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

4 is the maximum. Remove one to add another.

aura-2 vs qwen3-asr-1.7b vs mai-transcribe-2 vs muse-spark-1.3
AttributeAura-2aura-2Qwen3 ASR 1.7Bqwen3-asr-1.7bMAI-Transcribe 2mai-transcribe-2Muse Spark 1.3muse-spark-1.3
Pricing
Input$0 / 1M$0 / 1M$0 / 1M$1.25 / 1M
Output$0 / 1M$0 / 1M$0 / 1M$4.25 / 1M
Cache Write (5m)Not applicableNot applicableNot applicable$1.25 / 1M
Cache Write (1h)Not applicableNot applicableNot applicable$1.25 / 1M
Cache ReadNot applicableNot applicableNot applicable$1.25 / 1M
Web Search$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Context
Max contextN/AN/AN/A1M
Max outputN/AN/AN/AN/A
Capabilities
VisionNoNoNoYes
Function CallingNoNoNoYes
JSON ModeNoNoNoYes
StreamingNoNoNoYes
Catalogue
ProviderDeepgramQwenMicrosoftMeta
Categoryvoicevoicevoicechat
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-07-162026-08-132026-09-03—
Description
SummaryDeepgram Aura-2 text-to-speech for real-time voice applications. Billed per input character.Qwen3-ASR 1.7B speech-to-text. Billed per second of audio.Microsoft MAI-Transcribe-2 speech-to-text. Billed per second of audio.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.