Skip to main content
Kyeo AI
AI Audio Models
Currently unavailable

Gemini 3.8 Flash TTS

Gemini 3.8 Flash TTS cannot be selected for new generation tasks; this page records its availability.

Online use is currently unavailable

This page is for reviewing the model's capabilities, use cases, and public references. The model does not appear in the home workbench, and you cannot submit generation tasks with it.

View available models

Examples

Audio scene

Use the uploaded storyboard as the full visual reference. Follow panels left to right, top to bottom. Generate one continuous 15-second cinematic anime video. Match the storyboard’s character design, clothing, framing, lighting, emotion, and scene order. IMPORTANT: Visuals only. No dialogue, no narration, no vocals, no music, no sound effects, no generated audio. Style: nostalgic late 90s / early 2000s anime film, hand-drawn feeling, painted night backgrounds, soft moonlight, warm yellow-green firefly glow, peaceful magical realism, gentle cinematic motion. 0:00-0:02 — Wide backyard at night under a starry sky. Cool moonlight on grass. A distant forest glows softly with many fireflies. The young boy stands small in frame and notices one tiny light near the ground. Slow push-in. 0:02-0:04 — Medium shot. The boy kneels beside one lone firefly glowing near the grass. Its warm light softly illuminates his curious face from below. Slow dolly down to his eye level. 0:04-0:06 — Close-up of the boy’s hands gently cupping the firefly. Soft glow leaks through his fingers. Cut to his calm smile and wonder-filled eyes. Intimate slow push-in. 0:06-0:08 — Wide-to-medium tracking shot. The boy walks across the moonlit meadow toward the glowing forest, holding his cupped hands near his chest. Tall grass moves gently around him. Warm light pulses softly from his hands. 0:08-0:10 — At the forest edge, the boy stops and slowly opens his hands. The firefly rests on his palm for a quiet beat. Dark trees behind him, many fireflies floating deeper in the forest. Slow push-in. 0:10-0:12 — Close-up as the firefly lifts from his palm, leaving a soft glowing trail. Camera follows it upward, then gently pans as it flies toward the other fireflies. The boy watches in silhouette. 0:12-0:14 — Wide magical forest shot. The lone firefly joins the group, and all fireflies brighten together in one soft golden-green pulse. The forest fills with warm light. The boy stands still, peaceful and small. 0:14-0:15 — Final wide shot. The boy walks back toward his distant home. The glowing forest remains behind him. Stars and moonlight create a calm, nostalgic ending. Slow pull-back. Camera: slow dolly, smooth tracking, stable cinematic movement, soft transitions. Avoid: fast cuts, shaky camera, character morphing, inconsistent face, changed outfit, changed hairstyle, extra limbs, bad anatomy, harsh lighting, flicker, teleporting objects, warped backgrounds, text, watermark, UI.

Audio scene

Create a 15 second vertical 9:16 ultra realistic smartphone selfie video at night. A completely original young woman fills almost the entire frame. She has a short electric blue curly bob, warm amber eyes, soft freckles across her nose, subtle crescent shaped silver eye makeup, glossy natural lips and a tiny silver nose ring. She wears an oversized midnight purple quilted hood with burnt orange satin lining and delicate embroidered constellation patterns, with a black high neck top underneath. The camera stays extremely close to her face like a casual front phone camera recording inside a dim car. Warm dashboard light softly illuminates her skin while the background remains dark and slightly blurred. Natural handheld micro movement, realistic phone lens distortion, detailed skin texture and believable eye reflections. At the beginning she tilts her head slightly toward the camera with a playful wide smile and visible teeth. She looks directly into the lens and naturally moves her lips as if having a friendly conversation. During the next few seconds she gently straightens her head, blinks naturally, raises one eyebrow and switches between a soft smile and an amused grin. Around the middle she laughs silently, eyes narrowing briefly, cheeks lifting, then relaxes again. During the final five seconds her mood gradually changes. Her smile fades, her eyes open wider and her expression becomes calm and slightly serious while she continues subtle natural lip movement. She briefly closes her eyes, opens them again and finishes looking directly into the camera with a quiet neutral expression. Keep the performance spontaneous and human with realistic breathing, tiny facial muscle movements and perfect character consistency. No scene cuts, no text, no logos, no watermark.

Audio scene

Main Subject: Young Korean woman, early 20s, light cardigan over a summer dress, small crossbody bag, hair down and slightly wavy, excited cheerful expression. Location: Small local fairground, early evening. Ferris wheel lights starting to glow, distant carnival games, scattered benches, string lights overhead. No crowds, no commercial branding. Visual Style: Ultra-realistic documentary realism, joyful candid feeling, soft dusky evening light. Camera Style: Early 2000s consumer DV camcorder aesthetic, handheld shake, autofocus hunting on flashing lights, exposure pumping between bright lights and shadow. No stabilization. Timeline (15 sec, each slot = 2 compressed beats): 00:00–00:03 → She sits in the ferris wheel cabin, then looks out as it slowly rises. 00:03–00:06 → She turns to camera saying "여기서 보는 경치 진짜 좋다" ("The view from here is really nice"), smiling. 00:06–00:09 → The cabin reaches the top; she gasps softly at the skyline view. 00:09–00:12 → She points at something below, laughing excitedly. 00:12–00:15 → She looks at camera saying "다시 타고 싶다" ("I want to ride again"), grinning as it fades. Audio: Faint carnival music in distance, wind, creaking cabin, distant chatter. Her dialogue as noted above. No music beyond ambient scene sound. Goal: A joyful, nostalgic fair moment warm, excited, believable.

Audio scene

THE GIANT FIRE ROLL 13s, 1:1, 30fps, 7 hard cut shots. Photoreal handheld, harsh midday sun, South Asian cooking yard, iron trough over wood fire, bubbling ghee. AYAAN: man 32, brown skin, short black hair, trimmed beard, calm, never comic. Face and build identical every shot; clothes change only after a cut, never on camera. KABIR: man 30, stubble, off-camera until S7. ROLL: 2m masala roll, 38cm thick, spiral scoring identical throughout, heavy enough to bend posture; crust advances pale gold to charred. S1 0-1.55 24mm wide. Beige sleeveless kurta, olive dhoti, red gamcha. Ayaan strides at lens, raw roll on shoulder. KABIR: "That's lunch?" AYAAN into lens: "For now." S2 1.55-3.1 28mm low. White shirt, leather apron, headwrap. Roll hits ghee, violent sizzle, steam at lens. AYAAN: "Stand back." S3 3.1-4.7 35mm high diagonal down the trough. Emerald kurta, rust waistcoat. Copper ladle throws butter along the spiral. KABIR: "New clothes?" AYAAN: "New stage." S4 4.7-6.25 50mm low tracking above the rim. Chef jacket, red bandana. Firewood dropped under the trough, flame rolls beneath. AYAAN: "More fire." S5 6.25-8 35mm handheld, whip-pan down. Charcoal shirt, goggles. Two hooks turn the roll a quarter turn, metal shrieks. KABIR: "Too much!" AYAAN: "Almost." S6 8-10.25 28mm wide. Cream kurta, cobalt waistcoat. Knife cracks crust. 65mm macro: steam, paneer, vegetables, molten cheese. AYAAN: "Taste it." S7 10.25-13 50mm two-shot. Maroon sherwani; Kabir in denim shirt. He bites, crunch, eyes widen. KABIR: "Bigger tomorrow?" AYAAN, looking past him: "Behind you." Fast pan to a cart 8m away holding a 4m raw roll, cart bowing. Black at 13.00. AUDIO diegetic only: dialogue, sand steps, fire crackle, sizzle, steam, metal scrape, knife crack, crunch. No music. LAST FRAME: black, no on-screen text, captions, subtitles, logos or watermarks. NEGATIVE: music, text, dissolves, slow motion, drone, on-camera wardrobe morph, face change, extra fingers, crowd, glossy ad.

Audio scene

Create a 30 second cinematic surreal mystery film, 16:9, inspired by a pale, foggy winter morning in a quiet American coastal town. The visual palette is muted ivory, warm gray, faded sage, and soft beige. Natural diffused light, subtle film grain, shallow depth of field, gentle halation, realistic skin and fabric textures, restrained camera movement, atmospheric fog, premium art house cinematography. No dialogue, no subtitles, no on screen text. 0–5 seconds: Begin with a slow cinematic close-up of a young woman with a short black bob and soft bangs, wearing an ivory knitted turtleneck. She stands motionless beside a window. Pale morning light softly illuminates her face. Her expression is calm but slightly uneasy. The camera slowly pushes toward her eyes while distant traffic and soft room ambience can be heard. 5–10 seconds: Match cut to a wide aerial view of a silent fog-covered lake surrounded by low hills and winter reeds. A few birds float across the still water. Slowly drift forward through the mist toward a lonely suburban neighborhood. Everything feels unusually quiet and suspended in time. 10–15 seconds: Interior of an old house. A ceramic vase filled with thin flowering branches stands beside a bowl of pale fruit on a windowsill. A steaming cup of coffee sits nearby. Outside the glass, vintage cars move slowly through the fog. The camera gently tracks toward the coffee cup as its steam curls upward. 15–20 seconds: Cut to a deserted parking lot at dusk-like morning light. A single streetlamp glows through thick mist. Across the road stands a large white colonial style house reflected perfectly in dark still water. Slowly zoom toward an upstairs window where a vague silhouette appears for only a moment, then disappears. 20–25 seconds: Inside a softly lit corridor filled with blurred people walking past camera, reveal a mysterious humanoid figure with a realistic black goat head, long curved horns, and a clean ivory overcoat. The figure walks calmly toward camera while everyone else remains out of focus. Its movement is natural and restrained, not monstrous. Slow handheld backward tracking shot, subtle tension building in the music. 25–30 seconds: The young woman walks along a foggy small-town street toward a corner building while the goat-headed figure follows several meters behind her. She suddenly stops. Cut to a close up of the coffee cup beside the window the liquid surface begins to ripple even though nothing touches it. Through the blurred window reflection, the horned figure is now standing directly behind her. Hold for one second, then cut abruptly to black. Visual direction: photorealistic cinematic imagery, 35mm film texture, vintage lenses, soft bloom around lights, volumetric fog, overcast winter daylight, controlled highlights, creamy low-contrast color grade, realistic human motion, subtle surrealism, smooth match cuts, slow dolly shots, symmetrical compositions, occasional shallow-focus close-ups. Sound design: distant wind, faint birds, soft traffic through fog, ceramic cup movement, quiet footsteps, low atmospheric drone gradually increasing, subtle heartbeat like bass during the final ten seconds, abrupt silence on the cut to black. Avoid: horror gore, aggressive monster behavior, exaggerated facial expressions, bright saturated colors, fantasy magic effects, warped architecture, deformed hands, extra limbs, unstable character appearance, excessive camera shake, fast action, cartoon styling, text, logos, dialogue.

Audio scene

15-SECOND CINEMATIC EMOTIONAL GYM SCENE — 16:9 Use image as the sole face/identity reference. Preserve her exact facial structure, eyes, nose, lips, jawline, hairline, long wavy black hair, and skin tone. Adult fictional woman. Neutral fitted athletic tank top and leggings, no logos. 0–3s: Static 85mm upper-body close-up, mid-chest up. She runs steadily on a treadmill with earbuds, controlled breathing, focused neutral expression, light sweat. 3–5s: Her stride subtly falters. She stares blankly ahead as tension builds around her eyes and brows. Her breathing becomes uneven and catches in her throat. 5–10s: Tears rapidly fill both eyes and roll down her cheeks, mixing with sweat. Her eyes and nose redden, chin trembles, brows tighten. She keeps running while gripping the rails. A quiet muffled sob escapes between heavy breaths. 10–15s: Her restraint breaks. She slows slightly but keeps running. A sharp gasp leads into a loud, raw, uncontrollable cry. Her jaw and lower lip shake; tears flood her face; eyes squeeze shut then reopen. Her shoulders, chest, and throat visibly jerk with each sob. One hand grips the rail tighter. She never wipes her tears, covers her face, or stops. Hold on the raw breakdown through the final frame. Camera: Locked-off upper-body close-up, 85mm portrait look, shallow DOF, sharp face/eyes, soft gym bokeh. No zoom, dolly, cuts, or camera shake. Setting: Quiet nearly empty gym at night, treadmills/equipment blurred behind her, city lights through windows. Cool fluorescent light mixed with warm city glow, natural skin, realistic sweat and tears, subtle film grain. Audio: Treadmill hum, footsteps, heavy breathing, distant gym ambience, muffled sobs, sharp gasps, loud broken crying, subtle ambient music. No dialogue. Avoid: Falling, stumbling, malfunction, comedy, silent crying, restrained breakdown, face covering/wiping tears, eye contact with camera, beauty filters, face morphing, wardrobe changes, extra people, text, logos, watermarks.

Is this model right for you?

Published documentation is available, but safe generation support must be completed before inputs can be accepted.

What it does best
This information page covers Gemini 3.8 Flash TTS, a model from Google.
Who it is for
Useful for tracking availability or choosing a model for a task you need to finish now.
Why use it on Kyeo AI
Input, output usage and billing checks must be complete before requests can spend credits.
Interface documentation is published.The generation entry is paused.Available alternatives are linked below.
Gemini 3.8 Flash TTS availabilityGemini 3.8 Flash TTS alternativesGemini 3.8 Flash TTS generation statusGemini 3.8 Flash TTS requirements

What to know first

New generation requests are not accepted.
Input and attachment controls are closed.
No reopening date has been promised.

Related models

Still deciding? Take a quick look at these similar alternatives.

ElevenLabs Dialogue V3

ElevenLabs Dialogue V3 provides line-by-line dialogue generation: enter each turn, choose a voice, and pay by total dialogue length. It is not a real-time voice agent, and ElevenLabs notes that users may need multiple generations to find a usable result. Start with a sample to check speaker changes, audio tags, language code, output format, and long-script completeness.

View details

ElevenLabs Turbo 2.5

ElevenLabs Turbo 2.5 is a retained single-speaker TTS workflow on Kyeo AI. It exposes a voice choice plus stability, similarity boost, style, speed, timestamps, surrounding text, and language code. The workflow remains selectable, but ElevenLabs now recommends Flash v2.5 instead. The Turbo name does not make low latency, language support, timestamp accuracy, voice authorization, or output quality a Kyeo guarantee.

View details

Suno Sounds

Suno Sounds is Kyeo AI's text-to-sound entry. Choose V6 / V6_MINI / V6_WILD, request a one-shot or loop-oriented result, and optionally set 1–300 BPM and a key. Features described for Suno's official beta product, sample counts, and subscription rights do not automatically apply to results generated on Kyeo.

View details

Frequently asked questions

Sources

Gemini 3.8 Flash TTS has published interface documentation. Generation is currently unavailable on Kyeo AI.

Model status review
Integration

This review confirms documentation availability and the paused calling state on this site.