Qwen3 ASR 1.7B
Qwen3 ASR 1.7B is an open-source multilingual speech-to-text model developed by Qwen with 1.7 billion parameters.
Qwen
DeepInfraMultilingual speech recognition at 1.7B parameters
Qwen3 ASR 1.7B is a speech-to-text model developed by Qwen, the AI research team at Alibaba. It belongs to the Qwen3 ASR model family and contains 1.7 billion parameters, making it a compact option for automatic speech recognition tasks. The model is open source and supports multiple languages, reflecting Qwen's focus on broad linguistic coverage in their model releases.
This model is designed for transcription use cases where converting spoken audio into text is the primary requirement. Its relatively small parameter count makes it suitable for deployment in resource-constrained environments while still supporting multilingual input. Developers looking for an open-source ASR model with multilingual capabilities can access it through DeepInfra's inference infrastructure.
What Qwen3 ASR 1.7B supports
Speech Transcription
Converts spoken audio into written text using a 1.7B parameter architecture trained for automatic speech recognition tasks.
Multilingual Support
Recognizes and transcribes speech across multiple languages, reflecting the multilingual focus of the Qwen3 ASR model family.
Open Source Access
Released as an open-source model under the Qwen organization, allowing inspection, fine-tuning, and self-hosted deployment.
Cloud Inference
Available via DeepInfra's hosted inference API, enabling transcription without managing your own model infrastructure.
Ready to build with Qwen3 ASR 1.7B?
Get Started FreeCommon questions about Qwen3 ASR 1.7B
What is the context window for Qwen3 ASR 1.7B?
The metadata does not specify a context window for this model. As a speech-to-text transcription model, context window constraints differ from text-based models — audio length limits would depend on the inference provider's configuration.
Is Qwen3 ASR 1.7B free to use?
No published pricing is listed in the available metadata. Pricing for inference via DeepInfra may apply; check DeepInfra's pricing page for current rates.
What languages does Qwen3 ASR 1.7B support?
The model is tagged as multilingual, indicating support for more than one language. For a specific list of supported languages, refer to the official Qwen model documentation or the DeepInfra model page.
Is Qwen3 ASR 1.7B open source?
Yes, the model is tagged as open source and is published under the Qwen organization, meaning the model weights are publicly available for use and modification.
What is the knowledge cutoff or release date for this model?
The metadata lists a release date of 2026. No specific training data cutoff date is provided in the available information.
Explore similar models
QwenQwen3 TTS
Qwen3 TTS is an open-source multilingual text-to-speech model from Qwen with a 10,000-token context window.
QwenQwen Image 3.0
Qwen Image 3.0 is an image generation model from Qwen that supports text prompts and source image inputs at $0.03 per image.
QwenQwen Image 3.0 Pro
Qwen Image 3.0 Pro is a flagship image generation model from Qwen supporting text-to-image and image-guided generation.
MistralVoxtral Mini 3B
Voxtral Mini 3B is a 3-billion-parameter open-source speech-to-text model released by Mistral in July 2025.
OpenAIWhisper-1
Whisper-1 is OpenAI's speech-to-text model that transcribes and translates audio at $0.006 per minute.
ElevenLabsScribe v2
Scribe v2 is a speech-to-text transcription model from ElevenLabs that supports speaker identification.
Start building with Qwen3 ASR 1.7B
No API keys required. Create AI-powered workflows with Qwen3 ASR 1.7B in minutes — free.