llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model Directory

Scoring & Data

Scoring & Data
1224 models729 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

naturalness benchmark

Artificial Analysis Text To Speech Leaderboard

Artificial Analysis Text To Speech is an official Elo leaderboard published by Artificial Analysis.

Updated Sep 8, 2026

Models96
Model coverage96
MetricElo
EvidenceB

On this page

  • Ranking
  • Highlights
  • Distribution
  • Top models
  • About
  • FAQ

Artificial Analysis Text To Speech Ranking

Higher elo ranks better on this benchmark.

30 of 96 rows
Columns

Show columns

Sort by
Rank
Model
Elo
Percentile
Participants
Evidence
Evaluated
Rank01ModelCASonic 3.6CartesiaElo1,282.00 elo (1,265.00 elo - 1,299.00 elo)Percentile100.00%Participants96EvidenceBEvaluatedN/A
Rank02ModelINRealtime TTS-2InworldElo1,252.00 elo (1,234.00 elo - 1,270.00 elo)Percentile98.95%Participants96EvidenceBEvaluatedN/A
Rank03ModelALQwen-Audio-3.0-TTS-PlusAlibabaElo1,241.00 elo (1,227.00 elo - 1,255.00 elo)Percentile97.89%Participants96EvidenceBEvaluatedN/A
Rank04ModelSPSimba 3.2SpeechifyAIElo1,240.00 elo (1,226.00 elo - 1,254.00 elo)Percentile96.84%Participants96EvidenceBEvaluatedN/A
Rank05ModelVLLuna TTSVUI LabsElo1,228.00 elo (1,214.00 elo - 1,242.00 elo)Percentile95.79%Participants96EvidenceBEvaluatedN/A
Rank06ModelINRealtime TTS-2 Flash - Research PreviewInworldElo1,222.00 elo (1,207.00 elo - 1,237.00 elo)Percentile94.74%Participants96EvidenceBEvaluatedN/A
Rank07ModelBRBreeze TTS 2BreezeBlueElo1,215.00 elo (1,198.00 elo - 1,232.00 elo)Percentile93.68%Participants96EvidenceBEvaluatedN/A
Rank08ModelELv3 ConversationalElevenLabsElo1,210.00 elo (1,195.00 elo - 1,225.00 elo)Percentile92.63%Participants96EvidenceBEvaluatedN/A
Rank09ModelGOGemini 3.1 Flash TTSGoogleElo1,208.00 elo (1,196.00 elo - 1,220.00 elo)Percentile91.58%Participants96EvidenceBEvaluatedN/A
Rank10ModelSTStepAudio 2.5 TTS (Aug 2026)StepFunElo1,205.00 elo (1,188.00 elo - 1,222.00 elo)Percentile90.53%Participants96EvidenceBEvaluatedN/A
Rank11ModelCASonic 3.5CartesiaElo1,193.00 elo (1,181.00 elo - 1,205.00 elo)Percentile89.47%Participants96EvidenceBEvaluatedN/A
Rank12ModelSMLightning V3.1 Pro (Jul 2026)Smallest.aiElo1,190.00 elo (1,176.00 elo - 1,204.00 elo)Percentile88.42%Participants96EvidenceBEvaluatedN/A
Rank13ModelSOSoniox TTS Real-Time v2SonioxElo1,179.00 elo (1,168.00 elo - 1,190.00 elo)Percentile87.37%Participants96EvidenceBEvaluatedN/A
Rank14ModelELEleven v3ElevenLabsElo1,175.00 elo (1,164.00 elo - 1,186.00 elo)Percentile86.32%Participants96EvidenceBEvaluatedN/A
Rank15ModelMISpeech 2.8 HDMiniMaxElo1,171.00 elo (1,160.00 elo - 1,182.00 elo)Percentile85.26%Participants96EvidenceBEvaluatedN/A
Rank16ModelMAFalcon 2Murf AIElo1,158.00 elo (1,143.00 elo - 1,173.00 elo)Percentile84.21%Participants96EvidenceBEvaluatedN/A
Rank17ModelMISpeech 2.8 TurboMiniMaxElo1,152.00 elo (1,141.00 elo - 1,163.00 elo)Percentile83.16%Participants96EvidenceBEvaluatedN/A
Rank18ModelGRGradium TTS (Aug 2026)GradiumElo1,149.00 elo (1,134.00 elo - 1,164.00 elo)Percentile82.11%Participants96EvidenceBEvaluatedN/A
Rank19ModelASAsync Flash v1.5asyncElo1,141.00 elo (1,128.00 elo - 1,154.00 elo)Percentile81.05%Participants96EvidenceBEvaluatedN/A
Rank20ModelFAFish Audio S2.1 ProFish AudioElo1,141.00 elo (1,128.00 elo - 1,154.00 elo)Percentile80.00%Participants96EvidenceBEvaluatedN/A
Rank21ModelSTStep TTS 2 (Mar 2026)StepFunElo1,138.00 elo (1,126.00 elo - 1,150.00 elo)Percentile78.95%Participants96EvidenceBEvaluatedN/A
Rank22ModelMISpeech 2.6 HDMiniMaxElo1,134.00 elo (1,123.00 elo - 1,145.00 elo)Percentile77.89%Participants96EvidenceBEvaluatedN/A
Rank23ModelSMLightning V3.1 Pro TTS (Jun 2026)Smallest.aiElo1,133.00 elo (1,120.00 elo - 1,146.00 elo)Percentile76.84%Participants96EvidenceBEvaluatedN/A
Rank24ModelMIAzure HD 2.5MicrosoftElo1,131.00 elo (1,119.00 elo - 1,143.00 elo)Percentile75.79%Participants96EvidenceBEvaluatedN/A
Rank25ModelFAFish Audio S2 ProFish AudioElo1,128.00 elo (1,116.00 elo - 1,140.00 elo)Percentile74.74%Participants96EvidenceBEvaluatedN/A
Rank26ModelMISpeech 2.6 TurboMiniMaxElo1,127.00 elo (1,116.00 elo - 1,138.00 elo)Percentile73.68%Participants96EvidenceBEvaluatedN/A
Rank27ModelXASpaceXAI TTSxAIElo1,123.00 elo (1,107.00 elo - 1,139.00 elo)Percentile72.63%Participants96EvidenceBEvaluatedN/A
Rank28ModelSPSimba 3.0SpeechifyAIElo1,122.00 elo (1,110.00 elo - 1,134.00 elo)Percentile71.58%Participants96EvidenceBEvaluatedN/A
Rank29ModelASAsync Pro v1.0asyncElo1,121.00 elo (1,108.00 elo - 1,134.00 elo)Percentile70.53%Participants96EvidenceBEvaluatedN/A
Rank30ModelMISpeech 02 HDMiniMaxElo1,112.00 elo (1,101.00 elo - 1,123.00 elo)Percentile69.47%Participants96EvidenceBEvaluatedN/A

Artificial Analysis Text To Speech Highlights

The leading models and scores on this benchmark.

Artificial Analysis Text To Speech Score Distribution

A closer view of the leading scores on this benchmark.

Artificial Analysis Text To Speech

The Top AI Models for Artificial Analysis Text To Speech

The first five results on this benchmark, with official price and output speed added where the model identity can be matched.

What is Artificial Analysis Text To Speech?

What Artificial Analysis Text To Speech measures and how its scores work.

Artificial Analysis Text To Speech is a benchmark leaderboard for text-to-speech systems.

It measures naturalness using the Elo metric, reported in elo units.

Scores are shown in elo. This benchmark is verified and has an evidence level of B.

Family
Artificial Analysis Text To Speech
Modality
audio
Primary category
naturalness
Score direction
higher
LLMBoard eligible
No
Evaluation key
overall

Artificial Analysis. Benchmark scores retain their original unit. Overall score eligibility is shown separately.

FAQ

Common questions about Artificial Analysis Text To Speech.

Which model scores highest on Artificial Analysis Text To Speech?

Sonic 3.6 is currently ranked first with 1,282.00 elo.

What are the top three models on Artificial Analysis Text To Speech?

The current leaders are Sonic 3.6 (1,282.00 elo), Realtime TTS-2 (1,252.00 elo), and Qwen-Audio-3.0-TTS-Plus (1,241.00 elo).

Which Artificial Analysis Text To Speech model has the lowest official input price?

No matched official input price is currently available.

Which models are fastest among Artificial Analysis Text To Speech results?

No matched runtime record is currently available.

Does the highest elo result prove overall model quality?

No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.

What does Artificial Analysis Text To Speech measure?

It measures naturalness using the Elo metric, reported in elo units.

Is a higher elo better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

96 model results are currently shown.

Does this benchmark affect the overall score?

No. This benchmark is shown for reference but does not contribute to the overall score.

Rank #1Sonic 3.61,282.00 elo (1,265.00 elo - 1,299.00 elo)
Rank #2Realtime TTS-21,252.00 elo (1,234.00 elo - 1,270.00 elo)
Rank #3Qwen-Audio-3.0-TTS-Plus1,241.00 elo (1,227.00 elo - 1,255.00 elo)
Rank #4Simba 3.21,240.00 elo (1,226.00 elo - 1,254.00 elo)

Ranking basisThis artificial analysis text to speech AI model leaderboard uses descending elo in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.

  1. 01
    CA
    Sonic 3.6Cartesia
    Elo
    1,282.00 elo

    Strengths

    • Ranks #1 of 96 compared models
    • 100th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures Artificial Analysis Text To Speech, not total model capability
  2. 02
    IN
    Realtime TTS-2Inworld
    Elo
    1,252.00 elo

    Strengths

    • Ranks #2 of 96 compared models
    • 99th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures Artificial Analysis Text To Speech, not total model capability
  3. 03
    AL
    Alibaba
    Elo
    1,241.00 elo

    Strengths

    • Ranks #3 of 96 compared models
    • 98th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures Artificial Analysis Text To Speech, not total model capability
  4. 04
    SP
    SpeechifyAI
    Elo
    1,240.00 elo

    Strengths

    • Ranks #4 of 96 compared models
    • 97th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures Artificial Analysis Text To Speech, not total model capability
  5. 05
    VL
    VUI Labs
    Elo
    1,228.00 elo

    Strengths

    • Ranks #5 of 96 compared models
    • 96th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures Artificial Analysis Text To Speech, not total model capability

Selection summary

Best AI Models for Artificial Analysis Text To Speech

Sonic 3.6 currently leads Artificial Analysis Text To Speech with 1,282.00 elo. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price, and runtime.

Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.

Qwen-Audio-3.0-TTS-Plus
Simba 3.2
Luna TTS
Benchmark rank #1Sonic 3.61,282.00 elo
Benchmark rank #2Realtime TTS-21,252.00 elo
Benchmark rank #3Qwen-Audio-3.0-TTS-Plus1,241.00 elo