benchmarks/structured speech-to-text/best STT models 2026
two independent benchmarks · transcript + task accuracy

Best speech-to-text (STT) models in 2026

Short answer: Best depends on the metric. For ordinary transcript accuracy (most accurate by WER), universal-3.5-pro from AssemblyAI currently leads the rolling 7d benchmark at 3.3% WER. For voice agent workflows that must recover exact values (best Task Success Rate), Deepgram Nova-3 leads at 71.0%, but the top results are close enough that the workflow-specific entity rows matter more than a universal winner.

“Best” is not one ranking. Most accurate transcripts, lowest finalization latency, and best exact-value recovery are measured on separate tables: a live Word Error Rate and latency benchmark, and a separate exact structured-value benchmark. The values are not blended into a made-up overall score.

Most accurate, lowest latency, or best exact-value recovery

Start with the job your transcript must do. Each row names the metric that should decide “best,” then points to the live ranking.

How to choose which speech-to-text ranking to read
Use caseRead this metricEvidence
Captions, notes, search, analyticsMost accurate (lowest WER)Read the WER ranking in [01] ↓
Forms, callbacks, workflow automationBest Task Success RateRead the TSR ranking in [02] ↓
Individual emails, phones, paths, and IDsBest CTEM for the specific entity typeRead the full entity matrix →
Realtime exact-value captureBest streaming TSRCompare streaming rows in [02] ↓
Lowest-latency transcript finalizationLowest latency (p95 TTFS, then median)Compare the latency columns in [01] ↓

Most accurate speech-to-text (STT) models by Word Error Rate

Lower WER is better. These figures are Coval's rolling 7d aggregate on identical audio, mirrored with attribution and last synced Aug 14, 2026. Median and p95 TTFS show lowest-latency finalization, not the time to the first partial transcript.

Most accurate speech-to-text models by average Word Error Rate
RankModelProviderWERMedian TTFSp95 TTFS
1universal-3.5-proAssemblyAI3.3%124 ms280 ms
2realtimeReson83.6%269 ms405 ms
3chirp_3Google4.2%805 ms1,120 ms
4enhancedSpeechmatics4.4%326 ms515 ms
5grok-sttxAI4.5%192 ms255 ms
6gpt-4o-transcribeOpenAI4.7%713 ms1,059 ms
7inworld-stt-1Inworld AI4.8%98 ms121 ms
8ink-2Cartesia5.0%105 ms137 ms
9chirp_2Google5.1%763 ms1,179 ms
10pulseSmallest5.2%192 ms293 ms

The current accuracy-latency Pareto frontier contains 4 models: parakeet-tdt-0.6b-v3 (Together AI), stt-rt-v5 (Soniox), inworld-stt-1 (Inworld AI), universal-3.5-pro (AssemblyAI). A frontier model is not beaten by another model on both WER and median TTFS. Open the complete live STT benchmark →

Most accurate speech-to-text (STT) models for exact values

This independent snapshot uses 300 English workplace recordings containing 1,482 audited values across 26 types. TSR requires every target value in a recording to be correct; CTEM scores individual values. Scores are fractions rendered as percentages, and higher is better.

Speech-to-text models ranked by exact-value Task Success Rate
RankModelProviderModeTSRCTEMFormat-invariant WER
1Deepgram Nova-3Deepgrambatch71.0%91.4%8.2%
2ElevenLabs Scribe v2ElevenLabsbatch68.0%91.8%6.8%
3Deepgram Nova-3Deepgramstreaming61.0%88.3%9.5%
4ElevenLabs Scribe v2 RealtimeElevenLabsstreaming59.0%88.1%5.1%
5Google Cloud Chirp 3Google Cloudbatch58.0%88.7%5.8%
6OpenAI GPT Realtime (Whisper)OpenAIstreaming57.3%88.7%8.6%
7Google Cloud Chirp 3Google Cloudstreaming56.3%87.3%6.8%
8Inkling (Thinking Machines)Thinking Machines Labbatch54.7%85.3%5.0%
9OpenAI GPT-4o TranscribeOpenAIbatch54.0%87.0%4.6%
10Whisper large-v3OpenAIbatch53.3%87.3%5.9%

Deepgram Nova-3 and ElevenLabs Scribe v2 are separated by 3.0 percentage points on TSR. With only 300 clips, treat that as an overlapping top group rather than a durable universal ordering. Check the per-entity matrix for the values your application uses. Open all systems and entity types →

What each ranking measures

The WER/latency table and structured-value table use different audio, protocols, windows, and scopes. Their percentages cannot be averaged or compared directly. This page combines the decision, not the scores.

BenchmarkWhat it answersPrimary metricsProvenance
Live STT benchmarkWhich model has the fewest word errors, and how quickly does it finalize?Average WER, median and p95 TTFSCoval sells voice-agent evaluation infrastructure. Rolling data and open runner are attributed to Coval.
Structured STT benchmarkDoes the transcript preserve every exact value a downstream task needs?TSR, CTEM, format-invariant WERDataset by Besimple AI; baselines run and scored by Openbenchmarks.

Best speech-to-text (STT) models: common questions

What is the best speech-to-text (STT) model in 2026?

Best depends on the metric. For ordinary transcript accuracy (most accurate by WER), universal-3.5-pro from AssemblyAI currently leads the rolling 7d benchmark at 3.3% WER. For voice agent workflows that must recover exact values (best Task Success Rate), Deepgram Nova-3 leads at 71.0%, but the top results are close enough that the workflow-specific entity rows matter more than a universal winner.

What is the most accurate speech-to-text (STT) model?

Most accurate means best WER for readable transcripts, or best Task Success Rate when a wrong digit, email, path, or ID breaks the workflow. Those are different rankings; use the tables below instead of one blended score.

Which is the best STT model provider?

No provider wins every definition of accuracy. AssemblyAI supplies the current lowest-WER model in the rolling transcript benchmark, while Deepgram supplies the highest-TSR model for exact structured values. Choose the provider whose model wins on your audio, deployment mode, language, latency budget, and failure-sensitive fields.

Is the model with the lowest Word Error Rate always the most accurate?

Only for a task defined by average word correctness. On the structured benchmark, AssemblyAI Universal 3.5 Pro has the lowest format-invariant WER at 3.9%, while Deepgram Nova-3 leads recording-level Task Success Rate at 71.0%. A transcript can have few wrong words and still corrupt the one phone number, email, path, or ID a workflow needs.

Which speech-to-text (STT) model has the lowest latency?

Lowest latency here means lowest p95 Time to Final Segment, not the first partial transcript. Tiny median gaps at the fast end are usually smaller than the rest of a voice pipeline. Use the TTFS columns in the WER table, then confirm on the live STT board.

What is the best speech-to-text (STT) model for realtime voice agents?

Deepgram Nova-3 currently has the highest structured-value Task Success Rate among streaming systems on this board at 61.0%. That is not a complete voice-agent recommendation: also compare p95 finalization latency, interruption handling, endpointing, language coverage, and performance on your own calls.

How should I compare speech-to-text (STT) models fairly?

Send identical audio to every model, separate batch from streaming, and report at least average WER, p95 finalization latency, and a task-specific metric for critical values. Keep prompts, vocabulary boosts, cleanup, and endpointing settings controlled or disclose them. Finally, repeat the test on production audio because accents, noise, languages, and domain vocabulary can change the ordering.