ElevenLabsAudio modelActive
Eleven v3
PopularityRank 283 of 876
39out of 100same as last month
Summary
Eleven v3 is ElevenLabs’ expressive text-to-speech model for multilingual, multi-speaker output. The provider documents more than 70 languages, a 5,000-character text limit, and a Text to Dialogue API for conversations with multiple voices. Its value lies in emotional range and contextual delivery, not general audio reasoning.
ElevenLabs now describes v3 as a previous-generation synthesis model and lists Eleven v4 and Eleven v4 Turbo as newer speech-synthesis models. The separate Eleven v3 Conversational profile uses a Text to Dialogue WebSocket for real-time speech synthesis. The models therefore differ in transport and real-time behavior despite sharing the v3 label.
All benchmark results
Every published result with its source, test setup and comparison models.
Show all 125 published benchmark results
Page 1 of 11
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
Qwen-Audio-3.0-TTS paper Table 4: ElevenLabs-v3, CV3-Eval multilingual voice-cloning subset, Chinese (zh), CER (Show measurement, test conditions, and source)
- Source value
- 4.46
- Score
- 4.46
- Metric
- character error rate (CER) on CV3-Eval multilingual voice cloning, Chinese (zh)
- Unit
- %
- Benchmark version
- arXiv:2607.23938v1, published 2026-07-27; evaluation date not stated
- Category
- audio
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- Qwen-Audio-3.0-TTS paper, Alibaba Token Foundry
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Vendor-reported result. Exact ElevenLabs-v3 public-API result (API model eleven_v3); CV3-Eval multilingual voice-cloning subset, Chinese (zh), CER. The paper gives no per-row evaluated sample count or confidence interval.
- Context
- This preprint is authored by Alibaba Token Foundry, a competing speech-generation provider. Treat its comparative scores as vendor-reported, not an independent third-party evaluation. They apply only to the exact model named in this row; MiniMax-Speech-2.8-HD results do not establish Speech 2.8 Turbo performance.
Qwen-Audio-3.0-TTS paper Table 4: ElevenLabs-v3, CV3-Eval multilingual voice-cloning subset, English (en), WER (Show measurement, test conditions, and source)
- Source value
- 3.61
- Score
- 3.61
- Metric
- word error rate (WER) on CV3-Eval multilingual voice cloning, English (en)
- Unit
- %
- Benchmark version
- arXiv:2607.23938v1, published 2026-07-27; evaluation date not stated
- Category
- audio
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- Qwen-Audio-3.0-TTS paper, Alibaba Token Foundry
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Vendor-reported result. Exact ElevenLabs-v3 public-API result (API model eleven_v3); CV3-Eval multilingual voice-cloning subset, English (en), WER. The paper gives no per-row evaluated sample count or confidence interval.
- Context
- This preprint is authored by Alibaba Token Foundry, a competing speech-generation provider. Treat its comparative scores as vendor-reported, not an independent third-party evaluation. They apply only to the exact model named in this row; MiniMax-Speech-2.8-HD results do not establish Speech 2.8 Turbo performance.
Qwen-Audio-3.0-TTS paper Table 4: ElevenLabs-v3, CV3-Eval multilingual voice-cloning subset, Japanese (ja), CER (Show measurement, test conditions, and source)
- Source value
- 5.71
- Score
- 5.71
- Metric
- character error rate (CER) on CV3-Eval multilingual voice cloning, Japanese (ja)
- Unit
- %
- Benchmark version
- arXiv:2607.23938v1, published 2026-07-27; evaluation date not stated
- Category
- audio
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- Qwen-Audio-3.0-TTS paper, Alibaba Token Foundry
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Vendor-reported result. Exact ElevenLabs-v3 public-API result (API model eleven_v3); CV3-Eval multilingual voice-cloning subset, Japanese (ja), CER. The paper gives no per-row evaluated sample count or confidence interval.
- Context
- This preprint is authored by Alibaba Token Foundry, a competing speech-generation provider. Treat its comparative scores as vendor-reported, not an independent third-party evaluation. They apply only to the exact model named in this row; MiniMax-Speech-2.8-HD results do not establish Speech 2.8 Turbo performance.
Qwen-Audio-3.0-TTS paper Table 4: ElevenLabs-v3, CV3-Eval multilingual voice-cloning subset, Korean (ko), CER (Show measurement, test conditions, and source)
- Source value
- 5.46
- Score
- 5.46
- Metric
- character error rate (CER) on CV3-Eval multilingual voice cloning, Korean (ko)
- Unit
- %
- Benchmark version
- arXiv:2607.23938v1, published 2026-07-27; evaluation date not stated
- Category
- audio
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- Qwen-Audio-3.0-TTS paper, Alibaba Token Foundry
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Vendor-reported result. Exact ElevenLabs-v3 public-API result (API model eleven_v3); CV3-Eval multilingual voice-cloning subset, Korean (ko), CER. The paper gives no per-row evaluated sample count or confidence interval.
- Context
- This preprint is authored by Alibaba Token Foundry, a competing speech-generation provider. Treat its comparative scores as vendor-reported, not an independent third-party evaluation. They apply only to the exact model named in this row; MiniMax-Speech-2.8-HD results do not establish Speech 2.8 Turbo performance.
Qwen-Audio-3.0-TTS paper Table 4: ElevenLabs-v3, CV3-Eval multilingual voice-cloning subset, German (de), WER (Show measurement, test conditions, and source)
- Source value
- 3.64
- Score
- 3.64
- Metric
- word error rate (WER) on CV3-Eval multilingual voice cloning, German (de)
- Unit
- %
- Benchmark version
- arXiv:2607.23938v1, published 2026-07-27; evaluation date not stated
- Category
- audio
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- Qwen-Audio-3.0-TTS paper, Alibaba Token Foundry
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Vendor-reported result. Exact ElevenLabs-v3 public-API result (API model eleven_v3); CV3-Eval multilingual voice-cloning subset, German (de), WER. The paper gives no per-row evaluated sample count or confidence interval.
- Context
- This preprint is authored by Alibaba Token Foundry, a competing speech-generation provider. Treat its comparative scores as vendor-reported, not an independent third-party evaluation. They apply only to the exact model named in this row; MiniMax-Speech-2.8-HD results do not establish Speech 2.8 Turbo performance.
Qwen-Audio-3.0-TTS paper Table 4: ElevenLabs-v3, CV3-Eval multilingual voice-cloning subset, Spanish (es), WER (Show measurement, test conditions, and source)
- Source value
- 3.92
- Score
- 3.92
- Metric
- word error rate (WER) on CV3-Eval multilingual voice cloning, Spanish (es)
- Unit
- %
- Benchmark version
- arXiv:2607.23938v1, published 2026-07-27; evaluation date not stated
- Category
- audio
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- Qwen-Audio-3.0-TTS paper, Alibaba Token Foundry
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Vendor-reported result. Exact ElevenLabs-v3 public-API result (API model eleven_v3); CV3-Eval multilingual voice-cloning subset, Spanish (es), WER. The paper gives no per-row evaluated sample count or confidence interval.
- Context
- This preprint is authored by Alibaba Token Foundry, a competing speech-generation provider. Treat its comparative scores as vendor-reported, not an independent third-party evaluation. They apply only to the exact model named in this row; MiniMax-Speech-2.8-HD results do not establish Speech 2.8 Turbo performance.
Qwen-Audio-3.0-TTS paper Table 4: ElevenLabs-v3, CV3-Eval multilingual voice-cloning subset, French (fr), WER (Show measurement, test conditions, and source)
- Source value
- 9.31
- Score
- 9.31
- Metric
- word error rate (WER) on CV3-Eval multilingual voice cloning, French (fr)
- Unit
- %
- Benchmark version
- arXiv:2607.23938v1, published 2026-07-27; evaluation date not stated
- Category
- audio
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- Qwen-Audio-3.0-TTS paper, Alibaba Token Foundry
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Vendor-reported result. Exact ElevenLabs-v3 public-API result (API model eleven_v3); CV3-Eval multilingual voice-cloning subset, French (fr), WER. The paper gives no per-row evaluated sample count or confidence interval.
- Context
- This preprint is authored by Alibaba Token Foundry, a competing speech-generation provider. Treat its comparative scores as vendor-reported, not an independent third-party evaluation. They apply only to the exact model named in this row; MiniMax-Speech-2.8-HD results do not establish Speech 2.8 Turbo performance.
Qwen-Audio-3.0-TTS paper Table 4: ElevenLabs-v3, CV3-Eval multilingual voice-cloning subset, Italian (it), WER (Show measurement, test conditions, and source)
- Source value
- 4.68
- Score
- 4.68
- Metric
- word error rate (WER) on CV3-Eval multilingual voice cloning, Italian (it)
- Unit
- %
- Benchmark version
- arXiv:2607.23938v1, published 2026-07-27; evaluation date not stated
- Category
- audio
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- Qwen-Audio-3.0-TTS paper, Alibaba Token Foundry
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Vendor-reported result. Exact ElevenLabs-v3 public-API result (API model eleven_v3); CV3-Eval multilingual voice-cloning subset, Italian (it), WER. The paper gives no per-row evaluated sample count or confidence interval.
- Context
- This preprint is authored by Alibaba Token Foundry, a competing speech-generation provider. Treat its comparative scores as vendor-reported, not an independent third-party evaluation. They apply only to the exact model named in this row; MiniMax-Speech-2.8-HD results do not establish Speech 2.8 Turbo performance.
Qwen-Audio-3.0-TTS paper Table 4: ElevenLabs-v3, CV3-Eval multilingual voice-cloning subset, Russian (ru), WER (Show measurement, test conditions, and source)
- Source value
- 5.38
- Score
- 5.38
- Metric
- word error rate (WER) on CV3-Eval multilingual voice cloning, Russian (ru)
- Unit
- %
- Benchmark version
- arXiv:2607.23938v1, published 2026-07-27; evaluation date not stated
- Category
- audio
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- Qwen-Audio-3.0-TTS paper, Alibaba Token Foundry
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Vendor-reported result. Exact ElevenLabs-v3 public-API result (API model eleven_v3); CV3-Eval multilingual voice-cloning subset, Russian (ru), WER. The paper gives no per-row evaluated sample count or confidence interval.
- Context
- This preprint is authored by Alibaba Token Foundry, a competing speech-generation provider. Treat its comparative scores as vendor-reported, not an independent third-party evaluation. They apply only to the exact model named in this row; MiniMax-Speech-2.8-HD results do not establish Speech 2.8 Turbo performance.
Qwen-Audio-3.0-TTS paper Table 4: ElevenLabs-v3, CV3-Eval multilingual voice-cloning subset, Arabic (ar), WER (Show measurement, test conditions, and source)
- Source value
- 5.51
- Score
- 5.51
- Metric
- word error rate (WER) on CV3-Eval multilingual voice cloning, Arabic (ar)
- Unit
- %
- Benchmark version
- arXiv:2607.23938v1, published 2026-07-27; evaluation date not stated
- Category
- audio
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- Qwen-Audio-3.0-TTS paper, Alibaba Token Foundry
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Vendor-reported result. Exact ElevenLabs-v3 public-API result (API model eleven_v3); CV3-Eval multilingual voice-cloning subset, Arabic (ar), WER. The paper gives no per-row evaluated sample count or confidence interval.
- Context
- This preprint is authored by Alibaba Token Foundry, a competing speech-generation provider. Treat its comparative scores as vendor-reported, not an independent third-party evaluation. They apply only to the exact model named in this row; MiniMax-Speech-2.8-HD results do not establish Speech 2.8 Turbo performance.
Qwen-Audio-3.0-TTS paper Table 4: ElevenLabs-v3, CV3-Eval multilingual voice-cloning subset, Indonesian (id), WER (Show measurement, test conditions, and source)
- Source value
- 2.85
- Score
- 2.85
- Metric
- word error rate (WER) on CV3-Eval multilingual voice cloning, Indonesian (id)
- Unit
- %
- Benchmark version
- arXiv:2607.23938v1, published 2026-07-27; evaluation date not stated
- Category
- audio
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- Qwen-Audio-3.0-TTS paper, Alibaba Token Foundry
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Vendor-reported result. Exact ElevenLabs-v3 public-API result (API model eleven_v3); CV3-Eval multilingual voice-cloning subset, Indonesian (id), WER. The paper gives no per-row evaluated sample count or confidence interval.
- Context
- This preprint is authored by Alibaba Token Foundry, a competing speech-generation provider. Treat its comparative scores as vendor-reported, not an independent third-party evaluation. They apply only to the exact model named in this row; MiniMax-Speech-2.8-HD results do not establish Speech 2.8 Turbo performance.
Qwen-Audio-3.0-TTS paper Table 4: ElevenLabs-v3, CV3-Eval multilingual voice-cloning subset, Portuguese (pt), WER (Show measurement, test conditions, and source)
- Source value
- 2.33
- Score
- 2.33
- Metric
- word error rate (WER) on CV3-Eval multilingual voice cloning, Portuguese (pt)
- Unit
- %
- Benchmark version
- arXiv:2607.23938v1, published 2026-07-27; evaluation date not stated
- Category
- audio
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- Qwen-Audio-3.0-TTS paper, Alibaba Token Foundry
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Vendor-reported result. Exact ElevenLabs-v3 public-API result (API model eleven_v3); CV3-Eval multilingual voice-cloning subset, Portuguese (pt), WER. The paper gives no per-row evaluated sample count or confidence interval.
- Context
- This preprint is authored by Alibaba Token Foundry, a competing speech-generation provider. Treat its comparative scores as vendor-reported, not an independent third-party evaluation. They apply only to the exact model named in this row; MiniMax-Speech-2.8-HD results do not establish Speech 2.8 Turbo performance.
Page 1 of 11
Popularity compared
How often the model is searched for, used and mentioned, compared with every model of its category.
Popularity index
0 to 100, higher is more popular
20 of 83 models
As of November 2026 · Source: gradually.ai popularity index
Over time
Weekly values from October 18, 2026 to November 6, 2026
Eleven v3Maya 2 Native 40GPT-Live-Transcribe 39Scribe v2 39Sonic 3.6 39
Method changes in the timeline, a jump at these points is no market event:
- 1November 1, 2026: Value only with search or usage data, 30-day attention
What is gaining popularity right now, across models, vendors, harnesses and AI subscriptions, is collected in All AI trends.
Eleven v3 compared
- 1Eleven v3 vs. Sonic 3.611 shared tests
- 2Eleven v3 vs. Aura-24 shared tests
- 3Eleven v3 vs. Fish Audio S2 Pro3 shared tests
- 4Eleven v3 vs. Kokoro-82M1 shared test
- 5Eleven v3 vs. Gemini 3.1 Flash TTS12 shared tests
- 6Eleven v3 vs. GPT-4o Mini TTS9 shared tests
- 7Eleven v3 vs. Voxtral Mini TTS3 shared tests
- 8Eleven v3 vs. Eleven Flash v2.57 shared tests
- 9Eleven v3 vs. MAI-Voice-2.14 shared tests
Show all 19 comparisons
- 10Eleven v3 vs. Eleven v423 shared tests
- 11Eleven v3 vs. Eleven v4 Turbo4 shared tests
- 12Eleven v3 vs. MAI-Voice-2.1-Flash4 shared tests
- 13Eleven v3 vs. Fish Audio S2.1 Pro4 shared tests
- 14Eleven v3 vs. Gemini 3.8 Flash-Lite TTS9 shared tests
- 15Eleven v3 vs. Gemini 3.8 Flash TTS23 shared tests
- 16Eleven v3 vs. MAI-Voice-21 shared test
- 17Eleven v3 vs. MAI-Voice-2-Flash1 shared test
- 18Eleven v3 vs. MiniMax Speech 2.87 shared tests
- 19Eleven v3 vs. Voxtral Mini TTS 33 shared tests
Similar models
More models of the same kind as Eleven v3, chosen by model line, developer, size, price and release date.
- Scribe v2ElevenLabs · same developer
- Eleven v3 ConversationalElevenLabs · same developer
- Scribe v2 RealtimeElevenLabs · same developer
- Eleven Flash v2.5ElevenLabs · same developer
- Eleven Multilingual STS v2ElevenLabs · same developer
- Eleven Text to Sound v2ElevenLabs · same developer
- Eleven Music v2.5ElevenLabs · same developer
- Scribe v2 MedicalElevenLabs · same developer
All specifications
Architecture
Input and output
Watermarking and provenance
AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.
- AI watermarking
- Subject to limitations. ElevenLabs describes an inaudible watermark in its own generated audio and identifies SynthID, including for speech generation. Older recordings made before its introduction and third-party model outputs are not automatically covered.
- Source 1: AI watermarkingSource 2: AI watermarkingSource 3: AI watermarkingSource 4: AI watermarking
- Watermarking technique
- SynthID
- Source 1: Watermarking techniqueSource 2: Watermarking techniqueSource 3: Watermarking techniqueSource 4: Watermarking technique
- Labelling reviewed
- Nov 5, 2026
- Source 1: Labelling reviewedSource 2: Labelling reviewedSource 3: Labelling reviewedSource 4: Labelling reviewed
Licence and access
API
Further details
- Evaluated API variant
- Exact API variant: eleven_v3 (retrieved 2026-10-16)
- Source: Evaluated API variant
Sources and data date
Show all 41 sources
Benchmark sources at a glance
Which independent evaluators tested this model. This is coverage, not a quality ranking.
No active result from the reviewed external evaluators can currently be attributed to this model. Other source evidence remains available below.
Without vendor claims and historical or disputed results; those stay labelled in the single values.