LTX 2.5 Dialogue & Voice Prompts
More than 80 LTX-2.5 video prompts collected from Civitai, fal.ai's LTX-2.5 example pages and X. Each one is quoted in full, word for word, credited to its author and linked to the original post, and the card plays the clip it produced where the source has one. We did not write any of them. Many Civitai entries were made with the open LTX-2.5 weights in local ComfyUI workflows, so they are the same model family but were not run on our API.
Last updated: · LTX 2.5 Fast API — pricing & playground · API docs
TL;DR
LTX-2.5 is the open-weights video and audio model Lightricks released on 11 August 2026, and every clip it makes comes with sound generated alongside the picture. On apimodels.app it runs in two tiers. LTX 2.5 Fast (ltx-2.5-fast) takes a prompt alone, a prompt plus one first frame, or a prompt plus an audio track, and returns 720p, 1080p or 1440p at 24 to 50 fps, 6 to 20 seconds long, from $0.081 per second. LTX 2.5 Pro (ltx-2.5-pro), the tier Lightricks positions for final renders, takes text or a first frame and returns 720p or 1080p at 6, 8 or 10 seconds, from $0.108 per second. Prompts can be up to 5,000 characters; there is no 4K, last frame, reference image or video input; failed tasks are not charged. This page collects more than 80 LTX-2.5 prompts that other people published on Civitai, on fal.ai's LTX-2.5 pages and on X. Many of the Civitai ones were run locally on the open weights with the creator's own settings, so the same text can look different on the API.
Source: Lightricks LTX (the model vendor’s official site)
Sci-Fi Cafe Holo-Phone Complaint
Use the provided start image exactly as the first frame. Short clip of a woman in a sci-fi cafe with holographic waitresses and futuristic flying cars outside. Performance: The woman speaks and gesticulates casually, saying "No, it's not that. I love my holo-phone. It's just that... well, okay, this is just an example, but you'd think by now we'd be done wiping our asses with paper!" Keep the acting natural and cinematic.
Overcast Outdoor Interview
A cinematic outdoor interview scene in soft overcast daylight. The camera begins in a medium over-the-shoulder shot from behind the male interviewer, keeping the blonde woman in sharp focus while he holds the microphone naturally toward her. She maintains eye contact with him and speaks calmly, her lips moving naturally in sync with her words: "I think people sometimes forget how much the little things matter." She gives a small thoughtful smile and makes a subtle hand gesture as she finishes. The camera slowly pushes closer toward her face with shallow depth of field. She pauses, listening attentively. The interviewer slightly lowers the microphone toward himself and asks in a relaxed, curious voice, "So what made you realize that?" The camera smoothly shifts focus toward him for a brief reaction shot, then returns to the woman as the microphone moves naturally back toward her. She takes a short breath, tilts her head slightly and replies with a warmer expression, "Honestly? Someone reminded me when I needed it most." She gives a gentle smile and briefly looks down before meeting his eyes again. The camera settles into a close-up of her face for the final moment, capturing subtle blinking, breathing, loose strands of hair moving in the breeze and natural facial micro-expressions. Realistic conversational timing, natural pauses between speakers, accurate lip synchronization, restrained body language, smooth cinematic camera movement, natural motion blur, realistic skin texture, shallow depth of field, soft ambient city noise, distant birds, light wind through nearby trees, no music.
Spreadsheet Hypnosis Goose Moment
The woman pauses while working on a spreadsheet, and mumbles aloud while in an apparent hypnotic state, saying "what even are numbers? it's just a symbol... that has a value? but why? it's just like, some lines, right?" She snaps awake. "Oh my god, the goose!"
Store Return Wedding Dress
She speaks to the assistant off-camera, polite and matter-of-fact. "I'd like to return this." She glances at the bag. "I bought it for my sister's wedding, which... is now my wedding... so... I'll need it in white." She smiles bashfully. Quiet store, a soft till beep. Single continuous take.
Construction Site Family Interview
She speaks loudly over nearby construction noise to the interviewer off-camera, composed and pleased. "I know it's construction, but I run this site like a family." She pauses. "Which means nobody talks, and one of us isn't allowed at Christmas." A small satisfied nod. She holds it. Sound of power tools, diesel engines, a reversing beeper. Single continuous take.
Detective Explains the Methodical Suspect
The detective speaks to her colleague off-camera, grave and authoritative. "We're looking for someone calm. Methodical." She pauses, looks down at the notebook. "They rinsed the mug. Then they left it in the sink. So, calm, but not raised right." She looks back up and holds it. Quiet room, a faint police radio. Single continuous take.
Kiwi Woman at Job Interview
She speaks with a native Kiwi accent to the interviewer off-camera, pleasant and entirely sincere. "Why here?" A small nod, as if it's a good question. "I'd be keen to work wherever, honestly. This is the closest Woolies to my house." She pauses. "There's a Bunnings closer. But they haven't called back." She holds the look, helpful. Quiet office, a distant printer. Single continuous take.
Fisherwoman Talks About the Fish
She speaks to the interviewer off-camera, slow and quietly certain. "Grew up on boats. And I've learned one thing." She pauses, looks out at the water. "The fish are in the water. Not on the boat. You'd be surprised how many people check the boat." She looks back. Gulls, water slapping the hull. Single continuous take.
Captain Gives Odd Flight Announcement
She speaks into the handset, warm and practised, like every announcement she's ever made. "Good morning, this is your captain. Flight time today is about an hour." She pauses. "We'll be cruising at... hmm... four hundred feet, I guess." A beat. "I like to see things." She sets the handset down. Cabin hum, a seatbelt chime. Single continuous take.
Two Goblin Guards Banter
The goblin on the right says, "Aren't you cute?" The goblin on the left says, "Yup, we got jobs here as guards."
Deadpan Cafe Manager Interview
She speaks to the interviewer off-camera, calm and quietly certain. "How long have I worked here? Since Tuesday." She pauses. "I'm the manager now. Sarah was the manager. Sarah went to lunch." A small nod. She holds it. Café room tone, the hiss of a steam wand. Single continuous take.
Amsterdam Night Selfie Vlog
A spunky 20-year-old African woman with curly brown hair, wearing oversized tortoiseshell sunglasses and a denim jacket, walks through the vibrant, neon-lit streets of Amsterdam’s nightlife district at night. The camera follows her in a handheld selfie style, keeping her centered as she strolls past bustling crowds, glowing street lamps, and glowing shop signs reflecting off wet pavement. She beams with wide, joyful smiles, laughing as she speaks to the camera. Her voice is bright and playful. Shot 1: She begins walking forward, smiling and talking directly to the camera, exclaiming “This is my first time in Amsterdam and I already love it!” The camera gently bobs with her steps as she laughs, revealing the lively street behind her with trams passing and people mingling. She gestures with her free hand, excitement radiating in her posture. Shot 2: As she continues walking, she pauses slightly, turning her head to glance around playfully, then leans in toward the camera with a mischievous grin and says, “I already tried some weed in a local coffee shop, and I met a cute guy there.” She raises her eyebrows and winks, the camera tilting slightly to catch the sparkle in her eyes. Shot 3: She leans even closer, grinning, then whispers teasingly, “I’ll totally go home with that guy, and just see what will happen.” Her cheeks flush slightly as she says this, her eyes darting away for a split second before returning with an even bigger grin. She chuckles nervously, “Oh my gosh, I’m so embarrassed saying that,” and shakes her head with a giggle, her hand fluttering near her sunglasses. Behind her, the street noise fades slightly as she pauses, soaking in the moment, the neon lights casting colorful glows across her face. The video ends with her stepping forward again, laughing heartily, the camera following her as she walks away, still smiling, the energy of the city pulsing behind her. No fade to black—just her motion and laughter carrying the vibrant rhythm of Amsterdam’s nightlife.
Irish Woman Speaks to Camera
Create a SFW video where the woman, 25yrs, Irish, speaking English with lilting Irish accent, says: "Hi guys, Coral here. I understand someone on this site is asking for my number. I'm flattered, but I'm a shy gal, so, sorry. But hey, from my portfolio you can see I frequent the MTA, the Underground and the DART & LUAS in Dublin. If you're on one of them, stay alert and maybe, who knows?"
Vienna Hotel Room 1974 Standoff
A slow dolly in on a man seated at a small table in a Vienna hotel room in 1974, framed from just off his left shoulder. He is in his fifties, thinning grey hair, tie loosened, a cigarette burning down in an ashtray he has forgotten about. A single practical lamp on the table lights him hard from below the eyeline and leaves the rest of the room in near darkness, the window behind him carrying wet streetlight and nothing else. He looks up at someone off camera, waits, and says quietly in English with a slight German accent: "You had the file for six weeks and you brought me a photograph." Then he taps the ash and looks back down. 40mm at f/2, cool tungsten falloff, fine grain, one continuous shot with no cuts. Sound: his voice close and dry with the room's small reverb under it, traffic hissing on wet road below, a radiator ticking, no music.
Defense Lawyer Closing Argument
A woman in her forties speaking American English, low and measured, a defense lawyer near the end of a long trial, no urgency anywhere in the delivery, quiet courtroom room tone sitting behind the voice: "You have heard eleven days of testimony. Not one of those days put my client in that room." 9 seconds.
Insect Dragon Speaks in Lady Voice
The insect dragon says in a lady's voice, "I hope I look good, hun."
How to write great LTX 2.5 prompts
- 1Write one shot as one paragraph, in the order it happens. The fal.ai examples on this page each describe a single camera setup from start to finish: shot size and subject, what happens, how the camera moves, the light, and last the lens. "Slow push-in on a boxer … hard overhead spotlights cutting through haze … 50mm at f/2" is the pattern. A pile of keywords gives the model no order to follow.
- 2Write the sound, because every clip has it. LTX-2.5 generates audio together with the picture, and our API has no silent option, so decide what it should sound like. Put spoken lines in quotes and say who speaks, then name the ambience and the one sound that matters. Several Civitai prompts here script a two-person conversation line by line, describing each voice before it speaks.
- 3Size the action to a length the API offers. On Fast, text and image prompts run 6 to 20 seconds in even steps, and only 6, 8 or 10 at 1440p or at 48 / 50 fps; Pro runs 6, 8 or 10. Local workflows often set length as a frame count, so divide it by the frame rate to see what the post asked for and pick the nearest allowed length. The API does not pick a length from your prompt; set duration.
- 4With a first frame, describe the motion, not the picture. In image-to-video the image already fixes the subject, the set and the framing, so spend the prompt on what moves: who turns, what the camera does, what you hear. The clip keeps the image's shape, and sending aspect_ratio together with a first frame returns a 400.
- 5For audio-to-video, the track leads and the prompt casts it. On LTX 2.5 Fast, an audio_url becomes the soundtrack as it is, and the picture is generated to match it. Describe who is on screen, how they move and how the shot is framed, as in our docs example: "A young presenter speaks to the camera in a bright studio, natural hand gestures, medium shot." Length follows the audio unless you set duration. Pro does not take audio.
- 6Strip what the API cannot take. A local LTX-2.5 workflow can carry a negative prompt, LoRA trigger words, extra guide images or a last frame. Our request takes a prompt, one first frame, one audio track and the generation settings, and nothing else: a last frame, reference images or video input return a 400. There is no negative-prompt field either, so anything a post kept there is lost unless you move it into the prompt.
- 7Keep on-screen text and chaotic physics off the critical path. Lightricks' own prompting guide says on-screen text and chaotic physics are still uneven. If a shot depends on a readable sign or a pile of objects colliding, plan for several tries, or add the text in the edit.
Prompt formula
Shot size and subject + one clear action, in order + camera move + light and time of day + lens or film look + spoken lines in quotes and the ambience + a length the tier allows (sent as duration, not written in the prompt)
Example from the collection, quoted as posted (hichuicomfy on Civitai): Style: high-resolution food photography - close-up - The chocolate is poured over the whipped cream and berries. The chocolate flows slowly, creating rich, glossy streaks across the white cream and the blue blueberry, the deep brown contrasting with the vibrant fruit. A soft, rich sound of chocolate dripping and settling accompanies the pour.
Frequently asked questions
What is LTX-2.5?
LTX-2.5 is Lightricks' video and audio model, released with open weights on 11 August 2026, and it generates sound together with the picture on every clip. Lightricks offers it in two API tiers: Fast, for speed and cost, and Pro, which it describes as tuned for visual fidelity and motion stability. Lightricks also says LTX-2.5 adds native multi-shot scenes, a new video decoder and better prompt adherence; those are the vendor's claims, not our test results.
Who wrote these prompts?
Other people did: every prompt here was published by a creator on Civitai or X, or by fal.ai on its LTX-2.5 pages, and we did not write or edit any of them. Each card quotes the prompt in full, word for word, names the author and links the original post. The prompts and clips belong to their creators; our own notes and data are licensed CC BY 4.0. To correct a credit or have an entry removed, email us or open an issue on the GitHub repository.
I ran a Civitai prompt from this page on the API and got something different. Why?
Most Civitai prompts here were run on the open LTX-2.5 weights on the creator's own machine, not on our API, so the same text can come out differently. A local ComfyUI run may use a dev or distilled checkpoint, a LoRA, its own sampler settings, a negative prompt or extra guide images, and none of that is in the prompt text. The prompt carries over; those settings do not. Treat the clip on the card as what that setup produced, and expect a few tries on Fast or Pro to get close.
Where can I run these prompts, and what does it cost?
On apimodels.app, with the model ids ltx-2.5-fast and ltx-2.5-pro on POST /v1/video/generations, billed per second of output. Fast is $0.081/s at 720p, $0.117/s at 1080p and $0.171/s at 1440p: 6 seconds at 720p is $0.486, 10 seconds at 1080p $1.17 and 20 seconds at 1080p $2.34. Pro is $0.108/s at 720p and $0.153/s at 1080p, so 10 seconds at 1080p is $1.53. Both are 10% below Lightricks' API list price, audio-to-video on Fast is billed on the output length to 0.01 s, and failed tasks are not charged. A common way to work is to try a prompt on Fast and render the chosen shot on Pro; the fields are the same, so switching is one model string.
Why does a prompt from this page get rejected or fail on the API?
Requests outside the API's limits are rejected with a 400 before a task is created, and are not charged. The limits: prompts up to 5,000 characters; 6 to 20 seconds in even steps on Fast and 6, 8 or 10 on Pro; no 4K, last frame, reference images or video input; no audio and no 1440p on Pro; and no aspect_ratio when you send a first frame. A task can also fail after it starts, on content review or a busy upstream, and is not charged either.
Does LTX-2.5 make the sound too?
Yes: every clip comes with sound generated together with the picture, and our API has no silent option. If the sound matters, write the dialogue in quotes and name the ambience. On LTX 2.5 Fast you can also send your own track as audio_url, and the picture is generated to match it.
Can I use these prompts and videos commercially?
The prompts and clips belong to their creators, so check the original post before reusing a prompt commercially. For clips you generate yourself, follow the terms of the service you generate them with. If you run the open weights locally, they come under Lightricks' LTX-2.x Community License, which sets its own conditions; read it before any commercial use.
Run these prompts on apimodels.app
LTX 2.5 Fast is live here alongside 180+ other image, video, audio and language models — one API, one key, pay as you go, with $0.10 of trial credit on sign-up.
This library is open source on GitHub
The whole collection is on GitHub as Markdown and JSON: every prompt with its author's credit and a link to the original post on Civitai, fal.ai or X. Prompts are quoted in full, word for word, and belong to their creators. The clips stay with their creators and are linked, not re-hosted. Our own notes and data are licensed CC BY 4.0. Open an issue to correct a credit or have a prompt removed.
View on GitHub