Router Which model to call, per language and per objective, decided from published measurements instead of a vendor's English leaderboard. Benchmark coverage by language Score against cost, per stage Accuracy (WER) $0.0010 $0.0160 2.0% 11.0% Realtime STT-1 3.3% · $0.0025 Universal-3.5 Pro 2.0% · $0.0075 Velma 2 4.4% · $0.0010 GPT-4o Transcribe 2.3% · $0.0060 GPT-4o-mini Transcribe 2.7% · $0.0030 Cost ($/min) # Model 1 Universal-3.5 Pro assemblyai:universal-3-5-pro 2.0% $0.0075 2 GPT-4o Transcribe openai:gpt-4o-transcribe 2.3% $0.0060 3 GPT-4o-mini Transcribe openai:gpt-4o-mini-transcribe 2.7% $0.0030 4 Qwen3-ASR alibaba:qwen3-asr-flash 2.8% $0.0054 5 Realtime STT-1 inworld:inworld-stt-1 3.3% $0.0025 6 Chirp 3 google:chirp_3 3.9% $0.0160 7 Velma 2 modulate:velma-2-stt-streaming-english-v2 4.4% $0.0010 8 Grok STT xai:stt 4.8% $0.0033 9 Solaria-1 gladia:solaria-1 5.0% $0.0125 10 Pulse smallest:pulse 5.1% ~$0.0050 11 stt-rt-v5 soniox:stt-rt-v5 7.5% $0.0020 12 Gradium ASR gradium:default 8.4% $0.0104 13 Nova-3…