Collections / Speech to text

Best Speech-to-Text and Transcription Models

Transcribe and understand spoken audio.

Selection from the public model catalog; collection usage order is available at the source. View source

5 models
Xiaomi: MiMo-V2.6-Pro-UltraSpeedxiaomi/mimo-v2.6-pro-ultraspeed1M contextUnverified/M input tokensXiaomi: MiMo-V2.6-Flashxiaomi/mimo-v2.6-flash1.1M contextUnverified/M input tokensXiaomi: MiMo-V2.6-Proxiaomi/mimo-v2.6-pro1.1M contextUnverified/M input tokensQwen: Qwen3.8 Omni Flashqwen/qwen3.8-omni-flash1M context$0.15/M input tokensXiaomi: MiMo-V2.5xiaomi/mimo-v2.51.1M contextUnverified/M input tokens