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. MAI-Transcribe 2MicrosoftRemove
  2. Aura-2DeepgramRemove
  3. Muse Spark 1.3MetaRemove
  4. Qwen3 ASR 1.7BQwenRemove

4 is the maximum. Remove one to add another.

mai-transcribe-2 vs aura-2 vs muse-spark-1.3 vs qwen3-asr-1.7b
AttributeMAI-Transcribe 2mai-transcribe-2Aura-2aura-2Muse Spark 1.3muse-spark-1.3Qwen3 ASR 1.7Bqwen3-asr-1.7b
Pricing
Input$0 / 1M$0 / 1M$1.25 / 1M$0 / 1M
Output$0 / 1M$0 / 1M$4.25 / 1M$0 / 1M
Cache Write (5m)Not applicableNot applicable$1.25 / 1MNot applicable
Cache Write (1h)Not applicableNot applicable$1.25 / 1MNot applicable
Cache ReadNot applicableNot applicable$1.25 / 1MNot applicable
Web Search$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Context
Max contextN/AN/A1MN/A
Max outputN/AN/AN/AN/A
Capabilities
VisionNoNoYesNo
Function CallingNoNoYesNo
JSON ModeNoNoYesNo
StreamingNoNoYesNo
Catalogue
ProviderMicrosoftDeepgramMetaQwen
Categoryvoicevoicechatvoice
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-09-032026-07-16—2026-08-13
Description
SummaryMicrosoft MAI-Transcribe-2 speech-to-text. Billed per second of audio.Deepgram Aura-2 text-to-speech for real-time voice applications. Billed per input character.Muse Spark 1.3 is Meta's multimodal reasoning model designed for long-running agentic, multi-agent, and coding workflows. It maintains context and information across extended tasks, enabling reliable execution in complex, multi-step environments. The model is optimized to resolve conflicting information, seek clarification or confirmation when necessary, and execute concisely, making it well suited for autonomous agents, collaborative multi-agent systems, and long-horizon software engineering workflows.Qwen3-ASR 1.7B speech-to-text. Billed per second of audio.