STACKFOR
StackFor AI NPCs and dialogue
Provisional seed stack, low confidence, not hands-on tested. Affiliate status was not an input.
Characters who can talk without you writing every line, and a way to keep them in bounds.
STACK SCORE
84
Mean of the role winners, compatibility +3. Separate from each tool score.
Provisional seed scores. Method seed-v0-provisional, confidence low, not hands-on tested. The band around a number is a ±8 display label, not a measured interval. Ordering uses the point estimate.
We may earn a commission if a tracking link is connected and you buy through it. It never changes ranks. In this v1 seed, tracking URLs are empty, so “Open site” goes to the vendor. Sponsorship rules.
Recommended stack
Characters that talk, remember, and stay in the game's lore, with voices.
Example compatibility note, not a measured integration test. Inworld and Convai ship Unity and Unreal plugins.
ROLE
LLM API
The model call inside the product.
82
74–90 · low confidence
Low-latency flash models.
Realtime API for voice.
ROLE
TTS / voice
The speaking voice.
86
78–94 · low confidence
- Cartesia79
Very low latency.
ROLE
Engine
The game you might ship.
79
71–87 · low confidence
- Unity76
Most NPC plugins target Unity.
MetaHuman-grade characters.
Ranked tools
Sorted by StackFor Score only. A tool can appear twice when it fills two roles. Affiliate programs are not on this list.
- #1
86
78–94 · low confidence
Expressive voices and streaming.
Goal fit25%90Output quality20%94Ease for vibe coders15%86Pricing and free tier15%62Integrations and API10%88Momentum10%90Community sentiment5%84No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open ElevenLabs - #2
82
74–90 · low confidence
Consistent character writing.
Goal fit25%84Output quality20%90Ease for vibe coders15%74Pricing and free tier15%66Integrations and API10%86Momentum10%88Community sentiment5%82No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Anthropic API - #3
82
74–90 · low confidence
Low-latency flash models.
Goal fit25%86Output quality20%84Ease for vibe coders15%76Pricing and free tier15%78Integrations and API10%84Momentum10%82Community sentiment5%72No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Gemini API - #4
82
74–90 · low confidence
Realtime API for voice.
Goal fit25%86Output quality20%88Ease for vibe coders15%76Pricing and free tier15%64Integrations and API10%94Momentum10%86Community sentiment5%74No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open OpenAI API - #5
79
71–87 · low confidence
Very low latency.
Goal fit25%84Output quality20%86Ease for vibe coders15%74Pricing and free tier15%70Integrations and API10%76Momentum10%82Community sentiment5%70No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Cartesia - #6
79
71–87 · low confidence
Community plugins.
Goal fit25%76Output quality20%84Ease for vibe coders15%62Pricing and free tier15%100Integrations and API10%70Momentum10%78Community sentiment5%86No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Godot - #7
76
68–84 · low confidence
Character engine and real-time TTS.
Goal fit25%86Output quality20%80Ease for vibe coders15%72Pricing and free tier15%64Integrations and API10%74Momentum10%70Community sentiment5%68No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Inworld - #8
76
68–84 · low confidence
Most NPC plugins target Unity.
Goal fit25%86Output quality20%88Ease for vibe coders15%58Pricing and free tier15%68Integrations and API10%84Momentum10%60Community sentiment5%68No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Unity - #9
75
67–83 · low confidence
MetaHuman-grade characters.
Goal fit25%84Output quality20%92Ease for vibe coders15%48Pricing and free tier15%70Integrations and API10%80Momentum10%64Community sentiment5%74No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Unreal Engine - #10Convai
NPC platform · role rank 2
74
66–82 · low confidence
NPC actions and plugins.
Goal fit25%80Output quality20%78Ease for vibe coders15%78Pricing and free tier15%64Integrations and API10%76Momentum10%66Community sentiment5%66No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Convai
Draft feature checklist
Goal fit is scored against these must-haves. The list is a draft rubric, not a test log.
NPC platform
- Engine plugins
- Memory and goals
- Safety controls
LLM API
- Fast, cheap dialogue
TTS / voice
- Low-latency voices
Engine
- Runtime
Questions
Are these scores from hands-on tests?
No. Every score on this page is a provisional seed estimate with low confidence. The band around the number is a display convention, not a measured interval.
Can a paid listing change who is recommended?
No. Affiliate programs and sponsored cards are not inputs. A sponsored card, when one exists, is labeled and sits outside the ranking.
NEWSLETTER
The weekly AI stack drop
New tools worth your time, by use case. One email a week. A sponsor, when there is one, is labeled.