Category Rankings
Reviewed by Spicy · Tested · Updated
An AI Dungeon alternative should solve a specific campaign problem: character setup, scene control or continuity. Meridian Realms AI remains my world-building pick, but its October 6 adventure run still showed coin-state and persona mistakes. I also ran AI Dungeon’s free Dynamic Small as the reference, so the comparison includes what the original actually does.
🌶️ Our #1 pick: Meridian Realms AI 4.5/5
Visit Meridian Realms AICompare adventure continuity and authoring controls, with the original included as a reference.
I may earn a commission through Visit links, at no extra cost to you. Rankings follow my review criteria. Affiliate disclosure.
The short version, before we get into the spicy details.
Meridian Realms AI: My world-building pick completed 20 turns on Orion, with useful regeneration controls and some inventory drift.
Soulkyn: A male companion with visible context controls; the trial ended after eight script replies, before either recall checkpoint.
AI Peeps: The free account completed 20 turns and recalled the inventory, but moved toward boarding before accepting a correction.
Scores and pricing are recorded in our platform reviews. Prices and allowances can change; check the dated evidence below. Click a column to sort.
| 1.Meridian Realms AI | 4.8/5 | 4.8/5 | 4.6/5 | 4.3/5 | $7.99/mo | 10 msgs · 5 imgs |
| 2.Soulkyn | 4/5 | 3.8/5 | 4.5/5 | 4/5 | €24.99/mo Premium (checked October 9); 300 voice messages | Existing trial expired October 6; check account eligibility |
| 3.AI Peeps | 4.2/5 | 4.1/5 | 4.3/5 | 4.5/5 | $7.99/mo recorded in April review; current price unverified | 10 daily text messages shown October 9; free voice unverified |
| 4.Replika | 2.9/5 | 4/5 | 3.5/5 | 4/5 | $19.99/mo | 100 msgs |
What each ranking is based on, including the gaps. A blank metric means it was not recorded, not that the result was zero.
Completed the 20-turn adventure script. At turn 10 recalled the planted facts and one remaining coin, but misattributed the tower promise. At turn 20 retained Mira, mint dislike, dawn, key and ledger; the remaining coin became uncertain despite no later transaction. Regenerate retained the original and replacement as separate slides.
A male character accepted the adventure setup, but only eight script replies completed. The on-screen notice said the trial had ended and ongoing freemium beyond the starter trial was disabled. Neither the turn-10 nor turn-20 recall check was reached.
Completed the same 20-turn script using the existing free account. Both checkpoints recalled the planted facts and inventory. The account allowance decreased from 30 to 10 remaining messages.
The full review records native mobile apps, a 3D-style character, memory notes and a scenario builder; chat score 2.9.
| Platform | Evidence level | Date | Model | Attempts | Usable | Est. cost | Main finding or limitation |
|---|---|---|---|---|---|---|---|
| Meridian Realms AI | Fresh niche test | Oct 6, 2026 | Orion | — | — | — | Completed the 20-turn adventure script. At turn 10 recalled the planted facts and one remaining coin, but misattributed the tower promise. At turn 20 retained Mira, mint dislike, dawn, key and ledger; the remaining coin became uncertain despite no later transaction. Regenerate retained the original and replacement as separate slides. |
| Soulkyn | Fresh niche test | Oct 6, 2026 | v4 shown in chat | — | — | — | A male character accepted the adventure setup, but only eight script replies completed. The on-screen notice said the trial had ended and ongoing freemium beyond the starter trial was disabled. Neither the turn-10 nor turn-20 recall check was reached. |
| AI Peeps | Fresh niche test | Oct 6, 2026 | — | — | — | — | Completed the same 20-turn script using the existing free account. Both checkpoints recalled the planted facts and inventory. The account allowance decreased from 30 to 10 remaining messages. |
| Replika | Full-review evidence | — | — | — | — | — | The full review records native mobile apps, a 3D-style character, memory notes and a scenario builder; chat score 2.9. |
#14.5/5Best for a persistent world and detailed character setup, Meridian offers unlimited worlds and characters on the recorded $7.99 Starter plan. Orion completed the 20-turn adventure script and retained most planted facts, but confused the assigned player name with the account persona and became uncertain about the remaining coin. Regenerate keeps alternate replies instead of discarding the original. AI Dungeon already exposes Story Cards and Plot Components, so switch for Meridian’s world-and-character workflow rather than assuming the original lacks authoring controls.
Completed the 20-turn adventure script. At turn 10 recalled the planted facts and one remaining coin, but misattributed the tower promise. At turn 20 retained Mira, mint dislike, dawn, key and ledger; the remaining coin became uncertain despite no later transaction. Regenerate retained the original and replacement as separate slides.
What worked
What missed
Limit: Existing account persona and narrator influence the setup. This single adventure test does not establish romantic performance, voice support or superiority over every model.
Recorded pricing: $7.99/mo · Free access: 10 msgs · 5 imgs
#24.2/5Best for a companion-led adventure with visible settings, Soulkyn combines a scenario builder and memory notes with S-to-X content ratings. The male-character test completed only eight script replies before the account’s trial ended, and it described two coins after one had been exchanged. Those settings make it a workflow alternative to AI Dungeon, but the incomplete run cannot establish better long-session memory.
A male character accepted the adventure setup, but only eight script replies completed. The on-screen notice said the trial had ended and ongoing freemium beyond the starter trial was disabled. Neither the turn-10 nor turn-20 recall check was reached.
What worked
What missed
Limit: A preflight preceded the script in the same chat, and the trial gate prevented completion. Fresh voice/image results are unverified; older free allowances are not ongoing free access.
Recorded pricing: €24.99/mo Premium (checked October 9); 300 voice messages · Free access: Existing trial expired October 6; check account eligibility
#34.2/5Best for a free companion-style adventure test, AI Peeps completed all 20 turns and recalled the key, remaining coin and ledger at both checks. It also started moving the character onto the boat before accepting a correction, so good fact recall did not guarantee perfect scene control. Its recorded $7.99 Peep Pal plan and scenario tools give you a simpler companion workflow; AI Dungeon’s native Story actions and authoring components suit more direct adventure editing.
Completed the same 20-turn script using the existing free account. Both checkpoints recalled the planted facts and inventory. The account allowance decreased from 30 to 10 remaining messages.
What worked
What missed
Limit: The default character was Lola; the prompt assigned Elias. This verifies prompted adventure roleplay, not native male-character availability. Model name was not displayed.
Recorded pricing: $7.99/mo recorded in April review; current price unverified · Free access: 10 daily text messages shown October 9; free voice unverified
#43.3/5Best for mobile users who want a 3D companion inside their story, Replika brings native apps and a character style that feels more animated than the usual stack of generated pictures. Memory notes and a scenario builder address some of the control AI Dungeon switchers are missing, but the comparison gets ugly once the chat score appears: Replika manages just 2.9, and filters clamp down when conversations move beyond PG-13. The free tier includes 100 messages and character creation, while Pro costs $19.99 a month. That makes Replika the visual wildcard here, not my first choice for a sprawling uncensored campaign.
The full review records native mobile apps, a 3D-style character, memory notes and a scenario builder; chat score 2.9.
Limit: No fresh 20-turn adventure test; this is a companion comparison, not proof of a dedicated inventory or campaign engine.
Recorded pricing: $19.99/mo · Free access: 100 msgs
I used a new Quick Play adventure with Dynamic Small and no active Plot Components or Story Cards. It completed 20 Story actions, keeping Mira, dawn, the key, ledger and dock, but invented a strong-drink preference and omitted the remaining coin. The original north-tower promise was absent from the last recall. That is one free-model result, not a verdict on every AI Dungeon model. Settings expose Story Cards, AI Instructions, Story Summary, Plot Essentials and Author’s Note, and Retry with changes accepts a correction.
A bot can remember a sister’s name while losing a coin. The script moved from library to market to dock, exchanged one of two coins, and kept a key and ledger in different places. Secret Desires and AI Peeps retained the tracked inventory at both checkpoints. Meridian became uncertain about the remaining coin; Dynamic Small omitted it. These are prose continuity observations, not proof of an authoritative inventory system. Keep a short campaign ledger when a mistake would derail play.
Choose Meridian when detailed worlds, character definitions and alternate reply steering matter most. Choose AI Peeps for a companion-style scenario you can sample on the existing free allowance. Soulkyn gives you visible context and tone controls, but this account needs paid access to complete the test. Stay with AI Dungeon when native Story actions, Story Cards and Plot Components fit your campaign. Compare the model and monthly allowance you would actually use before paying for a different interface.
October 6 pricing follow-up: the signed-in Monthly tab lists Premium €24.99/month, Deluxe €49.99/month and Deluxe Plus €99.99/month, billed in EUR. Premium advertises unlimited messages, 300 image quota and 300 voice messages; the page explains one quota allows six tool images or one in-chat image. The older Just Chatting / $13.91 figures are historical. No checkout or purchase was completed. Current new-user free eligibility and actual model availability after payment remain unverified.
Meridian Realms AI is my world-building pick, with detailed worlds and character tools. Its 20-turn Orion run still showed inventory and persona drift, so I would not promise flawless campaign memory.
Soulkyn offers the clearest content controls here, with ratings from S to X and an intensity slider from 0 to 10. Its scenario builder, memory notes, and group chats give those settings somewhere more interesting to play than a basic one-on-one chat.
The October 6 run did not establish one universal winner. AI Peeps retained the planted inventory at both checks; Meridian became uncertain about a coin, and AI Dungeon’s free Dynamic Small omitted it. Different models and setups limit the comparison.
AI Peeps completed this 20-turn run on the existing free allowance. Meridian has a shorter recorded starter trial. Soulkyn’s tested account hit its trial gate after eight script replies, so ongoing free access should not be assumed.
Meridian Realms AI is the best fit for DnD-style roleplay because its world and character creation process is built around unusually deep detail. It also includes a scenario builder, memory notes, and group chats on the Premium plan.
They are companion platforms first, but both support scenario creation and character customization for fantasy or adventure roleplay. Soulkyn adds memory notes and group chats, while AI Peeps offers 50 free messages that renew weekly.
On October 6 I used one 20-turn adventure script with recall checks at turns 10 and 20 after scene changes. Meridian, Secret Desires, AI Peeps and the AI Dungeon reference completed it; Soulkyn stopped after eight script replies when the trial ended. Different models and starting personas limit direct comparisons. Older valid findings are retained separately; this is not a romantic, explicit-image or unlimited-memory benchmark.
The evidence labels show exactly how much category-specific support I had for each pick. The platform scores still come from the same ten equally weighted categories used across full Spicy Ranks reviews.
Download the October 6 cost and access observations (JSON). The data includes credit units, test settings, observation dates and unknowns. Account trials and credit charges can change; credits are not a dollar price.
Character AI alternative comparison: 7 adult roleplay tools, character controls, memory limits and dated pricing.
Find an AI Sissy Trainer That Remembers Your ProgressAI sissy trainer apps ranked for progression, memory, boundaries, voice, task variety, and control. I compare 5 options starting at $7.99.
Find the Best NSFW AI Chat App for Your Favorite FantasyCompare the best NSFW AI chat apps for memory, uncensored roleplay, privacy, media, free tiers, and real pricing. Nine options ranked.
Our #1 Pick
Compare Meridian Realms AI when detailed worlds and reply steering are your main reasons to switch.
