Skip to content
Apertis

Compare models

Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.

  1. Transcribe 1Fish AudioRemove
  2. Voxtral Mini 3B 2507Mistral AIRemove
  3. S2 ProFish AudioRemove
  4. Qwen3 ASR 0.6BQwenRemove

4 is the maximum. Remove one to add another.

transcribe-1 vs voxtral-mini-3b-2507 vs s2-pro vs qwen3-asr-0.6b
AttributeTranscribe 1transcribe-1Voxtral Mini 3B 2507voxtral-mini-3b-2507S2 Pros2-proQwen3 ASR 0.6Bqwen3-asr-0.6b
Pricing
Input$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Output$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Cache Write (5m)Not applicableNot applicableNot applicableNot applicable
Cache Write (1h)Not applicableNot applicableNot applicableNot applicable
Cache ReadNot applicableNot applicableNot applicableNot applicable
Web Search$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Context
Max contextN/AN/AN/AN/A
Max outputN/AN/AN/AN/A
Capabilities
VisionNoNoNoNo
Function CallingNoNoNoNo
JSON ModeNoNoNoNo
StreamingNoNoNoNo
Catalogue
ProviderFish AudioMistral AIFish AudioQwen
Categoryvoicevoicevoicevoice
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-07-292026-08-132026-07-292026-08-13
Description
SummaryFish Audio Transcribe 1 speech-to-text. Billed per second of audio.Mistral AI Voxtral Mini (3B) speech-to-text. Billed per second of audio.Fish Audio S2 Pro text-to-speech. Billed per UTF-8 byte of input text.Qwen3-ASR 0.6B speech-to-text. Billed per second of audio.