Kimi K3 + Omnilingual ASR Hausa Audio → English

Description

Hausa audio benchmark run using Omnilingual ASR for transcription and Kimi K3 for the English response.

Model

💪 Capabilities

🦻 Speech Recognition & Translation

Choose a language to translate incoming text & audio messages to English and responses back to your selected language. Useful for low-resource languages.

Filter to

Speech-to-Text Provider

Spoken Language

🔠 Translate to & from English

🗣️ Text to Speech & Lipsync

Filter to

Text-to-Speech Provider

MMS TTS Language

🫦 Add Lipsync Video

🩻 Photo & Document Intelligence

📊 Analytics & Evaluation

Advanced Settings

In general, you should not need to adjust these.

🔠 Language Model Settings

Response Format

Max Output Tokens

Answer Outputs

Reasoning Effort

Est.$0.04