Best Speech-to-Text and Transcription Models
Model rankings updated August 2026 based on real usage data.
Speech-to-text models convert spoken audio into text for transcription, captions, meeting summaries, call analysis, and voice-driven applications. This collection ranks transcription models by their usage on OpenRouter over the past week. The current top models are GPT-4o Mini Transcribe, GPT-4o Transcribe, and Voxtral Mini Transcribe. Compare accuracy, speed, language support, and cost to match the right model to your audio workflow.
Top Speech-to-Text Models on OpenRouter
OpenAI: GPT-4o Mini Transcribe
220M tokens
GPT-4o Mini Transcribe is OpenAI's smaller, cost-efficient speech-to-text model built on GPT-4o Mini audio capabilities. It's priced per token (input and output), making it suitable for high-volume transcription workflows that benefit from token-level billing transparency at a lower cost point.
OpenAI: GPT-4o Transcribe
86.1M tokens
GPT-4o Transcribe is OpenAI's high-quality speech-to-text model built on GPT-4o audio capabilities. It's priced per token (input and output), making it suitable for workflows that benefit from token-level billing transparency.
Mistral: Voxtral Mini Transcribe
11.8M tokens
Voxtral Mini Transcribe is Mistral's speech-to-text model, derived from the Voxtral Mini family. It accepts audio input and returns transcribed text via the standard transcription API. Suited for transcribing meetings, voice notes, podcasts, and other spoken content.
Nemotron 3.5 ASR Streaming Multilingual 0.6B is a speech recognition model from NVIDIA. Its prompt-conditioned, cache-aware FastConformer-RNNT design targets low-latency transcription across more than 40 languages for real-time captioning, voice agents, and multilingual transcription pipelines.
Voxtral Small 24B 2507 STT is a speech transcription model from Mistral AI. It is suited for transcription, translation, and audio understanding workloads that benefit from its larger model capacity.
Voxtral Mini 3B 2507 is a speech and audio understanding model from Mistral AI. It is suited for transcription, translation, and compact audio processing workloads.
Qwen3 ASR 1.7B is an automatic speech recognition model from Qwen. It supports multilingual language identification and transcription across 30 languages and 22 Chinese dialects, with streaming and offline inference plus segment-level and word-level timestamps.
Qwen3 ASR 0.6B is a compact automatic speech recognition model from Qwen. It supports multilingual language identification and transcription across 30 languages and 22 Chinese dialects, with streaming and offline inference plus segment-level and word-level timestamps.
GPT Transcribe is a high-accuracy speech-to-text model from OpenAI. It is suited for recorded audio, streamed file transcription, and committed Realtime turns, with free-form context, keyword hints, and multiple language hints for specialized terms and multilingual speech.
Transcribe 1 is a speech-to-text model from Fish Audio. It is suited for audio transcription with automatic language detection and can return timestamped word-level segments when alignment details are requested.