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$0.085 per 1,000 characters
ElevenLabs' most expressive text-to-speech model, and Craze's default narrator. Paste a script, cast a voice, and get narration in 90+ languages that keeps its character across long reads.
v4 covers more than 90 languages, up from 70+ on V3.
Audio tags like [excited], [whispers], [laughs] and [pause] go straight into the script, and v4 performs them.
Long narration used to drift: a voice could sound slightly different by the end of a ten-minute read.
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.
| ElevenLabs v4ElevenLabs | Gemini 3.8 Flash TTSGoogle DeepMind | Gemini 3.8 Flash Lite TTSGoogle DeepMind | ElevenLabs Voice ChangerElevenLabs | |
|---|---|---|---|---|
| Makes | Text to audio | Text to audio | Text to audio | Audio to audio |
| From | $0.085 per 1,000 characters | $0.032 per 1,000 characters | $0.022 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
ElevenLabs v4 is ElevenLabs' newest text-to-speech model, and the voice Craze narrates with by default. It turns a script into a performed read in more than 90 languages, follows audio tags you write inline, and keeps a voice sounding like itself from the first line of a long script to the last.
v4 replaced ElevenLabs V3 as Craze's default because it is better and cheaper. It reads the same catalog voices and your designed voices, takes the same delivery settings, and costs less per character.
v4 covers more than 90 languages, up from 70+ on V3. ElevenLabs reports the biggest gains in Japanese, Brazilian Portuguese, Mandarin and Cantonese, which helps when one video ships in several markets.
Audio tags like [excited], [whispers], [laughs] and [pause] go straight into the script, and v4 performs them. You can combine more than one tag on a line when a beat needs it, though one or two per beat still reads most naturally.
Long narration used to drift: a voice could sound slightly different by the end of a ten-minute read. v4 holds a voice's identity over longer passages, so a documentary or tutorial sounds like one narrator throughout.
Narration is billed $0.085 per 1,000 characters, based on the length of your script. Use the cost calculator on this page to estimate a script before you generate.
Clear, steady narration that holds up over several minutes and several languages.
Expressive reads with pauses and emphasis placed where the story needs them.
Energetic delivery with tags like [excited] and [laughs] for a fast hook.
ElevenLabs v4 Turbo reads the same voices and tags at half the price, and is tuned for low latency in real-time voice agents. Use v4 for finished narration, and Turbo for drafts or when cost matters more than the finest read.
Describe what you want the way you would brief an editor, and Craze writes the ElevenLabs v4 prompts for you. Every Craze plan, including Free, runs ElevenLabs v4 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 $0.085 per 1,000 characters, with top-ups when you need more.
Explainers, tutorials and product videos: Clear, steady narration that holds up over several minutes and several languages. Documentaries and storytelling: Expressive reads with pauses and emphasis placed where the story needs them. Social ads and short-form video: Energetic delivery with tags like [excited] and [laughs] for a fast hook.
ElevenLabs v4 is ElevenLabs' newest text-to-speech model and its most expressive one. It reads scripts in more than 90 languages, follows inline audio tags, and holds a voice's identity steadily across long passages.
Yes. When you ask Craze for a voiceover, it narrates with ElevenLabs v4 unless you name another text-to-speech model.
v4 reads the same voices as V3 and takes the same delivery settings, but covers 90+ languages instead of 70+, lets you stack several audio tags on one line, and keeps a voice consistent over longer scripts. On Craze it also costs less per character.
Yes. Put audio tags such as [excited], [whispers] or [pause] inline in the script, and choose an expressive, natural or steady delivery. v4 can combine several tags on the same line.
Yes. Voices you design in Craze with Voice Design work with v4, as do the voices in the Craze voice catalog.
ElevenLabs v4 is billed $0.085 per 1,000 characters, based on the length of your script in characters. Use the cost calculator on this page for an exact estimate.
ElevenLabs v4 is available on every Craze plan, including Free.
ElevenLabs released v4 and v4 Turbo on September 28, 2026.
