ElevenLabs model product
Eleven
Most expressive AI text-to-speech model with high emotional range and contextual understanding.
Updated Aug 17, 2026. Default version: Eleven v3
LLMBoard Text-to-Speech Score55.7Eleven v3
Coverage35%2 benchmark families
Context windowN/ATokens
Native catalog price$30 / 1M characters1M characters
Eleven Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Eleven Benchmark Results
Benchmark scores for Eleven v3.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkArtificial Analysis Text To Speech | Score1,177 Elo | Rank10 | Participants93 | PercentileN/A | EvidenceA | Evaluated |
| BenchmarkTTS Arena V2 | Score1,508 Elo | Rank29 | Participants31 | PercentileN/A | EvidenceA | Evaluated |
Eleven Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Eleven Pricing
Prices are shown in the model's native media unit and resolution tier.
- Native price
- $30 / 1M characters
- Price unit
- 1M characters
- Tier
- Standard
- Tracked offerings
- 1
Sort by
Provider | Provider model ID | Region | Native price | Unit | Tier | Updated |
|---|
| ProviderElevenlabs | Provider model IDeleven_v3 | Regionglobal | Native price$30 / 1M characters | Unit1M characters | TierN/A | Updated |
Media catalog prices are not converted into token input or output prices.
Eleven Runtime Performance
Provider-specific output speed and catalog latency for Eleven v3. Runtime does not affect the capability score.
No runtime data
Browse runtime rankingsNo provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Eleven Specifications
Technical details for the model's default version.
- Version
- Eleven v3
- Released
- Unknown
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- N/A
- Max output
- N/A
- Inputs
- text
- Outputs
- audio
- Open weights
- No
- License
- Unspecified
Eleven Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionEleven v3 | ReleasedN/A | LLMBoard55.7 | ParametersN/A | ContextN/A | Max outputN/A | Open weightsNo | LicenseUnspecified |
Eleven vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Eleven
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
EL
Eleven Turbo
ElevenLabs
EL
Multilingual
ElevenLabs
EL
Eleven Flash
ElevenLabs
OP
TTS 1 HD
OpenAI
What is Eleven?
Key information about Eleven and its available data.
Most expressive AI text-to-speech model with high emotional range and contextual understanding. Supports 70+ languages, 3K character limit. Best for audiobooks and emotional dialogue.
Data as of 2026-08-17.
FAQ
Common questions about Eleven.
When was Eleven released?
A release date is not available for the default version.
How much does Eleven cost?
Eleven's current catalog price is $30 / 1M characters.
Who created Eleven?
Eleven was created by ElevenLabs.
What is the context window for Eleven?
A context window is not available for the default version.
Is Eleven open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Eleven?
1 provider offerings are linked to the default version.
What models should I compare Eleven with?
Nearby ranked alternatives include Step Audio EditX (Mar 2026), TTS 1 HD, Eleven Turbo.