Creator
$19/month
Billed monthly
For solo creators posting every week
500 credits every month
- Up to 250 AI images
- Up to 50 AI videos
- Up to 1.5 hours of AI voiceover
- Roll over up to 1,000 credits
ElevenLabs voice generator
Five Eleven models, one line.
Sceneform runs five Eleven speech models in its Audio tool, with 49 voices or your own. Below, Sophie reads the same line on each one.
Make an ElevenLabs voiceoverPlans from $19 a month
Eleven v4 · Sophie, American, middle-aged, audiobook
The last ferry leaves at nine. Miss it, and the island keeps you until morning. Honestly? There are worse places to be stuck.
Eleven v4
Expressive, natural reads in the most languages.
8.2 s
Eleven v4 Turbo
Eleven v4's sound, faster and for less.
8.3 s
Eleven v3
Emotion you steer with tags in the script.
8.2 s
Eleven Multilingual v2
Steady narration that holds over long scripts.
7.7 s
Eleven Flash v2.5
The fastest speech at the lowest cost.
7.9 s
Sceneform or elevenlabs.io.What each one gives you.
elevenlabs.io is ElevenLabs' own app. It has a free plan, a cheaper first plan and tools Sceneform doesn't have. Sceneform puts five Eleven speech models next to its video, image and lip sync tools, on one plan.
Sceneformelevenlabs.io
- Cheapest monthly plan
- $19 a month, about 1.5 hours of voiceover
- $6 a month (Starter), about 30 minutes of speech
- Eleven speech models
- Eleven v4, v4 Turbo, v3, Multilingual v2 and Flash v2.5
- Eleven v4 and v3 on every plan, limited on Free
- Music, sound effects, voice changer
- Yes, as tabs in the Audio tool
- Yes
- Dubbing, speech to text, voice isolator
- No
- Yes
elevenlabs.io figures are from its pricing page with monthly billing, read 5 November 2026.
Which Eleven model?Pick by the job, not the version number.
All five read the 49 library voices and any voice you make. Leave Language on Auto and they follow your script.
| Model and its job | Languages | Script | Audio tags | Dialogue | Controls |
|---|---|---|---|---|---|
| Eleven v4Ads, social posts and narration | 85 | 10,000 characters | Yes | Yes | Stability, Similarity |
| Eleven v4 TurboDrafts and long batches | 85 | 10,000 characters | Yes | No | Stability, Similarity |
| Eleven v3Characters and acted scenes | 74 | 5,000 characters | Yes | Yes | Stability, Similarity, Speed |
| Eleven Multilingual v2Audiobooks, courses and explainers | 29 | 5,000 characters | No | No | Stability, Similarity, Style, Speed, Speaker boost |
| Eleven Flash v2.5Quick tests and high volume | 32 | 5,000 characters | No | No | Stability, Similarity, Speed |
Eleven v4
Ads, social posts and narration
- Languages
- 85
- Script
- 10,000 characters
- Audio tags
- Yes
- Dialogue
- Yes
- Controls
- Stability, Similarity
Eleven v4 Turbo
Drafts and long batches
- Languages
- 85
- Script
- 10,000 characters
- Audio tags
- Yes
- Dialogue
- No
- Controls
- Stability, Similarity
Eleven v3
Characters and acted scenes
- Languages
- 74
- Script
- 5,000 characters
- Audio tags
- Yes
- Dialogue
- Yes
- Controls
- Stability, Similarity, Speed
Eleven Multilingual v2
Audiobooks, courses and explainers
- Languages
- 29
- Script
- 5,000 characters
- Audio tags
- No
- Dialogue
- No
- Controls
- Stability, Similarity, Style, Speed, Speaker boost
Eleven Flash v2.5
Quick tests and high volume
- Languages
- 32
- Script
- 5,000 characters
- Audio tags
- No
- Dialogue
- No
- Controls
- Stability, Similarity, Speed
49 voices.Each one speaks on all five models.
The voice picker sorts them into six groups. Every group has at least one voice to play here. In Audio you can play each voice before you pick it.
Ads7
AlexanderAmerican, middle-aged
BenjaminBritish, middle-aged
CharlotteBritish, middle-aged
NexusAmerican, middle-aged
RoccoAmerican, middle-aged
EpicAmerican, middle-aged
ThunderAmerican, middle-aged
Social6
ZoeAmerican, young
JackAustralian, young
NoahAmerican, young
ChloeAmerican, young
SummerAmerican, young
PriyaIndian, young
Narration16
VictoriaAmerican, young
WilliamBritish, middle-aged
EleanorBritish, middle-aged
SophieAmerican, middle-aged
MichaelAmerican, middle-aged
ArthurAmerican, old
SebastianAmerican, middle-aged
MargaretBritish, old
LunaAmerican, young
EdmundBritish, middle-aged
ChesterAmerican, old
GraceBritish, middle-aged
RobertAmerican, middle-aged
ReginaldBritish, old
MaverickAmerican, middle-aged
BuckAmerican, old
Conversational9
SageAmerican, middle-aged
JakeAmerican, young
MatthewAmerican, middle-aged
RyanAmerican, middle-aged
HarperAmerican, middle-aged
EmmaAmerican, young
DavidAmerican, middle-aged
SophiaAmerican, young
RosieBritish, middle-aged
Characters9
DylanAmerican, middle-aged
RexAmerican, young
TexSouthern US, middle-aged
NigelBritish, young
CruellaAmerican, middle-aged
LilyAmerican, young
VortexAmerican, middle-aged
OracleAmerican, old
WilfredBritish, old
Calm2
DollySouthern US, middle-aged
MidnightAmerican, young
Need a voice that isn't here? Record a minute of yourself, upload a clip, or describe one in words. It works on all five models. How voice cloning works
More than speech.Music, sound effects and voice changes too.
Audio has four tabs, and each one runs an Eleven model. Here is one harbor scene with a track from each. The music and the sound came from the exact prompts shown.
VoiceoverEleven v4
The last ferry leaves at nine. Miss it, and the island keeps you until morning. Honestly? There are worse places to be stuck.
0:08Sophie
MusicEleven Music v2.5
Gentle acoustic folk instrumental for a travel video about a small island: fingerpicked guitar, soft brushed drums, light accordion, warm and unhurried, about 90 BPM. Steady and quiet enough for a voiceover to sit on top.
0:3030 seconds, instrumental
Sound effectsEleven Sound Effects
A ferry horn sounds twice across a quiet evening harbor, gulls calling in the distance, small waves lapping against a wooden pier.
0:1010 seconds
Voice changeEleven Voice Changer
The voiceover above, spoken again in William's voice. Every pause lands where Sophie put it.
0:08William
How to use ElevenLabs in Sceneform.Three steps in the Audio tool.
- 1
Open Audio and pick an Eleven model
In the Voiceover tab, choose Eleven v4, v4 Turbo, v3, Multilingual v2 or Flash v2.5 from the model menu.
- 2
Paste the script and pick a voice
Play any library voice before you choose it, or pick one you made. On v4, v4 Turbo and v3, type a bracket to add a tag like [whispers].
- 3
Generate, listen, download
Play the read in your history. Change a word and generate again, or download the MP3.
Simple pricing that scales with you.
Pick the plan for how much you post. Every model on every plan. Unused credits roll over. Cancel anytime.
Pro
Most popular$49/month
Billed monthly
For creators posting daily across channels
1,300 credits every month
- Up to 650 AI images
- Up to 130 AI videos
- Up to 4 hours of AI voiceover
- Roll over up to 2,600 credits
Studio
$99/month
Billed monthly
For brands and production teams
2,700 credits every month
- Up to 1,350 AI images
- Up to 270 AI videos
- Up to 9 hours of AI voiceover
- Roll over up to 5,400 credits
Scale
$199/month
Billed monthly
For agencies running always-on content
5,500 credits every month
- Up to 2,750 AI images
- Up to 550 AI videos
- Up to 18 hours of AI voiceover
- Roll over up to 11,000 credits
Every plan includesEvery model, 90+ and countingReusable AI personasSceneform Studio editorCommercial usage rights
Want checkout, comparison tables, or a custom volume? See the full pricing page
ElevenLabs voice generator FAQ
ElevenLabs' own app at elevenlabs.io has a free plan: about 10 minutes of speech a month, with no commercial license. In Sceneform, plans start at $19 a month. That plan covers about 1.5 hours of voiceover. Per 1,000 characters, Eleven v4, Eleven v3 and Eleven Multilingual v2 cost 4 credits; Eleven v4 Turbo and Eleven Flash v2.5 cost 3 credits. You can play every read on this page without an account.
No. This is Sceneform, a separate app from elevenlabs.io. Sceneform runs the Eleven models for you. Sign in, open Audio, and generate. There is no key to paste and no second subscription.
Five speech models: Eleven v4, Eleven v4 Turbo, Eleven v3, Eleven Multilingual v2 and Eleven Flash v2.5. Audio also has Eleven Music v2.5 for songs and instrumentals, Eleven Sound Effects, and Eleven Voice Changer.
Start with Eleven v4. Use v4 Turbo when you need many takes fast. Use v3 when you want to act out emotion with tags. Use Multilingual v2 for long, even narration, and Flash v2.5 when speed and cost matter most.
49 library voices, sorted into Ads, Social, Narration, Conversational, Characters and Calm. Every one works on all five speech models. You can play each voice before you pick it.
Yes. Record yourself for about a minute, upload a clip of at least 10 seconds, or describe a voice and keep one of three designs. A voice you make works on all five Eleven speech models.
It depends on the model: Eleven v4 85, Eleven v4 Turbo 85, Eleven v3 74, Eleven Multilingual v2 29, Eleven Flash v2.5 32. Leave Language on Auto and the model follows your script.
On Eleven v4, Eleven v4 Turbo and Eleven v3, write a tag in square brackets, such as [laughs] or [long pause]. The voice acts it out and doesn't read it. Eleven v4 and Eleven v3 also read a dialogue with up to 10 voices in one file.
Up to 10,000 characters in one generation on Eleven v4 and Eleven v4 Turbo, and 5,000 on the others.
Yes. Every paid plan includes commercial use. Download the MP3, or use it in Sceneform's video tools.
