Deepgram Voice AI Benchmarks
Speech models are compared on word error rate across production audio in 20 languages, while speech synthesis models are compared on read-aloud and hard-prompt sets.
Deepgram reports about 30 hours per vendor per language, excludes public datasets, and compares ten speech-to-text vendors. The page reports batch and streaming WER plus speech synthesis WER and first-audio latency.
- Made by
- Deepgram
- Released
- April 2026
- Kind
- Speech recognition and translation
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- Kept private
- Measures
- Efficiency
- Language
- Many languages
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- A model developer
- In views
- Audio and speech, Many languages, Lab internal evals
Deepgram Nova-3-multi tops the leaderboard with 13.8%
Best score per entry from the benchmark's own leaderboard, read on November 21st, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.
- 1 Deepgram Nova-3-multi 13.8%
- 2 ElevenLabs Scribe 16.3%
- 3 Soniox STT RT v4 18.1%
- 4 Google Chirp 3 18.5%
- 5 Azure Auto 19.3%
- 6 Speechmatics Enhanced 19.4%
- 7 AWS Transcribe 20.2%
- 8 AssemblyAI Universal 23%
- 9 OpenAI Whisper 25.3%
Source: Official Deepgram Voice AI Benchmarks leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Deepgram Nova-3-multi | 13.8% | Official leaderboard | ||
| 2 | ElevenLabs Scribe | 16.3% | Official leaderboard | ||
| 3 | Soniox STT RT v4 | 18.1% | Official leaderboard | ||
| 4 | Google Chirp 3 | 18.5% | Official leaderboard | ||
| 5 | Azure Auto | 19.3% | Official leaderboard | ||
| 6 | Speechmatics Enhanced | 19.4% | Official leaderboard | ||
| 7 | AWS Transcribe | 20.2% | Official leaderboard | ||
| 8 | AssemblyAI Universal | 23% | Official leaderboard | ||
| 9 | OpenAI Whisper | 25.3% | Official leaderboard |
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Audio and video
- Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy.
Qwen 3.8 Max 88.7%
- LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization.
Gemini 4 Argon 91.7%
- MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy.
Qwen 3.8 Max 82.4%
- MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy.
Qwen 3.8 Max 90.8%
- FLEURS In use Models transcribe read speech in 102 languages built from FLoRes-101 sentences. Model cards usually report word error rate, so lower scores are better.
Phi-4-multimodal 4.00%
- VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules.
Qwen3.5-Omni-Plus 93.1%
Data audit
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access The tasks are private.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the official leaderboard (9 entries).
- Pass Models scored 9 entries on its leaderboard, none a model we track.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom Lower is better, so there’s no ceiling to reach.
Leaderboard import 3 pass
- Pass Importer We read the board on deepgram.com: 9 entries at the last read, none a model we track.
- Pass Last read November 21st, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.