"
}
},
"required": [
"face",
"video",
"consent"
]
}🟢gif_face_swap(face, gif, consent)
Swap faces in GIFs. $0.75 per GIF (up to 10s). Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"face": {
"type": "string",
"description": "Face photo (the new face): public https URL or base64 data URI (image)."
},
"gif": {
"type": "string",
"description": "GIF"
},
"consent": {
"type": "boolean",
"description": "I have permission to use these faces"
}
},
"required": [
"face",
"gif",
"consent"
]
}🟢image_to_video(image, prompt, duration)
Animate any photo. from $0.50. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"image": {
"type": "string",
"description": "Photo to animate: public https URL or base64 data URI (image)."
},
"prompt": {
"type": "string",
"description": "Describe the motion (max 1500 characters)"
},
"duration": {
"type": "string",
"enum": [
"5",
"10"
],
"description": "Duration"
}
},
"required": [
"image",
"prompt"
]
}🟢text_to_video(prompt, duration, aspect_ratio)
Turn a prompt into a video. from $0.50. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"prompt": {
"type": "string",
"description": "Describe your video (max 1500 characters)"
},
"duration": {
"type": "string",
"enum": [
"5",
"10"
],
"description": "Duration"
},
"aspect_ratio": {
"type": "string",
"enum": [
"16:9",
"9:16",
"1:1",
"4:3",
"3:4"
],
"description": "Aspect ratio"
}
},
"required": [
"prompt"
]
}🟢ai_character_replace(video, character_image, prompt, resolution)
Replace characters in videos. from $0.75. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"video": {
"type": "string",
"description": "Video with the person to replace: public https URL or base64 data URI (video)."
},
"character_image": {
"type": "string",
"description": "New character: public https URL or base64 data URI (image)."
},
"prompt": {
"type": "string",
"description": "Instructions (optional) (max 500 characters)"
},
"resolution": {
"type": "string",
"enum": [
"720",
"1080"
],
"description": "Quality"
}
},
"required": [
"video",
"character_image"
]
}🟢ai_video_restyle(video, prompt, quality)
Restyle videos with a prompt. from $0.60. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"video": {
"type": "string",
"description": "Video to restyle: public https URL or base64 data URI (video)."
},
"prompt": {
"type": "string",
"description": "New style (max 800 characters)"
},
"quality": {
"type": "string",
"enum": [
"standard",
"draft"
],
"description": "Quality"
}
},
"required": [
"video",
"prompt"
]
}🟢ai_video_upscaler(video)
Upscale videos to 1080p. $0.80 per video (up to 10s, 1080p). Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"video": {
"type": "string",
"description": "Video to upscale: public https URL or base64 data URI (video)."
}
},
"required": [
"video"
]
}🟢ai_subtitle_generator(video, language, translate)
Generate SRT subtitles. $0.10 per video. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"video": {
"type": "string",
"description": "Video: public https URL or base64 data URI (video)."
},
"language": {
"type": "string",
"enum": [
"auto",
"en",
"es",
"fr",
"de",
"it",
"pt",
"ru",
"tr",
"ar",
"hi",
"ja",
"ko",
"zh",
"az"
],
"description": "Spoken language"
},
"translate": {
"type": "boolean",
"description": "Translate to English"
}
},
"required": [
"video"
]
}🟡ai_video_to_audio(video, prompt)
Add sound to silent videos. $0.05 per video. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"video": {
"type": "string",
"description": "Silent video: public https URL or base64 data URI (video)."
},
"prompt": {
"type": "string",
"description": "Describe the sound (optional) (max 300 characters)"
}
},
"required": [
"video"
]
}🟢ai_video_extender(video, prompt)
Make clips longer. $1.50 per extension (+6s). Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"video": {
"type": "string",
"description": "Video to extend: public https URL or base64 data URI (video)."
},
"prompt": {
"type": "string",
"description": "What happens next? (max 800 characters)"
}
},
"required": [
"video",
"prompt"
]
}🟢ai_video_colorizer(video)
Colorize old videos. $0.10 per video (up to 30s). Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"video": {
"type": "string",
"description": "Black and white video: public https URL or base64 data URI (video)."
}
},
"required": [
"video"
]
}🟢ai_voice_generator(text, voice_id, emotion)
Text to natural speech. $0.15 per 1,000 characters (min $0.05). Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "Text to speak (max 5000 characters)"
},
"voice_id": {
"type": "string",
"enum": [
"English_Wiselady",
"English_Deep-VoicedGentleman",
"English_CaptivatingStoryteller",
"English_FriendlyPerson",
"English_CalmWoman",
"English_ConfidentWoman",
"English_Trustworth_Man",
"English_PlayfulGirl",
"English_Graceful_Lady",
"English_MaturePartner",
"English_Comedian",
"English_Aussie_Bloke",
"French_FemaleAnchor",
"German_FriendlyMan",
"Spanish_Narrator",
"Italian_Narrator"
],
"description": "Voice"
},
"emotion": {
"type": "string",
"enum": [
"auto",
"happy",
"calm",
"sad",
"surprised",
"angry",
"neutral"
],
"description": "Emotion"
}
},
"required": [
"text"
]
}🟢ai_voice_cloner(reference_audio, reference_text, text, language, consent)
Clone a voice from a sample. $0.10 per 1,000 characters. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"reference_audio": {
"type": "string",
"description": "Voice sample (10–30 seconds): public https URL or base64 data URI (audio)."
},
"reference_text": {
"type": "string",
"description": "What is said in the sample (optional, improves accuracy) (max 500 characters)"
},
"text": {
"type": "string",
"description": "Text for the cloned voice (max 2000 characters)"
},
"language": {
"type": "string",
"enum": [
"auto",
"English",
"Spanish",
"French",
"German",
"Italian",
"Portuguese",
"Russian",
"Japanese",
"Korean",
"Chinese"
],
"description": "Language"
},
"consent": {
"type": "boolean",
"description": "This is my voice, or I have permission to clone it"
}
},
"required": [
"reference_audio",
"text",
"consent"
]
}🟢ai_music_generator(prompt, lyrics, is_instrumental)
Songs from a prompt. $0.40 per song. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"prompt": {
"type": "string",
"description": "Style and mood (max 2000 characters)"
},
"lyrics": {
"type": "string",
"description": "Lyrics (optional) (max 3000 characters)"
},
"is_instrumental": {
"type": "boolean",
"description": "Instrumental (no vocals)"
}
},
"required": [
"prompt"
]
}🟡ai_voice_changer(source_audio, reference_audio, consent)
Change a voice in any recording. $0.05 per recording. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"source_audio": {
"type": "string",
"description": "Recording to change: public https URL or base64 data URI (audio)."
},
"reference_audio": {
"type": "string",
"description": "Target voice sample: public https URL or base64 data URI (audio)."
},
"consent": {
"type": "boolean",
"description": "I have permission to use the target voice"
}
},
"required": [
"source_audio",
"reference_audio",
"consent"
]
}🟢ai_audio_translator(video, target_language)
Dub speech into 18 languages. $0.09 per second (min $0.50). Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"video": {
"type": "string",
"description": "Video with speech: public https URL or base64 data URI (video)."
},
"target_language": {
"type": "string",
"enum": [
"en",
"es",
"fr",
"de",
"it",
"pt",
"ru",
"tr",
"ar",
"hi",
"ja",
"ko",
"zh",
"nl",
"pl",
"uk",
"id",
"az"
],
"description": "Translate to"
}
},
"required": [
"video"
]
}🟢ai_speech_to_text(audio, language, translate)
Transcribe audio to text. $0.05 per file. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"audio": {
"type": "string",
"description": "Audio file: public https URL or base64 data URI (audio)."
},
"language": {
"type": "string",
"enum": [
"auto",
"en",
"es",
"fr",
"de",
"it",
"pt",
"ru",
"tr",
"ar",
"hi",
"ja",
"ko",
"zh",
"az"
],
"description": "Language"
},
"translate": {
"type": "boolean",
"description": "Translate to English"
}
},
"required": [
"audio"
]
}🟢ai_sound_effects(prompt, duration)
Sound effects from text. $0.05 per sound. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"prompt": {
"type": "string",
"description": "Describe the sound (max 500 characters)"
},
"duration": {
"type": "string",
"enum": [
"5",
"10",
"20",
"30"
],
"description": "Length"
}
},
"required": [
"prompt"
]
}🟢ai_vocal_remover(audio, keep)
Separate vocals and music. $0.10 per song. Runs asynchronously: returns a generation_id; call get_generation until status is "completed".
Input Schema
{
"type": "object",
"properties": {
"audio": {
"type": "string",
"description": "Song: public https URL or base64 data URI (audio)."
},
"keep": {
"type": "string",
"enum": [
"instrumental",
"vocals"
],
"description": "Keep"
}
},
"required": [
"audio"
]
}🟢get_generation(generation_id)
Check the status of a generation started by any asynchronous RegiAI tool. Returns output_url (or output_text) once status is "completed".
Input Schema
{
"type": "object",
"properties": {
"generation_id": {
"type": "integer",
"description": "The generation_id returned when the tool was started."
}
},
"required": [
"generation_id"
]
}Community
Evidence