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. Qwen3 ASR 0.6BQwenRemove
  2. Transcribe 1 ProFish AudioRemove
  3. Aura-2DeepgramRemove
  4. Perceptron Mk1.5PerceptronRemove

4 is the maximum. Remove one to add another.

qwen3-asr-0.6b vs transcribe-1-pro vs aura-2 vs perceptron-mk1.5
AttributeQwen3 ASR 0.6Bqwen3-asr-0.6bTranscribe 1 Protranscribe-1-proAura-2aura-2Perceptron Mk1.5perceptron-mk1.5
Pricing
Input$0 / 1M$0 / 1M$0 / 1M$0.15 / 1M
Output$0 / 1M$0 / 1M$0 / 1M$1.50 / 1M
Cache Write (5m)Not applicableNot applicableNot applicable$0.15 / 1M
Cache Write (1h)Not applicableNot applicableNot applicable$0.15 / 1M
Cache ReadNot applicableNot applicableNot applicable$0.15 / 1M
Web Search$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Context
Max contextN/AN/AN/A36.9K
Max outputN/AN/AN/AN/A
Capabilities
VisionNoNoNoNo
Function CallingNoNoNoNo
JSON ModeNoNoNoNo
StreamingNoNoNoYes
Catalogue
ProviderQwenFish AudioDeepgramPerceptron
Categoryvoicevoicevoicechat
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-08-132026-09-242026-07-162026-09-25
Description
SummaryQwen3-ASR 0.6B speech-to-text. Billed per second of audio.Fish Audio Transcribe 1 Pro speech-to-text with speaker labels; transcripts include speaker tags such as <|speaker:0|>. Billed per second of audio.Deepgram Aura-2 text-to-speech for real-time voice applications. Billed per input character.Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.