$ loading_
Industrial speech recognition for multilingual transcription, diarization, and emotion detection.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "FunASR" yet — see the docs or source repo.
Use FunASR to process this meeting audio, generate a Chinese transcript, separate by speaker, and add timestamps for each segment.
A meeting transcript with timestamps and speaker labels.
Use FunASR to analyze this customer support call, transcribe the speech, detect speaker turns, and label emotion changes in a structured output.
A structured call analysis with transcription, speaker segments, and emotion labels.
I want to integrate FunASR into my app for real-time speech-to-text. Provide an example using its OpenAI-compatible API and explain the response format.
A developer-ready API example with parameters and response format details.
Transcribe audio or video to text with optional speaker labeling.
Transcribe local audio with speaker diarization into structured text directly in AI tools.
Build multilingual voice agents with speech, translation, QA, and text-to-speech tools.
Transcribe audio into text or speaker-separated transcripts with OpenAI APIs.
Transcribe audio into structured notes with speakers, timestamps, summaries, and action items.
Transcribe audio into multilingual text with optional GPT-based post-processing.