MediaRuntime product

Audio Processing

Convert audio formats, extract audio from video, normalize delivery loudness, trim boundary silence, prepare speech audio, and return transcripts with the same job.

Read the API documentation Try the Sandbox

AAC/M4A, MP3, Opus and speech WAV

Audio extraction from video sources

SRT and WebVTT transcripts

POST https://mediaruntime.com/v1/transcode

From source to delivered artifacts

Provide video or audio

The audio output type accepts either an audio file or a video containing an audio stream.

Select delivery processing

Copy compatible audio, encode a predictable format, normalize to -16 LUFS, trim silence, or prepare 16 kHz mono WAV.

Add transcripts when needed

Attach subtitle settings to the audio output to produce SRT, WebVTT, or both alongside the audio artifact.

What you can build

Format conversion

Deliver AAC in M4A, MP3, Opus, or copy a compatible source stream without re-encoding.

Video-to-audio

Submit a MOV, MP4, WebM, or other supported video and return only its selected audio format.

Podcast and speech cleanup

Normalize loudness, remove leading and trailing silence, or combine both operations before AAC delivery.

Transcription pipelines

Produce SRT and WebVTT transcripts or a 16 kHz mono PCM WAV prepared for downstream speech systems.

Relevant presets

audio_copy_fastaudio_aac_128kaudio_mp3_128kaudio_opus_96kaudio_loudnorm_aac_128kaudio_trim_silence_aac_128kaudio_loudnorm_trim_aac_128kaudio_whisper_prep

Example job request

Submit from a trusted server with your MediaRuntime API key. The source can be any fetchable HTTPS URL; uploading through MediaRuntime is optional.

{
  "file_url": "https://cdn.example.com/media/interview.mp4",
  "metadata": {
    "media_type": "video",
    "asset_id": "interview-0426"
  },
  "outputs": [
    {
      "type": "audio",
      "preset": "audio_aac_128k",
      "path_suffix": "audio-and-transcript",
      "subtitles": {
        "enabled": true,
        "languages": [
          "auto"
        ],
        "format": "both",
        "model": "ggml-base.bin",
        "translate_to_english": false
      }
    }
  ]
}