Audio · Speech EnhancementAvailable

Speech Enhancement 1.0

zilapi/se-1.0 · by InverseAI

Makes recorded speech clearer and closer: for interviews, calls, lectures and voice-overs. Results are delivered as MP3, up to 320 kbps.

Speech enhancement API

POST /v1/audio/enhance takes a voice recording and returns speech that sounds clearer and closer to the microphone: noise, room echo (reverb) and muffled tone are reduced together. Use it when a recording needs more than noise removal, such as a laptop-mic call or a lecture recorded at the back of the room.

What developers use it for

Make interviews, lectures and voice-overs sound closer and clearer
Improve call and meeting recordings captured on laptop or phone microphones
Restore old or low-quality speech recordings
Enhance speech before transcription, captioning or dubbing

Create a job

One request: POST /v1/audio/enhance with the audio's input_url (or the file itself as multipart, up to 50 MB) and a webhook_url. We fetch it, run zilapi/se-1.0 and POST job.succeeded to your URL. The quickstart has every step.

curl -s https://api.zilapi.com/v1/audio/enhance \
  -H "Authorization: Bearer $ZILAPI_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"input_url": "https://example.com/episode-142.wav",
       "model": "zilapi/se-1.0",
       "webhook_url": "https://your-app.example.com/hooks/zilapi"}' \
  > job.json
JOB_ID=$(jq -r .id job.json)

Outputs

A succeeded job has one file, audio. Download it with GET /v1/jobs/{id}/output. <stem> is your input's name without its extension.

Outputs of zilapi/se-1.0
name	Filename	Contains
audio	<stem>-enhanced.mp3	The enhanced speech, MP3, up to 320 kbps

curl -s "https://api.zilapi.com/v1/jobs/$JOB_ID/output?name=audio" -H "Authorization: Bearer $ZILAPI_KEY" > output.json
curl -o "$(jq -r .filename output.json)" "$(jq -r .url output.json)"   # <stem>-enhanced.mp3

Limits and formats

Provider	InverseAI
Input formats	Common audio: WAV, MP3, M4A/AAC, FLAC, OGG and more, or the audio of a video
Max duration	6 h per file (21,600 s)
Max file size	5 GB (5,368,709,120 bytes)
Direct upload	Up to 50 MB in the job request itself (multipart)
Output	1 file, MP3, up to 320 kbps
Billing	Per second of input, 1-second minimum per job
Price	$0.043 / audio min ≈ $0.000717 / s
Retention	Input deleted 3 days after it is ready; outputs 7 days after the job succeeds

Parameters

Field	Type	Description
input_url	string	An https URL we fetch (up to 5 GB, 6 h). Send this or `file`.
file	string	A ready `file_…` id from `POST /v1/files`; or, in a multipart request, the audio itself (up to 50 MB).
model	string	Optional. `zilapi/se-1.0`, the default for Speech Enhancement.
webhook_url	string	Optional. An https URL that receives this job's `job.*` event, signed. See Webhooks.

Speech enhancement API: questions

How much does the speech enhancement API cost?

$0.043 per audio minute, billed per second of input. Failed jobs are free.

How is it different from noise removal?

Noise Removal takes out background noise. Speech Enhancement also reduces reverb and muffling, so the voice sounds closer and clearer. It is made for speech; use Noise Removal for music.

What do I get back?

One MP3, up to 320 kbps. Inputs up to 6 hours or 5 GB by URL, or 50 MB uploaded in the request.

Compare every model on the pricing page, read the step-by-step guide, or start with the quickstart.