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

4 is the maximum. Remove one to add another.

s2-pro vs transcribe-1 vs qwen3-asr-0.6b vs voxtral-mini-3b-2507
AttributeS2 Pros2-proTranscribe 1transcribe-1Qwen3 ASR 0.6Bqwen3-asr-0.6bVoxtral Mini 3B 2507voxtral-mini-3b-2507
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 AudioFish AudioQwenMistral AI
Categoryvoicevoicevoicevoice
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-07-292026-07-292026-08-132026-08-13
Description
SummaryFish Audio S2 Pro text-to-speech. Billed per UTF-8 byte of input text.Fish Audio Transcribe 1 speech-to-text. Billed per second of audio.Qwen3-ASR 0.6B speech-to-text. Billed per second of audio.Mistral AI Voxtral Mini (3B) speech-to-text. Billed per second of audio.