Voice AI BenchmarksBy

PROVIDERLAST 30 DAYS

official resource

OpenAI voice AI models and benchmarks

OpenAI creates voice models across transcription, synthesis and native speech-to-speech interaction.

Measured models
6
STTTTSS2S
Best STT model#10 / 24
180ms
Whisper Large v3
Best TTS model#30 / 30
1075ms
GPT-4o mini TTS
Best S2S model#1 / 2
1306ms
GPT Realtime 2

Overview

OpenAI ships voice models across STT, TTS and S2S — dedicated Audio API models, Realtime paths, and open-weight Whisper served by third parties.

Every model below is measured daily on the same fixed inputs and ranked against the full field, never blended into a company score.

Model lineup

Speech-to-Text
GPT Realtime Whisper, GPT-4o Transcribe, GPT-4o mini Transcribe, Whisper Large v3
Text-to-Speech
GPT-4o mini TTS
Speech-to-Speech
GPT Realtime 2

Speech-to-Text

Full STT dashboard

Ranked on Time to Final Segment against 24 measured models.

Time to Final Segmentms · lower is better · OpenAI models markedEvery measured STT model on Time to Final Segment, with OpenAI's models highlighted.
  1. #1STT RT v564 ms
  2. #2Parakeet TDT 0.6B v370 ms
  3. #3STT 183 ms
  4. #4Nova 399 ms
  5. #5Nova 2101 ms
  6. #6Ink 2108 ms
  7. #7Scribe v2 Realtime120 ms
  8. #10Whisper Large v3180 ms
  9. #19GPT Realtime Whisper559 ms
  10. #20GPT-4o mini Transcribe623 ms
  11. #22GPT-4o Transcribe742 ms
leaders plus OpenAI models · 13 other models in the full table
Word Error Rate% · lower is better · OpenAI models markedEvery measured STT model on Word Error Rate, with OpenAI's models highlighted.
  1. #1Universal 3.5 Pro3.2%
  2. #2resonant-13.4%
  3. #3Chirp 34.1%
  4. #4Enhanced4.3%
  5. #5GPT-4o Transcribe4.7%
  6. #6Grok STT4.8%
  7. #7STT 14.8%
  8. #10GPT-4o mini Transcribe5.1%
  9. #11GPT Realtime Whisper5.2%
  10. #24Whisper Large v38.2%
leaders plus OpenAI models · 18 other models in the full table
Time to First Tokenms · lower is better · OpenAI models markedEvery measured STT model on Time to First Token, with OpenAI's models highlighted.
  1. #1Universal 3.5 Pro1030 ms
  2. #2Flux1089 ms
  3. #3Flux Multilingual1175 ms
  4. #4Parakeet TDT 0.6B v31210 ms
  5. #5Whisper Large v31241 ms
  6. #6Nova 31434 ms
  7. #7Nova 21436 ms
  8. #18GPT Realtime Whisper1823 ms
leaders plus OpenAI models · 16 other models in the full table
TTFS vs WER — OpenAI vs every measured modelEach point is one measured STT model · OpenAI models highlighted · 30-day averagesTime to Final Segment against Word Error Rate for every measured STT model, with OpenAI's models highlighted.
STT RT v5 — 64 ms, 5.8%Parakeet TDT 0.6B v3 — 70 ms, 11.0%STT 1 — 83 ms, 4.8%Nova 3 — 99 ms, 6.3%Nova 2 — 101 ms, 7.9%Ink 2 — 108 ms, 4.9%Scribe v2 Realtime — 120 ms, 5.5%Universal 3.5 Pro — 146 ms, 3.2%Default via Azure — 155 ms, 5.3%Velma 2 STT Streaming — 191 ms, 6.4%Grok STT — 199 ms, 4.8%Pulse — 205 ms, 5.3%Default via Speechmatics — 223 ms, 5.5%Default via Gradium — 249 ms, 10.0%resonant-1 — 288 ms, 3.4%Enhanced — 341 ms, 4.3%Voxtral Mini Transcribe Realtime 2602 — 356 ms, 6.2%Solaria 1 — 680 ms, 7.1%Chirp 2 — 811 ms, 5.0%Chirp 3 — 813 ms, 4.1%Whisper Large v3 — 180 ms, 8.2%GPT Realtime Whisper — 559 ms, 5.2%GPT-4o mini Transcribe — 623 ms, 5.1%GPT-4o Transcribe — 742 ms, 4.7%
Benchmarked models with their Time to Final Segment over the last 30 days.
ModelHostTTFSRank
GPT Realtime WhisperOpenAI559 ms19th of 24
GPT-4o TranscribeOpenAI742 ms22nd of 24
GPT-4o mini TranscribeOpenAI623 ms20th of 24
Whisper Large v3Together AI180 ms10th of 24

Text-to-Speech

Full TTS dashboard

Ranked on Time to First Audio against 30 measured models.

Time to First Audioms · lower is better · OpenAI models markedEvery measured TTS model on Time to First Audio, with OpenAI's models highlighted.
  1. #1Palabra TTS v1116 ms
  2. #2vui124 ms
  3. #3TTS Flash 2128 ms
  4. #4TTS 2176 ms
  5. #5Blizzard235 ms
  6. #6Neural236 ms
  7. #7Mist v3256 ms
  8. #30GPT-4o mini TTS1075 ms
leaders plus OpenAI models · 22 other models in the full table
Word Error Rate% · lower is better · OpenAI models markedEvery measured TTS model on Word Error Rate, with OpenAI's models highlighted.
  1. #1TTS RT v13.7%
  2. #2TTS Rt v23.9%
  3. #3Neural4.3%
  4. #4Eleven v3 Conversational4.4%
  5. #5Lightning v3.1 Pro4.4%
  6. #6Default4.6%
  7. #7S2.1 Pro4.6%
  8. #12GPT-4o mini TTS4.8%
leaders plus OpenAI models · 22 other models in the full table
TTFA vs WER — OpenAI vs every measured modelEach point is one measured TTS model · OpenAI models highlighted · 30-day averagesTime to First Audio against Word Error Rate for every measured TTS model, with OpenAI's models highlighted.
Palabra TTS v1 — 116 ms, 5.9%vui — 124 ms, 7.9%TTS Flash 2 — 128 ms, 4.9%TTS 2 — 176 ms, 4.8%Blizzard — 235 ms, 7.4%Neural — 236 ms, 4.3%Mist v3 — 256 ms, 6.3%TTS Rt v2 — 262 ms, 3.9%Sonic 3.5 — 274 ms, 6.1%TTS RT v1 — 275 ms, 3.7%Dragon HD Latest — 310 ms, 5.1%Coda — 313 ms, 5.2%Aura 2 — 328 ms, 5.3%S2.1 Pro — 374 ms, 4.6%Default — 384 ms, 4.6%Speech 2.8 Turbo — 411 ms, 4.8%Eleven v3 Conversational — 412 ms, 4.4%Grok TTS — 420 ms, 4.7%S1 — 434 ms, 4.9%Flash v2.5 — 455 ms, 6.7%Speech 2.8 HD — 460 ms, 4.7%Sonic 3.6 — 466 ms, 5.5%Simba 3.2 — 484 ms, 4.7%Chirp 3 HD — 512 ms, 5.2%Simba 3.0 — 526 ms, 5.3%Falcon 2 — 549 ms, 5.2%Lightning v3.1 Pro — 586 ms, 4.4%Qwen3 TTS Flash Realtime — 645 ms, 8.8%S2.1 Pro Free — 806 ms, 4.7%GPT-4o mini TTS — 1075 ms, 4.8%
Benchmarked models with their Time to First Audio over the last 30 days.
ModelHostTTFARank
GPT-4o mini TTSOpenAI1075 ms30th of 30

Speech-to-Speech

Full S2S dashboard

Ranked on Voice-to-Voice Latency against 2 measured models.

Voice-to-Voice Latencyms · lower is better · OpenAI models markedEvery measured S2S model on Voice-to-Voice Latency, with OpenAI's models highlighted.
  1. #1GPT Realtime 21306 ms
  2. #2Gemini 3.1 Flash Live (Preview)1380 ms
Instruction Adherence% · higher is better · OpenAI models markedEvery measured S2S model on Instruction Adherence, with OpenAI's models highlighted.
  1. #1Gemini 3.1 Flash Live (Preview)76%
  2. #2GPT Realtime 271%
V2V vs Instruction — OpenAI vs every measured modelEach point is one measured S2S model · OpenAI models highlighted · 30-day averagesVoice-to-Voice Latency against Instruction Adherence for every measured S2S model, with OpenAI's models highlighted.
Gemini 3.1 Flash Live (Preview) — 1380 ms, 76%GPT Realtime 2 — 1306 ms, 71%
Benchmarked models with their Voice-to-Voice Latency over the last 30 days.
ModelHostV2VRank
GPT Realtime 2OpenAI1306 ms1st of 2

Limits of this comparison

Coval measures OpenAI's first-party APIs; Whisper Large v3 also appears where other providers host its open weights.

  • The different API paths are measured separately and do not cover every voice or session configuration.

Official resources

Same datasets, prompts and metric definitions for every model, measured by Coval’s open-source runner. Full methodology on the overview.

Evaluate your own voice agent

Use Coval to test your production configuration, prompts and calls—not only the public benchmark endpoints.

Book a Demo