Skip to content
Agents tracked: 444 Releases (7d): 644 Agent status: 6 with issuesSince last limit reset: Claude 31d · Codex 3d Updated Oct 23, 2026
AgentGid
✦ Ask

Video from a prompt: product recipe

For short videos made from a text prompt: script, voiceover, music, footage or generated clips, rendered in code. Every service below is from AgentGid's catalog, with the price and free tier from its official page; the first pick in each part ranks best on free tier, official MCP server, real use and price.

agent.md

What it costs

To start
Paid parts
no free tier listed: Runway API, Leonardo API
If you outgrow the free tiers
about $105 / month
ElevenLabs Music API $6, Cloudinary $99; billed by usage: Runway API, Deepgram
Model, per 1,000 video scripts
about $0.95
Claude Haiku 5.5; $7.12 with Gemini 3.8 Flash; AgentGid estimate at ~2,000 input + 1,500 output tokens each

How it fits together

  1. The model writes a script and a shot list from the prompt.
  2. Generate the voiceover, music and images or clips with the APIs below.
  3. Assemble and render in code (Remotion or ffmpeg) or with a rendering API, with captions.
  4. Store the files and serve them from storage with a CDN.

Video generation

Runway API first pick
MCP
 Video and image generation API with Runway Gen-4.5 and third-party models.
No free tier listed · $0.01 per credit; gen4.5 12 credits/sec, gen4_turbo 5 credits/sec · in 3 public agent repos
npm install @runwayml/sdk pip install runwayml agent.md
Luma API (Ray / Uni)
MCP
 Ray3.2 video and Uni-1.1 image generation API.
No free tier listed · Ray3.2: $0.15 per 5s video (540p), $0.30 (720p), $1.20 (1080p) · in 4 public agent repos
npm install lumaai pip install lumaai agent.md
Shotstack Video rendering and editing API, billed per minute of video made.
Free: 10 free credits to start · paid from $39/mo · Pay as you go: $10 for 50 minutes
npm install shotstack-sdk pip install shotstack-sdk agent.md

Also fits: D-ID API, Veo (Gemini API), Genmo, Loom · all video generation apis

Voiceover

Deepgram first pick
MCP
 Real-time and batch speech-to-text, text-to-speech and voice-agent APIs.
Free: $200 credit, no credit card · Nova-3 streaming $0.0048/min (promo; regular $0.0077); pre-recorded $0.0043/min; Flux $0.0065/min (promo); Au… · in 76 public agent repos
npm install @deepgram/sdk pip install deepgram-sdk agent.md
Retell AI
MCP
 Platform and API for phone voice agents and chat agents, billed per minute or message.
Free: $10 in free credits · $0.07-$0.31/min for AI voice agents; $0.002+/msg for chat agents · in 254 public agent repos
npm install retell-sdk pip install retell-sdk agent.md

Also fits: Cartesia, Vapi (voice agent API), Fish Audio API, ElevenLabs · all voice (speech-to-text, text-to-speech)

Music and sound

ElevenLabs Music API first pick
MCP
 Text-to-music generation (Eleven Music) up to 5 minutes per track.
Free: Free plan: 3 music minutes/month · paid from $6/mo · $0.15 per minute
npm install @elevenlabs/elevenlabs-js pip install elevenlabs agent.md
ElevenLabs Sound Effects API
MCP
 Text-to-sound-effects generation, royalty-free, MP3 or WAV output.
Free: Free plan: 8 sound-effect generations/month · paid from $6/mo · $0.12 per minute
npm install @elevenlabs/elevenlabs-js pip install elevenlabs agent.md

Also fits: AIVA, Descript, Riffusion, Stable Audio API · all sound effects and music generation

Images and thumbnails

Leonardo API first pick
MCP
 Image and video generation API with multiple models, billed pay-as-you-go.
No free tier listed
npm install @leonardo-ai/sdk pip install leonardo-ai-sdk agent.md
OpenAI Image API (GPT Image) GPT Image models for image generation and editing via Images and Responses APIs.
No free tier listed · gpt-image-2 1024x1024: $0.006 low / $0.053 medium / $0.211 high per image
npm install openai pip install openai agent.md

Also fits: Gemini API image generation (Nano Banana / Imagen), Stability AI Image API, Recraft API, FLUX API · all image generation apis

File storage and CDN

Cloudinary first pick AI-powered image and video management, transformation, and optimized delivery APIs.
Free: 25 monthly credits, 3 users, 1 account · paid from $99/mo · 1 credit = 1,000 transformations OR 1GB storage OR 1GB bandwidth · in 97 public agent repos
npm install cloudinary agent.md

Also fits: Azure Blob Storage, UploadThing, Backblaze B2 Cloud Storage, ImageKit · all file storage and media cdn

Model

Default: fast and cheapClaude Haiku 5.5 · $0.1 input / $0.5 output per 1M tokens · or GPT-6 Luna, MiMo V2.6 Flash
Harder questionsGemini 3.8 Flash · $0.75 input / $3.75 output per 1M tokens · or Kimi K2.7 Code, DeepSeek V4 Pro
Hardest workKimi K3 · $3 input / $15 output per 1M tokens · or Claude Opus 5.5, Claude Fable 5.1

The cheapest model of each price tier that can call tools, from model prices. Try the default first and move up only for the questions it gets wrong.

Or start from a ready platform

/bragAgent skill that creates a 20-second launch video with music, motion and share copy for the project in the current repository. It runs in Claude Code, Codex an…
Free tier
OpenMontageOpen-source system that turns an AI coding assistant into a video production studio: you describe the video in plain language and the agent researches, writes …
Free tier
Pixelle-VideoPixelle-Video generates a short video from a single topic: it writes the script, creates AI images or video clips, synthesizes narration, adds background music…
Free tier
WatchAgent skill and plugin that turns a video URL or local file into timestamped frames and a transcript so Claude Code, Codex and other Agent Skills hosts can ana…
Free tier

Libraries

RemotionMakes videos programmatically with React components, rendered to MP4 and other formats.
npm install remotion · custom license, read it · Gid Score 61
fluent-ffmpegNode.js wrapper providing fluent API for FFmpeg audio and video processing.
npm install fluent-ffmpeg · MIT · Gid Score 54
ffmpeg-staticPrebuilt ffmpeg binaries for macOS, Linux and Windows: convert and stream video and audio, e.g. pull the audio track out of a video.
npm install ffmpeg-static · GPL-3.0-or-later · Gid Score 49

Agent Skills

krillinai-subtitle krillinai/OpenCreatorUse when generating subtitles with KrillinAI CLI from a YouTube link, Bilibili/local video, or existing media, including platform caption download, Whisper fallback, tra…
npx skills add krillinai/OpenCreator --skill krillinai-subtitle
remotion-video-enhancer anbeime/skill影片与视频编辑及自媒体创作者在制作PPT或视频需要提升视觉表现力时，使用此技能可一键生成Remotion风格的高级转场与Framer Motion交互动画，自动规划动画序列，让内容呈现专业级动态效果。 has scripts
npx skills add anbeime/skill --skill remotion-video-enhancer
remotion google-labs-code/stitch-skillsGenerate walkthrough videos from Stitch projects using Remotion with smooth transitions, zooming, and text overlays has scripts
npx skills add google-labs-code/stitch-skills --skill remotion
ffmpeg-encoder-check-4855c0 HKUDS/OpenSpaceCheck available FFmpeg encoders before writing encoding scripts to avoid library version mismatches
npx skills add HKUDS/OpenSpace --skill ffmpeg-encoder-check-4855c0
cdf-event-video-generation NVIDIA/skillsRun the CDF Orchestration Event Video Generation DAG on Kubernetes or OSMO - image-to-video anomaly generation, auto-labeling, and anomaly dataset generation. Select for… has scripts
npx skills add NVIDIA/skills --skill cdf-event-video-generation
chengfeng-subtitle Agentchengfeng/chengfeng-videocut-skills给剪好的口播做字幕：直接用已有的逐词稿加账本算出剪后时间（不必导出、不必重新转录）、用词典和作者文稿改写听错的专名、按句子分屏、在 Studio 里逐屏复核。用户说做字幕、加字幕、改字幕、重新分屏、字幕不对时使用。不要用于删词剪辑、物理剪切、分镜动画或成片渲染。
npx skills add Agentchengfeng/chengfeng-videocut-skills --skill chengfeng-subtitle

Read a skill before you install it: skills can run scripts.

Coding agent to build it

OpenAI Codex Claude Code OpenCode Pi Compare coding agents

Also on AgentGid

Short-video pipeline kit Stock video Music libraries Sound effects Voiceover sources

Before you ship

  • Check each generator's terms for commercial use and for what you may publish.
  • Keep API keys on the server, never in the browser or app; set spending limits where the provider offers them.
  • Read each service's terms for your use: data retention, commercial use, rate limits.
  • Log model calls (traces) and test with your own real inputs before launch.

The brief

# Product recipe: Video from a prompt (AgentGid)

For short videos made from a text prompt: script, voiceover, music, footage or generated clips, rendered in code.

Parts were picked from AgentGid's catalog by rules: free tier, official MCP server, use in public projects built with AI agents, downloads, price. Prices are list prices from the official pages (see each card for the check date); confirm before you commit.

## What it costs
- Start: these first picks have no free tier listed: Runway API, Leonardo API.
- If you outgrow the free tiers, the lowest paid plans of the first picks are ElevenLabs Music API $6, Cloudinary $99 (together about $105/month); usage beyond a plan's credits is billed on top.
- Billed by usage (grows with traffic): Runway API, Deepgram.
- Model, default: fast and cheap: about $0.95 per 1,000 video scripts with Claude Haiku 5.5 (AgentGid estimate at ~2,000 input + 1,500 output tokens each).
- Model, harder questions: about $7.12 per 1,000 video scripts with Gemini 3.8 Flash (AgentGid estimate at ~2,000 input + 1,500 output tokens each).
- Prices of the picks below were checked on the official pages between 2026-10-09 and 2026-10-22.

## How it fits together
1. The model writes a script and a shot list from the prompt.
2. Generate the voiceover, music and images or clips with the APIs below.
3. Assemble and render in code (Remotion or ffmpeg) or with a rendering API, with captions.
4. Store the files and serve them from storage with a CDN.

## Video generation
- Runway API: no free tier listed · usage: $0.01 per credit; gen4.5 12 credits/sec, gen4_turbo 5 credits/sec · official MCP https://dev.runwayml.com/mcp · npm @runwayml/sdk · pip runwayml · card https://agentgid.com/apis/runway/agent.md
- Luma API (Ray / Uni): no free tier listed · usage: Ray3.2: $0.15 per 5s video (540p), $0.30 (720p), $1.20 (1080p) · official MCP · npm lumaai · pip lumaai · card https://agentgid.com/apis/luma/agent.md
- Shotstack: free: 10 free credits to start · paid from $39/mo · usage: Pay as you go: $10 for 50 minutes · npm shotstack-sdk · pip shotstack-sdk · card https://agentgid.com/apis/shotstack/agent.md
- Also fits: D-ID API, Veo (Gemini API), Genmo, Loom (https://agentgid.com/apis/video-generation/)

## Voiceover
- Deepgram: free: $200 credit, no credit card · usage: Nova-3 streaming $0.0048/min (promo; regular $0.0077); pre-recorded $0.0043/min; Flux $0.0065/min (promo); Aura-2 TTS $0.030 per 1k characters · official MCP · npm @deepgram/sdk · pip deepgram-sdk · card https://agentgid.com/apis/deepgram/agent.md
- Retell AI: free: $10 in free credits · usage: $0.07-$0.31/min for AI voice agents; $0.002+/msg for chat agents · official MCP @retell-ai/mcp-server · npm retell-sdk · pip retell-sdk · card https://agentgid.com/apis/retell-ai/agent.md
- Also fits: Cartesia, Vapi (voice agent API), Fish Audio API, ElevenLabs (https://agentgid.com/apis/voice/)

## Music and sound
- ElevenLabs Music API: free: Free plan: 3 music minutes/month · paid from $6/mo · usage: $0.15 per minute · official MCP https://api.elevenlabs.io/v1/mcp · npm @elevenlabs/elevenlabs-js · pip elevenlabs · card https://agentgid.com/apis/elevenlabs-music/agent.md
- ElevenLabs Sound Effects API: free: Free plan: 8 sound-effect generations/month · paid from $6/mo · usage: $0.12 per minute · official MCP https://api.elevenlabs.io/v1/mcp · npm @elevenlabs/elevenlabs-js · pip elevenlabs · card https://agentgid.com/apis/elevenlabs-sound-effects/agent.md
- Also fits: AIVA, Descript, Riffusion, Stable Audio API (https://agentgid.com/apis/audio-generation/)

## Images and thumbnails
- Leonardo API: no free tier listed · official MCP https://mcp.leonardo.ai/v1/mcp · npm @leonardo-ai/sdk · pip leonardo-ai-sdk · card https://agentgid.com/apis/leonardo/agent.md
- OpenAI Image API (GPT Image): no free tier listed · usage: gpt-image-2 1024x1024: $0.006 low / $0.053 medium / $0.211 high per image · npm openai · pip openai · card https://agentgid.com/apis/openai-gpt-image/agent.md
- Also fits: Gemini API image generation (Nano Banana / Imagen), Stability AI Image API, Recraft API, FLUX API (https://agentgid.com/apis/image-generation/)

## File storage and CDN
- Cloudinary: free: 25 monthly credits, 3 users, 1 account · paid from $99/mo · usage: 1 credit = 1,000 transformations OR 1GB storage OR 1GB bandwidth · npm cloudinary · card https://agentgid.com/apis/cloudinary/agent.md
- Also fits: Azure Blob Storage, UploadThing, Backblaze B2 Cloud Storage, ImageKit (https://agentgid.com/apis/storage/)

## Model (all of these can call tools; prices per 1M tokens)
- Default: fast and cheap: Claude Haiku 5.5 ($0.1 in / $0.5 out) · https://agentgid.com/models/claude-haiku-5-5/agent.md · or GPT-6 Luna, MiMo V2.6 Flash
- Harder questions: Gemini 3.8 Flash ($0.75 in / $3.75 out) · https://agentgid.com/models/gemini-3-8-flash/agent.md · or Kimi K2.7 Code, DeepSeek V4 Pro
- Hardest work: Kimi K3 ($3 in / $15 out) · https://agentgid.com/models/kimi-k3/agent.md · or Claude Opus 5.5, Claude Fable 5.1

## Or start from a ready platform
- /brag: free tier · https://agentgid.com/agents/brag/agent.md
- OpenMontage: free tier · https://agentgid.com/agents/openmontage/agent.md
- Pixelle-Video: free tier · https://agentgid.com/agents/pixelle-video/agent.md
- Watch: free tier · https://agentgid.com/agents/claude-video/agent.md

## Libraries
- `npm install remotion`: Remotion (custom license: read it) · https://agentgid.com/tools/remotion/agent.md
- `npm install fluent-ffmpeg`: fluent-ffmpeg (MIT) · https://agentgid.com/tools/fluent-ffmpeg/agent.md
- `npm install ffmpeg-static`: ffmpeg-static (GPL-3.0-or-later) · https://agentgid.com/tools/ffmpeg-static/agent.md

## Agent Skills (read a skill before you install it: skills can run scripts)
- `npx skills add krillinai/OpenCreator --skill krillinai-subtitle`
- `npx skills add anbeime/skill --skill remotion-video-enhancer`
- `npx skills add google-labs-code/stitch-skills --skill remotion`
- `npx skills add HKUDS/OpenSpace --skill ffmpeg-encoder-check-4855c0`
- `npx skills add NVIDIA/skills --skill cdf-event-video-generation`
- `npx skills add Agentchengfeng/chengfeng-videocut-skills --skill chengfeng-subtitle`

## Coding agent to build it
- OpenAI Codex: free tier, from $8/mo · https://agentgid.com/agents/openai-codex/agent.md
- Claude Code: from $20/mo · https://agentgid.com/agents/claude-code/agent.md
- OpenCode: free tier, from $10/mo · https://agentgid.com/agents/opencode/agent.md

## Also on AgentGid
- Short-video pipeline kit: https://agentgid.com/build/kits/short-video/
- Stock video: https://agentgid.com/assets/stock-video/
- Music libraries: https://agentgid.com/assets/music/
- Sound effects: https://agentgid.com/assets/sound-effects/
- Voiceover sources: https://agentgid.com/assets/voiceover/

## Before you ship
- Check each generator's terms for commercial use and for what you may publish.
- Keep API keys on the server, never in the client; set spending limits where the provider offers them.
- Read each service's terms for your use (data retention, commercial use, rate limits).
- Log model calls (traces) and test with your own real inputs before launch.

Recipe page: https://agentgid.com/build/recipes/prompt-to-video/ · all product recipes: https://agentgid.com/build/recipes/agent.md

Other recipes

AI assistant over your documents (RAG) Voice agent (phone or web) AI chatbot for a website or app AI support agent for your customers Web research and scraping agent Telegram bot with AI Data analyst agent Solana trading or alert bot Design recipes

Picked by rules from AgentGid's catalog, not paid placement. Prices are list prices from the official pages, checked between 2026-10-09 and 2026-10-22; check them before you commit.