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. S1Fish AudioRemove
  2. Gemini 3.5 TranscribeGoogleRemove
  3. Voxtral Small 24B 2507 STTMistral AIRemove
  4. Aura-2DeepgramRemove

4 is the maximum. Remove one to add another.

s1 vs gemini-3.5-transcribe vs voxtral-small-24b-2507-stt vs aura-2
AttributeS1s1Gemini 3.5 Transcribegemini-3.5-transcribeVoxtral Small 24B 2507 STTvoxtral-small-24b-2507-sttAura-2aura-2
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/A98.3KN/AN/A
Max outputN/AN/AN/AN/A
Capabilities
VisionNoYesNoNo
Function CallingNoYesNoNo
JSON ModeNoNoNoNo
StreamingNoNoNoNo
Catalogue
ProviderFish AudioGoogleMistral AIDeepgram
Categoryvoicevoicevoicevoice
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-07-292026-09-252026-08-132026-07-16
Description
SummaryFish Audio S1 text-to-speech. Billed per UTF-8 byte of input text.Google Gemini 3.5 Transcribe speech-to-text. Billed per input and output token.Mistral AI Voxtral Small (24B) speech-to-text. Billed per second of audio.Deepgram Aura-2 text-to-speech for real-time voice applications. Billed per input character.