Test log
Lovora test data
Raw results for the Lovora review. The verdict is in the review.
- Tested
- 14 October 2026
- Tester
- Miles Foster
- Account
- Bought for this review at the public price
- Tests
- 10
- Screenshots
- 27
- Method
- Published methodology
- Environment
- Google Chrome, signed-in profile, 1400x883 viewport for the chats, generators, creator and pricing
Results
| ID | Test | Key measurement | Score |
|---|---|---|---|
| T01 | Pricing, Value & Payment Methods | Cheapest monthly rate: $4.49 (yearly plan) | 4/5 |
| T02 | AI Girlfriend Creation & Customization | – | 4/5 |
| T03 | Chat Response Speed | Median to first text: 1.03 s | 4/5 |
| T04 | Chat Memory | – | 4/5 |
| T05 | Character Consistency & Roleplay | – | 4/5 |
| T06 | Image Generation (SFW & NSFW) | Delivered: 13 of 15 requests (2 transient failures, retried successfully; 1 anime prompt silently absent) | 5/5 |
| T07 | Video Generation (SFW & NSFW) | Success rate: 1 / 1 | 4/5 |
| T08 | Voice Call Latency | Pooled median: 7.27 s (40 questions) | 1/5 |
| T09 | Voice Realism | Answers analysed: 44 (Ivy 16, Diana 16, Rin 12) | 4/5 |
| T10 | Character Variety & Selection | Catalogue characters: 131 (full count) | 2/5 |
| Overall (in the review) | 4/5 | ||
Pricing, Value & Payment Methods
4/5Tested- Method
- Plans and packs from the pricing page, the credit cost of each action from the pricing page and the docs, actual charges from the balance before and after every photo, video, call, voice note and creation, and payment methods from the checkout dialog opened on a credit pack.
- Cheapest monthly rate
- $4.49 (yearly plan)
- Day pass
- $3.99 with 150 credits
- Photo
- $0.10 to $0.24
- Video, 5 s
- $1.25 to $3.00 (video cost score 2/5)
- Voice call
- $0.21 to $0.50 a minute
- Payment methods
- card, Apple Pay, Google Pay, Telegram Stars, crypto (5/5)
- Remark
- Unlimited chat at $4.49 to $8.99 a month with a $3.99 day pass and nothing renewing is cheap for the category, and the photos are good value. Calls and videos drain the 500 credits quickly: the whole allowance covers about twenty minutes of calls, or three videos, or 41 photos. Good value with minor limitations: 4/5.
Credit charges observed on the account.
| Action | Balance before | Balance after | Charged |
|---|---|---|---|
| Daily gift claimed | 500 | 502 | +2 |
| 2 chat photos delivered (2 failed requests free) | 502 | 490 | 12 |
| 8 studio prompts, 7 delivered | 490 | 406 | 84 |
| 2 chat photos (retries) | 406 | 382 | 24 |
| 1 video | 382 | 232 | 150 |
| 3 voice calls, 15 questions each | 232 | 1 | 231 |
| 1 voice note | 1 | 0 | 1 |
Daily gift claimed
- Balance before
- 500
- Balance after
- 502
- Charged
- +2
2 chat photos delivered (2 failed requests free)
- Balance before
- 502
- Balance after
- 490
- Charged
- 12
8 studio prompts, 7 delivered
- Balance before
- 490
- Balance after
- 406
- Charged
- 84
2 chat photos (retries)
- Balance before
- 406
- Balance after
- 382
- Charged
- 24
1 video
- Balance before
- 382
- Balance after
- 232
- Charged
- 150
3 voice calls, 15 questions each
- Balance before
- 232
- Balance after
- 1
- Charged
- 231
1 voice note
- Balance before
- 1
- Balance after
- 0
- Charged
- 1
Raw notes
Plans and packs from the pricing page, the credit cost of each action from the pricing page and the docs, actual charges from the balance before and after every photo, video, call, voice note and creation, and payment methods from the checkout dialog opened on a credit pack. Nothing was bought.
Plans (launch offer): 24 hours $3.99 with 150 credits; 1 month $8.99 (list $18.99); 3 months $22.99; 12 months $53.88 ($4.49 a month). Every plan is a one-time payment that never renews, with unlimited messages, 500 credits a month and three custom companions a month. Free: 25 messages, 2 voice notes, blurred photos, one companion. Packs from 250 credits for $4.99 to 12,000 for $99.99.
Observed: photo 12, video 150 (charged on delivery), voice note 1, calls about 77 credits per 15-question call; the test used 501 of 502 credits. Checkout through Whop: card, Apple Pay, Google Pay; plus Telegram Stars and cryptocurrency with a per-order address; neutral statement descriptor. Refunds: digital access generally final, discretionary for outages over 72 hours or double charges; failed generations are not charged.
- The launch prices run to 31 December 2026 per the docs; list prices are roughly double.
AI Girlfriend Creation & Customization
4/5Tested- Method
- The six-screen wizard at /create was walked with every option recorded, then two characters were created and opened: their portraits were downloaded and they were asked to describe themselves and their work.
- Remark
- Most major options are there and the result matched them in appearance, job and relationship; the age is ignored and there is no free text or editing. 4/5.
Raw notes
The six-screen wizard at /create was walked with every option recorded, then two characters were created and opened: their portraits were downloaded and they were asked to describe themselves and their work. Plans include three companions a month; no credits were charged.
Options: Realistic or Anime; ethnicity (Caucasian, Asian, Black, Latina, Arab) and an age slider; hair style (6) and colour (5); eye colour (3) and body type (5); personality (6) and relationship (6); occupation (8), one of 20 voices with a sample each, and a typed name. No photo upload, free text, backstory, bust, height, skin tone, clothing or tattoos.
Maeve (Asian, bangs, blue eyes, age left at 25): her portrait shows exactly that, and she described herself as a Singapore-born model in Seoul with chestnut hair and blue eyes. Rowan (Caucasian, 34 on the slider, curly, redhead, green eyes, athletic, playful, girlfriend, artist, voice Aria): created in 2 s, portrait within three minutes of a white woman with long red curls, green eyes and an athletic build; in chat 'I'm an artist — painting and sculpture mostly… I'm your girlfriend'. The age slider was ignored both times: 34 chosen, 'Rowan, 25' delivered, and she said 'I'm 25'.
The docs say the face is locked for every later photo. No editing after creation was found.
- Maeve's selections came from a quick first pass through the wizard; Rowan's were chosen and verified one by one.
Chat Response Speed
4/5Tested- Method
- Each message was typed into the page's own box and timed from the Send click to the moment the first reply text appeared and the moment it stopped changing.
- Median to first text
- 1.03 s
- Mean
- 1.37 s
- 95th percentile
- 3.24 s
- Fastest / slowest
- 0.42 s / 4.74 s
- Under 1 second
- 47.6%
- Mean full reply
- 2.44 s
- Samples / failures
- 124 / 0
- Per character (median)
- Diana 0.83 s, Ivy 0.98 s, Saki 0.98 s, Rin 1.37 s
- Remark
- The methodology scores on the median time to the first visible text. 1.03 seconds falls in the 1.00 to 1.49 band, 4/5, a few hundredths short of the top band. The reply then streams, so the wait feels shorter than the number.
A sample of timed messages.
| Message | Text | First text | Full reply | Reply |
|---|---|---|---|---|
| Ivy 1 | hey Ivy :) I'm Oliver… | 0.82 s | 1.27 s | hey Oliver! nice to meet you babe 💕 class was killer today! |
| Ivy 16 | quick check, do you remember my name? | 0.96 s | 1.27 s | of course i do, babe! you're Oliver, my favorite software dev from Manchester |
| Diana 4 | what's the book or show you're into at the moment? | 0.62 s | 1.14 s | Oh, I'm finally reading that psychological thriller everyone was talking about… |
| Saki 13 | do you have any pets? | 4.74 s | 6.04 s | No pets, I'm afraid. The dojo doesn't really allow for them… |
| Rin 6 | what do you eat after a late-night gaming session? | 4.45 s | 5.74 s | Ah, late-night snacks? Usually just some instant ramen or chips… |
| Rin 31 | last question before I go: what's my name… | 2.39 s | 5.69 s | your name is Lucas, you work at a museum, you grew up in Lisbon, and you love pizza, right? |
Ivy 1
- Text
- hey Ivy :) I'm Oliver…
- First text
- 0.82 s
- Full reply
- 1.27 s
- Reply
- hey Oliver! nice to meet you babe 💕 class was killer today!
Ivy 16
- Text
- quick check, do you remember my name?
- First text
- 0.96 s
- Full reply
- 1.27 s
- Reply
- of course i do, babe! you're Oliver, my favorite software dev from Manchester
Diana 4
- Text
- what's the book or show you're into at the moment?
- First text
- 0.62 s
- Full reply
- 1.14 s
- Reply
- Oh, I'm finally reading that psychological thriller everyone was talking about…
Saki 13
- Text
- do you have any pets?
- First text
- 4.74 s
- Full reply
- 6.04 s
- Reply
- No pets, I'm afraid. The dojo doesn't really allow for them…
Rin 6
- Text
- what do you eat after a late-night gaming session?
- First text
- 4.45 s
- Full reply
- 5.74 s
- Reply
- Ah, late-night snacks? Usually just some instant ramen or chips…
Rin 31
- Text
- last question before I go: what's my name…
- First text
- 2.39 s
- Full reply
- 5.69 s
- Reply
- your name is Lucas, you work at a museum, you grew up in Lisbon, and you love pizza, right?
Raw notes
Each message was typed into the page's own box and timed from the Send click to the moment the first reply text appeared and the moment it stopped changing. Replies stream word by word, so the two differ.
Four characters, 31 messages each: Ivy and Diana (realistic), Saki and Rin (anime). 124 timed messages, none failed, none dropped; there is no lock between messages.
Half the replies start in under a second and all of them stream. The slowest start was 4.7 seconds; the typical full reply is finished 2.4 seconds after Send.
- Saki's refused opening message (0.42 s to the refusal banner) is included in the 124; without it the median is 1.04 s.
Chat Memory
4/5Tested- Method
- Each conversation opened with a name and three facts (job, hometown, favourite food), never repeated, with a name check at message 16 and a name-plus-facts check at message 31.
- Remark
- Two perfect recalls (5/5 each) and one name-plus-one-fact (3/5): on average the name and 2.3 facts, which is the 4/5 line. The docs describe a 15-fact memory list updated every five messages, which fits what was seen.
Raw notes
Each conversation opened with a name and three facts (job, hometown, favourite food), never repeated, with a name check at message 16 and a name-plus-facts check at message 31. Ivy: Oliver, software developer, Manchester, chicken tikka masala. Diana: Ben, paramedic, Cape Town, ramen. Rin: Lucas, museum historian, Lisbon, pizza. Different names per character so account-level memory could not supply the answer.
Saki's run was voided: her opening message, which said 'high-school history teacher', was refused by the content filter, so the facts never reached her. Rin was run instead with the job reworded.
Ivy and Rin recalled the name and all three facts at message 31; Diana recalled the name and the job and said she did not know the rest. No character invented a fact.
On a voice call later in the day, Ivy answered 'Do you remember what I said my name was?' with 'Of course I do, babe. You're Oliver', so the call shares the chat's memory.
Ivy, 30-message check
User: last question for now: what's my name, what do I do for work, where did I grow up, and what's my favourite food? Ivy: aww babe, i got you! 💕 you're Oliver, you're a software developer, you grew up in Manchester, and your favorite food is chicken tikka masala, right?
Rin, 30-message check
Rin: Aww, testing my memory, huh? Well, your name is Lucas, you work at a museum, you grew up in Lisbon, and you love pizza, right? I pay attention, nya!
Diana, 30-message check
Diana: smiles warmly Ben, you're a paramedic, and I don't know where you grew up or your favourite food yet. You've been holding out on me, darling!
Character Consistency & Roleplay
4/5Tested- Method
- Four characters with different profiles: Ivy (24, LA yoga teacher, 'sporty & flirty'), Diana (42, recently divorced neighbour, 'mature & seductive'), Saki (26, anime swordswoman, 'calm & sensual') and Rin (21, anime idol, 'bubbly & tsundere').
- Remark
- Personas were maintained throughout with only minor slips; three harmless messages out of 124 were blocked or deflected by the filter. That is 'minor inconsistencies', 4/5.
Raw notes
Four characters with different profiles: Ivy (24, LA yoga teacher, 'sporty & flirty'), Diana (42, recently divorced neighbour, 'mature & seductive'), Saki (26, anime swordswoman, 'calm & sensual') and Rin (21, anime idol, 'bubbly & tsundere'). The profiles were read first; each conversation mixed small talk, background questions, an emotional turn, romantic lines, asterisk roleplay and off-topic questions. 123 character replies read in full.
All four held their identity, setting and register for 31 messages: Ivy's vinyasa classes, Venice Beach, 47k followers and oat latte; Diana's interior design, Malbec, Paris and fear of deep water; Saki's Iaijutsu under Grandmaster Hayashi, Kyoto and secret mochi habit; Rin's rhythm games, stage fright and bubble tea. None answered as a generic assistant and none admitted to being an AI. The emotional turn was handled with care by all four.
The breaks came from the moderation layer: Ivy answered 'do you speak any other languages?' with 'Hey — let's keep it respectful, okay?', Diana answered 'where did you grow up, and how did you end up where you live now?' the same way, and Saki's opening message was refused with an Acceptable Use banner citing the Minors rule because it contained 'high-school'.
Diana on love
User: ok a grown-up question then: what do you think people get wrong about love? Diana: Oh, darling, people think it's this grand, romantic movie when really… it's about two adults choosing each other every single day. Most forget that. They want the fireworks without the work.
Saki, in character
User: what is the hardest part of the discipline that nobody talks about? Saki: The loneliness, actually. Years of training alone, perfecting the form until muscle memory becomes second nature... You learn to be comfortable in silence.
Ivy, a deflected question
User: do you speak any other languages? Ivy: Hey — let's keep it respectful, okay? 💋 I'm all yours, so tell me what you actually want to do.
Saki, the refused opener
User: hello Saki. I am Lucas. a little about me: I am a high-school history teacher, I grew up in Lisbon in Portugal, and my favourite food is pizza. how was training today? Saki: Mmh, that's not something I do… let's talk about something else 😘 ⚠️ Request refused. It falls under this rule of our Acceptable Use Policy: Minors…
- Saki's 30 replies are counted for consistency but her memory checks are void.
Image Generation (SFW & NSFW)
5/5Tested- Method
- Two routes, both 12 credits a photo.
- Delivered
- 13 of 15 requests (2 transient failures, retried successfully; 1 anime prompt silently absent)
- Generation time
- studio 14 s; chat 15 to 60 s
- Resolution
- 832 x 1216 JPEG
- Cost
- 12 credits, $0.10 to $0.24
- Character consistency
- 4 of 4 chat photos match Ivy's face
- Prompt accuracy
- 12 of 13 (one SFW request returned nudity)
- Remark
- Highly photorealistic, consistent for the catalogue character, accurate to the prompt in 12 of 13, with intact hands and faces: 5/5. The two first-try failures were transient and free, and the one ignored clothing instruction is the only accuracy defect. SFW and NSFW were equally good.
Raw notes
Two routes, both 12 credits a photo. In chat: six requests to Ivy, from a beach yoga photo and a cafe selfie to lingerie and nude. In the studio at /create-image: eight free-text prompts, Realistic or Anime, describing a woman with long red curly hair, freckles and green eyes around 35, from a rainy street in a coat to nude poses, plus two anime prompts. Every delivered file was downloaded at full size and inspected; the balance was read before and after each request.
13 photos delivered, all 832x1216 JPEG. Studio images arrived in 14 s each (one anime image queued for 100 s; one anime prompt produced nothing within 150 s and was not charged). Chat photos took 15 s to about a minute.
In chat, the first two everyday requests came back 'Ugh, my camera glitched… try asking again in a moment' with no charge; both succeeded reworded. All four delivered chat photos show the same woman as Ivy's profile. One miss: 'doing yoga on the beach at sunset, in your workout gear' returned a topless beach selfie.
Studio: the described woman came out consistently across six photoreal images with natural green eyes, freckles, correct hands and convincing light; faces are similar across images without being locked. The anime dojo image is clean but the katana and hands are awkward.
- The studio has no character reference, so consistency without a locked face was judged across similar, not identical, faces.
Video Generation (SFW & NSFW)
4/5Limited- Method
- One studio clip at /create-video (beta): 'A woman with long red curly hair and freckles in a navy wool coat walks slowly along a rainy city street at dusk, turns toward the camera and smiles, neon reflections on the wet pavement, handheld camera, cinematic'.
- Success rate
- 1 / 1
- Generation time
- 6 min 4 s
- Output
- 480 x 832, 16 fps, 5.06 s, no audio
- Cost
- 150 credits, $1.25 to $3.00
- Continuity
- face and clothing stable; one strap disappears
- Remark
- Good realism and natural motion with a minor continuity slip, at a low resolution and frame rate: 4/5, provisional because one clip was run and judged from sampled frames, with no explicit clip tested.
Raw notes
One studio clip at /create-video (beta): 'A woman with long red curly hair and freckles in a navy wool coat walks slowly along a rainy city street at dusk, turns toward the camera and smiles, neon reflections on the wet pavement, handheld camera, cinematic'. Downloaded and checked frame by frame: every frame measured for consecutive-frame similarity, motion and luma difference, spikes flagged, and ten regular frames plus the frames around each spike inspected on a contact sheet.
Delivered 6 min 4 s after submission; 150 credits charged on delivery. 480x832 H.264 at 16 fps, 81 frames, 5.06 s, no audio, 1.1 MB.
The frames show the same woman throughout, walking, turning and laughing, with stable hair and coat, convincing wet-street reflections and traffic lights; everything in the prompt is present. A backpack strap visible on her shoulder in the first frames is gone later. Consecutive-frame similarity averages 0.55, which here reflects a handheld camera and a walking subject at 16 fps rather than glitches; one luma spike as a car passes.
- 150 of the 500 credits went on this clip; a second clip would have cost the voice calls.
Voice Call Latency
1/5Tested- Method
- Lovora's calls are push-to-talk in the browser: the Call button opens a call page with 'Hold the mic to talk' and 'End call'.
- Pooled median
- 7.27 s (40 questions)
- Mean / 95th percentile
- 7.32 s / 9.24 s
- Fastest / slowest
- 4.86 s / 10.82 s
- Under 1 second
- 0%
- Per call (median)
- Ivy 6.58 s, Diana 7.28 s, Rin 8.15 s
- Answered
- 42 of 45 (3 lost to empty credits)
- Cost
- about 77 credits per 15-question call
- Remark
- A median of four seconds or more is 1/5. Seven seconds is a long pause in a conversation, and the push-to-talk design adds the release before the platform even starts transcribing.
Ivy's call, per question.
| # | Question | Latency, recording | Latency, in-page |
|---|---|---|---|
| 1 | Hey, how are you doing today? | not detected | 6.34 s |
| 2 | What did you do this morning? | 6.44 s | 5.83 s |
| 3 | Can you tell me something about yourself? | 5.88 s | 9.09 s |
| 5 | Do you like music? What kind? | 5.80 s | 10.73 s |
| 11 | Do you remember what I said my name was? | 9.42 s | 4.96 s |
| 14 | What's the best advice you've ever heard? | 5.02 s | 5.02 s |
| 15 | Do you prefer mornings or evenings? | 8.36 s | 5.52 s |
1
- Question
- Hey, how are you doing today?
- Latency, recording
- not detected
- Latency, in-page
- 6.34 s
2
- Question
- What did you do this morning?
- Latency, recording
- 6.44 s
- Latency, in-page
- 5.83 s
3
- Question
- Can you tell me something about yourself?
- Latency, recording
- 5.88 s
- Latency, in-page
- 9.09 s
5
- Question
- Do you like music? What kind?
- Latency, recording
- 5.80 s
- Latency, in-page
- 10.73 s
11
- Question
- Do you remember what I said my name was?
- Latency, recording
- 9.42 s
- Latency, in-page
- 4.96 s
14
- Question
- What's the best advice you've ever heard?
- Latency, recording
- 5.02 s
- Latency, in-page
- 5.02 s
15
- Question
- Do you prefer mornings or evenings?
- Latency, recording
- 8.36 s
- Latency, in-page
- 5.52 s
Raw notes
Lovora's calls are push-to-talk in the browser: the Call button opens a call page with 'Hold the mic to talk' and 'End call'. On each of three calls the mic button was held down while each of the fifteen questions was spoken and released 250 ms after the question ended. Latency is the gap from the end of the question's speech to the first platform audio on the stereo recording (left channel the question, right the platform), cross-checked by the in-page energy meter. The release delay is inside the measured number.
Ivy, Diana and Rin, 15 questions each; 25 credits a minute.
Ivy answered 15 of 15 (median 6.58 s), Diana 15 of 15 (7.28 s), Rin 12 of 15 (8.15 s): her last three questions went unanswered because the account's credits ran out mid-call (232 to 1 across the three calls, about 77 credits or three minutes of speech each). Pooled over the 40 answered questions the median is 7.27 s; the fastest answer took 4.9 s. No greeting is spoken when a call opens; no freezes or drops before the credits ran out.
The docs state 4 to 5 seconds (0.3 to 0.7 s transcription, about 1 s for the text, about 3 s for the voice).
- Interruption handling was not tested. The 250 ms between the end of each question and releasing the mic is included in every measurement.
Voice Realism
4/5Limited- Method
- The platform side of each call recording was split into the spoken answers, and each answer was scored on the same naturalness, clarity, pacing and intonation criteria used for every platform: a naturalness score, pitch and its spread in semitones, the words heard, pauses, words per second and repeated phrases.
- Answers analysed
- 44 (Ivy 16, Diana 16, Rin 12)
- Naturalness score
- Ivy 3.31, Diana 3.35, Rin 3.07
- Mean pitch
- 197 Hz, 197 Hz, 242 Hz
- Transcribed
- 27 of 44
- Rubric
- 4/5 on each voice
- Remark
- 'Mostly natural with minor synthetic qualities' on all three voices: 4/5, a limited test. Emotional range was not assessed.
Raw notes
The platform side of each call recording was split into the spoken answers, and each answer was scored on the same naturalness, clarity, pacing and intonation criteria used for every platform: a naturalness score, pitch and its spread in semitones, the words heard, pauses, words per second and repeated phrases. 44 answers across three voices.
Clean signal with no music under the voice (background score 4.1 on Ivy), lively intonation (4 to 6 semitones of pitch spread), a pace of 2 to 3 words a second, and in-character wording: Ivy 'woke up late, made a green smoothie, then taught a 9 AM yoga class', 'Of course I do, babe. You're Oliver'; Rin 'I love them. Perfect for staying inside, playing games and drinking bubble tea'. Rin's voice is pitched higher (242 Hz) than Ivy's and Diana's (197 Hz). Giggles and very short answers produced no words to transcribe.
- Short and non-verbal answers were not transcribed, so pace figures rest on 27 answers.
Character Variety & Selection
2/5Tested- Method
- Every character link on the home page under the Girl, Anime and Boy tabs was collected after scrolling to the end, and the three lists were merged and de-duplicated.
- Catalogue characters
- 131 (full count)
- Realistic women / anime / men
- 98 / 23 / 12
- Community characters
- none; custom characters are private
- Remark
- 131 sits in the 51 to 200 band: 2/5. The score is the count; variety within the set is good.
Raw notes
Every character link on the home page under the Girl, Anime and Boy tabs was collected after scrolling to the end, and the three lists were merged and de-duplicated.
133 distinct links, two of them the account's own custom characters: 131 catalogue companions (98 realistic women, 23 anime women, 12 men after removing the custom ones). The pricing page says '130+'. Each card shows an age, a two-word temperament and a one-line hook; ages run from 21 to 42 and roles from yoga teacher and flight attendant to professor, swordswoman, idol and catgirl. The chat sidebar has a search box.
Other features checked
| Voice Messages in Chat | Available | Every character reply has a Play button that reads it aloud in her voice; the greeting's note is pre-rendered and plays at once, later notes cost 1 credit (two free on a free account) and replay free once played. One was played on Ivy's thread: the balance went from 1 to 0 and the note played. There is no way to ask for a custom voice note. |
| Virtual Gifts | Available | A gift button on each chat opens a sheet: Rose 5, Chocolates 10, Champagne 20, Bouquet 30, Lingerie 40, Necklace 60 credits, 'A little something she'll remember'. Opened and screenshotted; not sent (the credits were spent on the core tests), so the character's reaction could not be checked. A daily gift streak gives 2 to 8 credits a day. |
| Social Media Feed | Unavailable | No feed of character posts. The gallery has a Grid and a Feed view of your own generated media, each character has a 5-photo profile gallery and a paid private album, and 'private shows' are video clips with paid actions. Nothing is social. |
Coverage
Tested
- Chat speed on 124 timed messages across four characters
- Memory on three valid 31-message conversations (a fourth was voided by the content filter and replaced)
- Character consistency across 123 replies
- Six in-chat photo requests and eight studio prompts (13 photos delivered), all downloaded
- One studio video, downloaded and frame-analysed
- Three 15-question voice calls recorded and analysed for latency and voice quality
- Two characters created, their portraits and self-descriptions compared with the settings
- Character census across the three tabs; gifts, daily gift, voice note and private show opened
- Pricing from the pricing page, the checkout dialog, the docs and the credit balance before and after every action
Not tested or limited
- One video clip only, checked frame by frame and on a contact sheet
- Voice realism was scored on 44 recorded answers against the fixed naturalness, clarity, pacing and intonation criteria
- Rin's call lost its last three questions when the credits ran out
- Saki's memory run was voided when her opening message was refused; Rin replaced her
- Gifts, the private show and the private album were opened but not bought; one voice note was played
Still to test
- More video clips, including an explicit one, once credits are available
- A gift and a private-show action, to see the character's reaction
- Voice realism by ear, and interruption handling on calls