speech.detect-language

What problem does it solve?

It solves the problem of not knowing what language is being spoken in an audio clip, which can block the right transcription and downstream processing.

Core Features & Use Cases

• Dominant Language Detection: Uses the native audio_transcribe tool with action detect-language to identify the primary spoken language.
• Provider-Aware Routing: Supports automatic provider selection (or the specified provider) to match transcription needs and optimize routing.
• Routing-Focused Output: Returns detected language plus provider, duration, cost, and warnings without presenting the full transcript unless requested.

Quick Start

Use speech.detect-language on the attached audio by asking: Detect the dominant spoken language in the clip provided, using provider auto, and return the detected language and routing details.