High-performance speech-to-text, speaker diarization, audio intelligence, and mfrSpeech LLM engine.
Click or Drag Audio File
MP3, WAV, M4A, OGG, FLAC (Max 500MB)
Real-time Pipeline Ready
No output generated yet. Upload an audio file or record mic to begin processing.
Execute custom LLM prompts, ask questions, or extract action items directly over your audio transcripts.
mfrSpeech AI output will appear here.
Use the snippets below to integrate mfrSpeech AI Engine seamlessly into your application.
Official mfrSpeech AI Engine API specifications for audio transcription, speaker diarization, and mfrSpeech LLM.
| Method | mfrSpeech Endpoint | Description | Mandatory Headers |
|---|---|---|---|
| POST | /api/upload |
Upload raw audio file binary (buffer / form-data) to CDN storage. | X-Mfr-Key (Optional) |
| POST | /api/transcript |
Submit new transcription request (diarization, sentiment, summary). | Content-Type: application/json |
| GET | /api/transcript/:id |
Fetch transcript status and complete intelligence results (JSON). | - |
| GET | /api/transcript/:id/srt |
Download SRT format subtitle file. | - |
| GET | /api/transcript/:id/vtt |
Download WebVTT format subtitle file. | - |
| POST | /api/speechmind/task |
Execute custom LLM prompt instructions (mfrSpeech AI). | Content-Type: application/json |
| POST | /api/speechmind/qa |
Question-Answering over transcript text (mfrSpeech Q&A). | Content-Type: application/json |
| DELETE | /api/transcript/:id |
Delete transcript resource from server storage. | - |