AI models on Craze
Every video, image, voice, music and sound model Craze can direct, with what each one makes and what it costs.
Every video, image, voice, music and sound model Craze can direct, with what each one makes and what it costs.
Starts at$0.022 per 1,000 characters
The lighter, lower-cost Gemini 3.8 speech model. Describe the voice in plain words and Craze narrates your video with it, for quick lines and drafts.
Describe the speaker: their character, age, accent, mood and pace.
Scratch narration, placeholder voice-over and quick lines add up across a project.
Craze creatively jams, researches and plans with you.
Craze generates anything imaginable. Video, audio, music, motion graphics and more.
Craze watches your footage and builds a final cut. With a real editor if you need it.
Every model here runs on every Craze plan, including Free, and Craze can use a different one for each shot.
| Gemini 3.8 Flash Lite TTSGoogle DeepMind | ElevenLabs v4ElevenLabs | Gemini 3.8 Flash TTSGoogle DeepMind | ElevenLabs Voice ChangerElevenLabs | |
|---|---|---|---|---|
| Makes | Text to audio | Text to audio | Text to audio | Audio to audio |
| From | $0.022 per 1,000 characters | $0.085 per 1,000 characters | $0.032 per 1,000 characters | $0.316 per minute of audio |
| Task | Inputs | Resolution | Aspect ratios | Sound |
|---|---|---|---|---|
| Text to speech | Text prompt | Follows the source | Follows the input | None |
$0/ month
$19/ month
$59/ month
$199/ month
Gemini 3.8 Flash Lite TTS is the lower-cost member of Google's Gemini 3.8 speech models. It reads your script in one of 30 voices, shaped by a plain-words direction of how the voice should sound.
Describe the speaker: their character, age, accent, mood and pace. The direction steers the performance without being read aloud, the same way it does on Gemini 3.8 Flash TTS.
Scratch narration, placeholder voice-over and quick lines add up across a project. Flash Lite keeps that work cheap, and you can move the final take to Flash TTS with the same voice and direction.
Pricing starts at $0.022 per 1,000 characters. The cost follows the length of the script. Use the calculator on this page to estimate the cost before you generate.
This model is available on every Craze plan, including Free.
Gemini 3.8 Flash TTS takes the same voices and directions and is the one to use for finished narration. Seed Speech is another low-cost option with bilingual voices. ElevenLabs v4 is Craze's default narrator.
On Craze, a script can run to 8,000 characters per generation. The model returns voice only; music and effects come from other tracks or generations. A voice direction applies to one generation, so keep the same voice and direction to reuse a sound.
Describe what you want the way you would brief an editor, and Craze writes the Gemini 3.8 Flash Lite TTS prompts for you. Every Craze plan, including Free, runs Gemini 3.8 Flash Lite TTS and every other media model, and Craze can use a different one for each job. Each voiceover lands on the timeline under your cut, and exports with the video or on its own as MP3. Generations come out of your plan's monthly credits, from $0.022 per 1,000 characters, with top-ups when you need more.
Gemini 3.8 Flash Lite TTS is the lighter of Google DeepMind's two Gemini 3.8 speech models. It takes the same 30 voices and plain-word voice directions as Gemini 3.8 Flash TTS, at a lower price.
You pay $0.022 per 1,000 characters. The cost calculator on this page estimates the total before you generate.
every Craze plan, including Free.
Yes. Add a voice direction to your script describing the character, accent, tone and pacing you want. It steers the read and is never spoken aloud.
Use Flash Lite for drafts, scratch narration and short lines where cost matters most. Switch to Gemini 3.8 Flash TTS for the take you plan to keep.
Name Gemini 3.8 Flash Lite TTS in chat with your script and how the voice should sound, or pick it in the Models panel, choose a voice, add a voice direction and generate.
