OpenMontage/docs/PROVIDERS.md

OpenMontage Provider Guide

Everything you need to know about every provider in OpenMontage — setup instructions, pricing, free tiers, and what each unlocks.

---

Quick Start: What Should I Set Up?

Start free, add paid providers as you need them. Here's the recommended order:

Step	Cost	What to set up	What it unlocks
1	$0	Pexels + Pixabay	Stock photos and videos — enough to produce basic videos
2	$0	Google API key	TTS with 700+ voices (1M chars/month free) + $300 new account credit
3	$0	ElevenLabs	Premium TTS + music + SFX (10K chars/month free)
4	$0	Piper (local install)	Fully offline TTS — no API key, no cost, no network
5	~$0.03/image	fal.ai	FLUX images + Kling/Veo/MiniMax video + Recraft — one key unlocks 6 tools
6	~$0.04/image	OpenAI	DALL-E 3 images + OpenAI TTS
7	~$0.04/image	Google Imagen	Imagen 4 images (shares the Google API key)
8	$12/month	Runway	Gen-4 video — highest quality AI video
9	pay-as-you-go	HeyGen	Avatar videos, multi-model video gateway
10	pay-as-you-go	Suno	Full song generation with vocals and lyrics
11	$0 + GPU	Local video gen	WAN 2.1, Hunyuan, CogVideo, LTX — free, offline
12	$0 + GPU	Local Diffusion	Stable Diffusion images — free, offline

Environment Variable Summary

# .env — add your keys here

# FREE (no cost, ever)
PEXELS_API_KEY=              # Stock photos + videos
PIXABAY_API_KEY=             # Stock photos + videos

# GOOGLE (one key, two tools, generous free tier)
GOOGLE_API_KEY=              # Google TTS + Google Imagen

# VOICE + MUSIC
ELEVENLABS_API_KEY=          # TTS, music, sound effects (10K chars/month free)
OPENAI_API_KEY=              # OpenAI TTS + DALL-E 3 images

# MULTI-MODEL GATEWAY (one key, 6+ tools)
FAL_KEY=                     # FLUX, Recraft, Kling, Veo, MiniMax video

# VIDEO
HEYGEN_API_KEY=              # HeyGen avatar video gateway
RUNWAY_API_KEY=              # Runway Gen-4 video (direct)
SUNO_API_KEY=                # Suno music generation

# LOCAL (no keys needed — just GPU + install)
VIDEO_GEN_LOCAL_ENABLED=     # Set to "true" for local video gen
VIDEO_GEN_LOCAL_MODEL=       # wan2.1-1.3b, wan2.1-14b, hunyuan-1.5, ltx2-local, cogvideo-5b

---

Cloud Providers

fal.ai — Multi-Model Gateway

Best bang for buck. One API key unlocks 6 tools across image and video generation.

Tools unlocked: flux_image, recraft_image, kling_video, veo_video, minimax_video Env var: FAL_KEY

Setup

1. Go to fal.ai and click Sign up (GitHub or Google)
2. Navigate to fal.ai/dashboard/keys
3. Click Create Key, copy it
4. Add to .env: FAL_KEY=your-key-here

Pricing

No subscription — pure pay-as-you-go, no minimum spend.

Image generation:

Model	Price	Per $1
FLUX Pro v1.1	$0.05/image	20 images
FLUX Dev	$0.03/image	33 images
Recraft v3	~$0.04/image	25 images

Video generation:

Model	Price	Per $1
Kling 2.5 Turbo Pro	$0.07/sec	14 seconds
MiniMax	~$0.05/sec	20 seconds
Veo 3	$0.40/sec	2.5 seconds
WAN 2.5	$0.05/sec	20 seconds

Free tier: None — but $0 to start, you only pay for what you use.

---

ElevenLabs — Voice, Music, Sound Effects

Premium voice quality. Best TTS for narration-heavy videos. Also generates music and sound effects.

Tools unlocked: elevenlabs_tts, music_gen Env var: ELEVENLABS_API_KEY

Setup

1. Go to elevenlabs.io and click Sign up
2. Go to Profile (bottom-left) > API Keys, or visit elevenlabs.io/app/settings/api-keys
3. Click Create API Key, name it, copy it
4. Add to .env: ELEVENLABS_API_KEY=xi_your-key-here

Pricing

Plan	Price	Characters/month	Key features
Free	$0	10,000	3 custom voices, API access, attribution required
Starter	$5/mo	30,000	No attribution
Creator	$22/mo	100,000	Professional voice cloning
Pro	$99/mo	500,000	96kbps audio, usage analytics
Scale	$330/mo	2,000,000	Priority support

Free tier: 10,000 characters/month (roughly 2-3 minutes of narration). API access included. Music generation and sound effects also available on free tier with limited credits.

---

Google — TTS + Imagen (Shared Key)

One key, two tools. Google Cloud TTS has 700+ voices in 50+ languages — the strongest localization option. Imagen 4 generates high-quality images.

Tools unlocked: google_tts, google_imagen Env var: GOOGLE_API_KEY

Setup

1. Go to Google AI Studio and sign in
2. Navigate to aistudio.google.com/apikey
3. Click Create API Key, select a Google Cloud project
4. Copy the key
5. Add to .env: GOOGLE_API_KEY=AIza...

For TTS specifically, you also need to enable the Text-to-Speech API:

1. Visit console.cloud.google.com/apis/library/texttospeech.googleapis.com
2. Click Enable
3. Make sure your API key's restrictions allow the Text-to-Speech API

For Imagen, enable the Generative Language API:

1. Visit console.cloud.google.com/apis/library/generativelanguage.googleapis.com
2. Click Enable

Google TTS Pricing

Voice Type	Free tier	Paid (per 1M chars)	Notes
Standard	1M chars/month	$4.00	Basic quality, fast
WaveNet	1M chars/month	$16.00	Natural-sounding
Neural2	1M chars/month	$16.00	Best quality
Studio	—	$24.00	Professional studio voices
Chirp	—	$4.00	Conversational style

The free tiers apply independently — you get 1M Standard AND 1M WaveNet AND 1M Neural2 characters per month free. That's roughly 250+ minutes of narration per month at zero cost.

Google Imagen Pricing

Model	Price per image
Imagen 4 Fast	$0.02
Imagen 4 Standard	$0.04
Imagen 4 Ultra	$0.06

Free tier for Imagen: None. Paid tier only.

New account bonus: Google Cloud offers $300 in free credits for new accounts (90-day trial), applicable to both TTS and Imagen.

Google TTS Voice Types

Google TTS offers 700+ voices across 50+ languages. Voice names follow the pattern {language}-{type}-{letter}:

Type	Example	Quality	Cost
Standard	en-US-Standard-A	Good	Cheapest
WaveNet	en-US-WaveNet-D	Very good	Mid
Neural2	en-US-Neural2-D	Excellent	Mid
Studio	en-US-Studio-O	Professional	Highest
Journey	en-US-Journey-D	Conversational	Mid

Languages include: English (US, UK, AU, IN), Spanish, French, German, Italian, Portuguese, Japanese, Korean, Chinese (Mandarin, Cantonese), Arabic, Hindi, Russian, Dutch, Polish, Turkish, Vietnamese, Thai, Indonesian, and 30+ more.

---

OpenAI — TTS + Image Generation

Solid all-rounder. DALL-E 3 handles complex multi-element compositions well. TTS is fast and affordable.

Tools unlocked: openai_tts, openai_image Env var: OPENAI_API_KEY

Setup

1. Go to platform.openai.com/signup and create an account
2. Add a payment method at platform.openai.com/account/billing
3. Navigate to platform.openai.com/api-keys
4. Click Create new secret key, name it, copy it
5. Add to .env: OPENAI_API_KEY=sk-...

TTS Pricing

Model	Price per 1M characters
tts-1	$15.00
tts-1-hd	$30.00
gpt-4o-mini-tts	$12.00

Image Pricing

Model	Size	Quality	Price per image
DALL-E 3	1024x1024	standard	$0.040
DALL-E 3	1024x1024	hd	$0.080
DALL-E 3	1024x1792	standard	$0.080
DALL-E 3	1024x1792	hd	$0.120

Free tier: None. Requires prepaid billing. Previously offered $5 in free credits for new accounts (discontinued for most signups).

---

Runway — Gen-4 Video

Highest-rated AI video quality. #1 on Elo rankings. Professional-grade video generation.

Tools unlocked: runway_video Env var: RUNWAY_API_KEY

Setup

1. Go to app.runwayml.com/signup and create an account
2. Subscribe to a paid plan (Standard or above — API requires subscription)
3. Go to Settings > API Keys at app.runwayml.com/settings/api-keys
4. Click Create API Key, copy it
5. Add to .env: RUNWAY_API_KEY=key_...

Pricing

Plan	Price	Credits/month	Video capacity
Free	$0	125 one-time	~5 seconds Gen-4
Standard	$12/mo	625	~25 seconds Gen-4
Pro	$28/mo	2,250	~90 seconds Gen-4
Unlimited	$76/mo	Unlimited (Explore Mode)	Unlimited Gen-4 Turbo

API pricing (approximate):

Model	Price per second
Gen-4 Turbo	~$0.05
Gen-4	~$0.10
Gen-4.5	~$0.25

Free tier: 125 one-time credits (no monthly renewal). Enough for about 5 seconds of Gen-4 video. API access requires a paid subscription.

---

HeyGen — Avatar Video Gateway

Multi-model video gateway. Access VEO, Sora, Runway, Kling, and Seedance through a single API.

Tools unlocked: heygen_video Env var: HEYGEN_API_KEY

Setup

1. Go to app.heygen.com/register and create an account
2. Navigate to the API section in settings
3. Generate your API key
4. Add API balance (prepaid, separate from web plan credits)
5. Add to .env: HEYGEN_API_KEY=your-key-here

Pricing

Service	Price
Avatar video (Engine III)	$0.017/sec
Avatar video (Engine IV)	$0.10/sec
Prompt to Video	$0.033/sec
Video Translation (Speed)	$0.05/sec
Video Translation (Precision)	$0.10/sec

Web plans:

Plan	Price	Notes
Free	$0	1 credit (demo)
Creator	$24/mo	Limited credits
Business	$72/mo	API access, more credits

Free tier: 1 credit on web platform. API is pay-as-you-go with prepaid balance.

---

Suno — AI Music Generation

Full songs with vocals and lyrics. Any genre, up to 8 minutes. Instrumentals or vocal tracks.

Tools unlocked: suno_music Env var: SUNO_API_KEY

Setup

1. Go to suno.com and create a Suno account
2. For API access, go to sunoapi.org and create an account
3. Navigate to the dashboard and copy your API key
4. Add credits (1 credit = $0.005 USD)
5. Add to .env: SUNO_API_KEY=your-key-here

Pricing

Suno platform:

Plan	Price	Credits	Notes
Free	$0	50/day	~10 songs/day, non-commercial only
Pro	$10/mo	2,500/mo	Commercial license
Premier	$30/mo	10,000/mo	Commercial license

API (via sunoapi.org): Pay-as-you-go, 1 credit = $0.005. Each generation produces 2 tracks.

---

Pexels — Free Stock Media

Completely free. No cost, no attribution required, commercial use allowed.

Tools unlocked: pexels_image, pexels_video Env var: PEXELS_API_KEY

Setup

1. Go to pexels.com/join and create a free account
2. Navigate to pexels.com/api
3. Click Your API Key or request API access
4. Copy your key from the dashboard
5. Add to .env: PEXELS_API_KEY=your-key-here

Pricing

Completely free. No paid tiers. No attribution required. Commercial use allowed.

• 200 requests/hour
• 20,000 requests/month
• Photo and video search + download

---

Pixabay — Free Stock Media

Completely free. 5M+ royalty-free images and videos.

Tools unlocked: pixabay_image, pixabay_video Env var: PIXABAY_API_KEY

Setup

1. Go to pixabay.com/accounts/register and create a free account
2. Navigate to pixabay.com/api/docs
3. Your API key is displayed at the top of the docs page (after login)
4. Copy the key
5. Add to .env: PIXABAY_API_KEY=your-key-here

Pricing

Completely free. No paid tiers. No attribution required. Commercial use allowed.

• ~100 requests/minute
• 5,000 requests/hour
• Photo and video search + download
• Standard API limited to 1280px images (full resolution requires editorial API)

---

Local Providers (Free, No API Key)

These providers run entirely on your machine. No network, no API key, no cost. Some require a GPU.

Remotion — Programmatic Video Composition

React-based video rendering. Turns still images into animated video with spring physics, animated text cards, stat cards, charts, and transitions. This is the key fallback when no video generation providers are configured — the agent generates images and Remotion animates them into professional-looking video.

Tool: video_compose (with operation="render" — auto-routes to Remotion when needed) Runtime: CPU (Node.js required) Env var: None

Setup

# Included in make setup, or install manually:
cd remotion-composer && npm install && cd ..

Requires Node.js 18+ and npx. The remotion-composer/ project is included in the repo.

What Remotion Renders

Component	What it produces
TextCard	Animated title/body text with spring physics entrance
StatCard	Animated statistics with count-up animations
ProgressBar	Animated progress indicators
CalloutBox	Highlighted callout panels with icon animations
ComparisonCard	Side-by-side comparison layouts
BarChart / LineChart / PieChart	Animated data visualizations
KPIGrid	Multi-metric dashboard cards
Image scenes	Still images with spring-animated motion (replaces Ken Burns)

When Does Remotion Activate?

The video_compose tool's render operation auto-detects when Remotion is needed:

• Cuts contain still images (.png, .jpg, etc.)
• Cuts have type set to text_card, stat_card, chart, etc.
• Cuts specify animation or transition_in/transition_out

If Remotion is not installed, compositions fall back to FFmpeg Ken Burns pan-and-zoom — functional but less engaging.

Cost: Free. Always local.

---

Piper TTS — Offline Text-to-Speech

Completely free, fully offline TTS. No network required. Good quality for drafts and budget-constrained projects.

Tool: piper_tts Runtime: CPU (no GPU needed) Env var: None

Setup

# Install via pip
pip install piper-tts

# Or download the binary from GitHub
# https://github.com/rhasspy/piper/releases

# Download a voice model (first run downloads automatically)
piper --download-dir ~/.piper/models --model en_US-lessac-medium

Available voices: ~30 English voices plus voices for German, French, Spanish, Italian, and other languages. Lower variety than cloud providers but completely free and offline.

Quality: Good for drafts, internal videos, and budget projects. For client-facing narration, use ElevenLabs or Google TTS.

---

Local Video Generation (GPU Required)

Free AI video generation. Requires an NVIDIA GPU with sufficient VRAM.

Tools: wan_video, hunyuan_video, cogvideo_video, ltx_video_local Runtime: Local GPU (CUDA required) Env vars: VIDEO_GEN_LOCAL_ENABLED=true, VIDEO_GEN_LOCAL_MODEL=<model>

Setup

# 1. Install the GPU stack
make install-gpu
# Or manually:
pip install diffusers transformers accelerate torch pillow requests

# 2. Enable local generation in .env
VIDEO_GEN_LOCAL_ENABLED=true

# 3. Choose a model based on your GPU VRAM
VIDEO_GEN_LOCAL_MODEL=wan2.1-1.3b      # 6GB+ VRAM (entry-level)
VIDEO_GEN_LOCAL_MODEL=wan2.1-14b       # 24GB+ VRAM (best local quality)
VIDEO_GEN_LOCAL_MODEL=hunyuan-1.5      # 12GB+ VRAM
VIDEO_GEN_LOCAL_MODEL=ltx2-local       # 8GB+ VRAM (fastest)
VIDEO_GEN_LOCAL_MODEL=cogvideo-5b      # 10GB+ VRAM
VIDEO_GEN_LOCAL_MODEL=cogvideo-2b      # 6GB+ VRAM (lightest)

Model Comparison

Model	VRAM	Quality	Speed	Best for
WAN 2.1 (1.3B)	6GB	Good	Fast	Entry-level GPU, quick iteration
WAN 2.1 (14B)	24GB	Excellent	Slow	Best quality-to-VRAM ratio
Hunyuan 1.5	12GB	Very good	Medium	Mid-range GPUs
LTX-2	8GB	Good	Fastest	Quick drafts, lowest latency
CogVideo (5B)	10GB	Good	Medium	Balanced option
CogVideo (2B)	6GB	Fair	Fast	Low-VRAM experimentation

All local models support: Image-to-video, text-to-video, offline generation, seeded reproducibility.

---

Local Diffusion — Offline Image Generation (GPU Required)

Free Stable Diffusion image generation. No API cost, fully offline.

Tool: local_diffusion Runtime: Local GPU (CUDA required) Env var: None (enable by installing dependencies)

Setup

pip install diffusers transformers accelerate torch

First run downloads the model (~4GB). Subsequent runs use the cached model.

VRAM requirement: 4GB+ (8GB recommended for 1024x1024 images)

Supports: Negative prompts, seeds, custom sizes. Quality is lower than FLUX or DALL-E 3 but completely free and offline.

---

LTX-2 on Modal — Self-Hosted Cloud GPU

Run LTX-2 on Modal's cloud GPUs. Your own endpoint, your own scale. More consistent than local GPU, cheaper than commercial APIs.

Tool: ltx_video_modal Runtime: Cloud (self-hosted) Env var: MODAL_LTX2_ENDPOINT_URL

Setup

1. Create a Modal account
2. Deploy the LTX-2 endpoint (see Modal docs)
3. Set the endpoint URL in .env: MODAL_LTX2_ENDPOINT_URL=https://your-modal-endpoint

Modal pricing: ~$0.99/hour for A100 GPU time. Cost per video depends on generation time.

---

Other Local Tools (Always Available)

These tools require only FFmpeg or Python packages — no GPU, no API key.

Tool	Install	What it does
FFmpeg tools (video_compose, video_stitch, video_trimmer, audio_mixer, audio_enhance, color_grade, face_enhance, frame_sampler, scene_detect)	brew install ffmpeg / sudo apt install ffmpeg / winget install FFmpeg	Video editing, audio processing, color grading, analysis
Transcriber	pip install faster-whisper	Speech-to-text with word-level timestamps
Background Remove	pip install rembg (CPU) or pip install rembg[gpu]	Remove image/video backgrounds
Upscale	pip install realesrgan (requires PyTorch + CUDA)	Real-ESRGAN image/video upscaling
Face Restore	pip install gfpgan (requires PyTorch)	CodeFormer/GFPGAN face restoration
Code Snippet	pip install Pygments Pillow	Syntax-highlighted code images
Diagram Gen	npm install -g @mermaid-js/mermaid-cli	Mermaid diagram rendering
Math Animate	pip install manim	ManimCE mathematical animations
Subtitle Gen	No install needed	SRT/VTT subtitle file generation
Video Understand	pip install transformers torch	CLIP/BLIP-2 visual analysis
Talking Head	Clone SadTalker	Avatar animation from photo + audio
Lip Sync	Clone Wav2Lip	Audio-driven lip synchronization

---

Provider-to-Tool Mapping

Provider	Env Var	Tools Unlocked	Cost
Pexels	PEXELS_API_KEY	pexels_image, pexels_video	Free
Pixabay	PIXABAY_API_KEY	pixabay_image, pixabay_video	Free
Piper	— (install only)	piper_tts	Free
Google	GOOGLE_API_KEY	google_tts, google_imagen	Free tier + paid
ElevenLabs	ELEVENLABS_API_KEY	elevenlabs_tts, music_gen	Free tier + paid
fal.ai	FAL_KEY	flux_image, recraft_image, kling_video, veo_video, minimax_video	Pay-as-you-go
OpenAI	OPENAI_API_KEY	openai_tts, openai_image	Paid only
Runway	RUNWAY_API_KEY	runway_video	Free trial + paid
HeyGen	HEYGEN_API_KEY	heygen_video	Pay-as-you-go
Suno	SUNO_API_KEY	suno_music	Pay-as-you-go
Local GPU	VIDEO_GEN_LOCAL_ENABLED	wan_video, hunyuan_video, cogvideo_video, ltx_video_local	Free (GPU required)
Local Diffusion	— (install only)	local_diffusion	Free (GPU required)
Modal	MODAL_LTX2_ENDPOINT_URL	ltx_video_modal	Self-hosted cloud

---

Capability Coverage

How many providers cover each capability:

Capability	Cloud Providers	Local Providers	Free Options
Image Generation	FLUX, Google Imagen, DALL-E 3, Recraft	Local Diffusion	Pexels, Pixabay (stock)
Video Generation	Kling, Runway, Veo, MiniMax, HeyGen	WAN, Hunyuan, CogVideo, LTX	Pexels, Pixabay (stock)
Text-to-Speech	ElevenLabs, Google TTS, OpenAI	Piper	Piper, Google free tier, ElevenLabs free tier
Music Generation	ElevenLabs, Suno	—	ElevenLabs free tier
Post-Production	—	FFmpeg (compose, stitch, trim, mix, enhance, grade)	All free
Analysis	—	WhisperX, Scene Detect, Frame Sampler, CLIP/BLIP-2	All free
Enhancement	—	Upscale, BG Remove, Face Enhance, Face Restore	All free
Avatar	—	SadTalker, Wav2Lip	All free

---

FAQ

Q: What's the absolute minimum I need to produce a video? A: FFmpeg + Node.js (both free, local). FFmpeg handles video assembly, audio mixing, and subtitles. With Node.js, Remotion renders still images into animated video — so even without any video generation API, the agent generates images and Remotion turns them into professional-looking video with spring animations, text cards, and transitions. Add Piper TTS for free narration and Pexels/Pixabay for free stock footage.

Q: I don't have any video generation providers. Can I still make videos? A: Yes. The agent generates still images (via any image provider — even free stock from Pexels/Pixabay) and Remotion composes them into animated video with spring physics transitions, text cards, stat cards, and charts. This is the default path for explainer and animation pipelines when no video gen is configured.

Q: What's the cheapest way to get AI-generated images and video? A: fal.ai (FAL_KEY). One key unlocks FLUX images at ~$0.03/image and multiple video providers. No subscription — pay only for what you generate.

Q: I have a GPU. What can I run locally for free? A: Set VIDEO_GEN_LOCAL_ENABLED=true and install diffusers. You get WAN 2.1, Hunyuan, CogVideo, and LTX video generation plus Stable Diffusion image generation — all free, all offline.

Q: Which TTS provider should I use? A: For quality → ElevenLabs. For localization (50+ languages) → Google TTS. For budget → Google free tier (1M chars/month). For offline → Piper.

Q: Do I need all these providers? A: No. Start with what you have. The selector pattern auto-routes to whatever's available. Missing a provider? The system falls through to the next one automatically.