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$0.106 per 1,000 characters
ElevenLabs' V3 text-to-speech model with emotional control and 70+ languages. Describe the tone and Craze generates natural-sounding narration from your script.
Craze runs ElevenLabs V3 when you ask for it by name.
The voice library includes voices in different ages, accents, and speaking styles.
Voices don't have to be flat and robotic.
Language switching is immediate and automatic.
ElevenLabs V3 handles natural pauses, emphasis, and phrasing.
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 V3ElevenLabs | ElevenLabs v4ElevenLabs | Gemini 3.8 Flash TTSGoogle DeepMind | Gemini 3.8 Flash Lite TTSGoogle DeepMind | |
|---|---|---|---|---|
| Makes | Text to audio | Text to audio | Text to audio | Text to audio |
| From | $0.106 per 1,000 characters | $0.085 per 1,000 characters | $0.032 per 1,000 characters | $0.022 per 1,000 characters |
| 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 V3 is a text-to-speech model that generates natural-sounding narration from scripts. With emotional control, 70+ languages, and over 10,000 voices in different styles and accents, you can add professional-quality voiceover to video without hiring talent or recording in a studio.
Narration is often the most time-consuming part of video production. Finding talent, recording, engineering, and revising can take weeks. ElevenLabs V3 generates natural-sounding voice in seconds, ready to layer with music and effects. The model handles everything from technical exposition to emotional storytelling.
The voice library includes voices in different ages, accents, and speaking styles. Browse native English speakers, Spanish narrators, Japanese voices, and accents from every region. Preview any voice before committing. Whether you need a friendly guide, a professional narrator, or a character voice, the library has options.
Voices don't have to be flat and robotic. Use audio tags to specify emotion, pace, and tone. "Excited and energetic" sounds different from "contemplative and slow." The model adjusts delivery to match the emotion you specify. This is especially useful for documentaries or educational content where tone shifts the meaning of information.
Language switching is immediate and automatic. Write a script in English, Japanese, and Mandarin, and ElevenLabs V3 generates each section with native pronunciation and pacing. International creators can build content for global audiences without hiring multilingual talent.
ElevenLabs V3 handles natural pauses, emphasis, and phrasing. Sentences land with intention. Comma placement creates breath. Punctuation shapes the delivery. The result sounds like a human read it, not a machine. Complex scripts, dialogue, and emotional narration all land with authenticity.
Craze now narrates with ElevenLabs v4 by default, which reads the same voices for less. V3 stays available when you ask for it by name, for example to match narration you already made with it.
ElevenLabs V3 is designed to sound natural from the start. Most scripts generate on the first pass, ready to use immediately. If a take doesn't land, regenerating with a different voice or emotional tag is quick enough that you can experiment without workflow friction.
Narration is billed $0.106 per 1,000 characters, based on the length of your script. A 30-second script costs less than a 5-minute documentary voiceover. Use the cost calculator on this page for exact estimates before you generate.
Narration adds context, emotion, and guide to every scene. ElevenLabs V3 generates voiceover that sounds professional and natural, without hiring talent or renting studio time.
Documentaries and educational videos rely on clear, expressive narration. Generate voices in multiple languages for international audiences.
Video essays, tutorials, and commentary need voiceover. ElevenLabs V3 generates narration on-brand with your content, with voices that sound like real people.
Game dialogue, NPC voices, and narrator tracks all start with narration. Generate character voices that match your vision, in any language.
Audiobooks need multiple character voices and a strong narrator. Combine ElevenLabs V3 with Voice Design to create distinct character voices from description.
ElevenLabs V3 is text-to-speech, generating narration from scripts using existing voices. Voice Design V3 creates custom voices from description, then you use those voices for narration. Use ElevenLabs V3 to generate narration immediately with the voice library. Use Voice Design V3 when you need a specific character voice that doesn't exist in the library.
Describe what you want the way you would brief an editor, and Craze writes the ElevenLabs V3 prompts for you. Every Craze plan, including Free, runs ElevenLabs V3 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 $0.106 per 1,000 characters, with top-ups when you need more.
Video producers and filmmakers: Narration adds context, emotion, and guide to every scene. Documentary and educational creators: Documentaries and educational videos rely on clear, expressive narration. YouTubers and content creators: Video essays, tutorials, and commentary need voiceover. Game developers and interactive media: Game dialogue, NPC voices, and narrator tracks all start with narration.
ElevenLabs V3 is a text-to-speech model that generates natural-sounding voices from scripts. It supports emotional control, 70+ languages, and over 10,000 voices in different styles and accents.
Craze now narrates with ElevenLabs v4 by default. Ask for ElevenLabs V3 by name to use it: write or paste your script, pick a voice or let Craze suggest one, and specify the emotional tone.
ElevenLabs V3 includes over 10,000 voices, with native accents, ages, and speaking styles. You can browse the voice library, preview voices, or use Voice Design to create a custom voice from description.
ElevenLabs V3 supports 70+ languages, with natural pronunciation and accent support. The model handles language switching within the same script.
Yes. ElevenLabs V3 supports audio tags for emotional control. Specify the emotion, pace, and tone in your prompt, and the model adjusts the delivery accordingly.
ElevenLabs V3 is billed $0.106 per 1,000 characters, based on the length of your script in characters. Use the cost calculator on this page for exact estimates of your narration cost.
ElevenLabs V3 is available on every Craze plan, including Free.
ElevenLabs released V3 to general availability on March 14, 2026, after an initial alpha release in June 2025. V3 brought improved expressiveness, audio tags for emotional control, and support for 70+ languages.
