Audio and STT

LatentKit supports audio input and speech-to-text through routed /v1 endpoints. Use /v1/transcription for transcription and /v1/translation for audio translation. Queued transcription is available through /v1/transcription/jobs for enabled workspaces.

For the reverse direction — generating spoken audio from text — see Speech (Text-to-Speech).

Your application still authenticates with one LatentKit API key. The key's assigned route must include an audio_input model, such as OpenAI gpt-4o-transcribe, gpt-4o-mini-transcribe, gpt-4o-transcribe-diarize, or whisper-1.

Batch Transcription

POST /v1/transcription accepts JSON or multipart form data.

Multipart upload

Use multipart form data when your backend has a local audio file.

curl https://ai.latentkit.com/v1/transcription \
  -H "Authorization: Bearer $LATENTKIT_API_KEY" \
  -F [email protected] \
  -F language=en \
  -F response_format=json

JSON input

Use JSON when your backend already has base64 audio or an approved audio URL.

curl https://ai.latentkit.com/v1/transcription \
  -H "Authorization: Bearer $LATENTKIT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio": {
      "base64": "<base64-audio>",
      "media_type": "audio/mpeg",
      "filename": "meeting.mp3"
    },
    "language": "en",
    "response_format": "json"
  }'

Required audio input can be one of:

multipart file
audio.base64
audio.data
audio.url
base64 input

Audio files are capped at 25 MiB by default. Supported OpenAI-compatible upload formats include mp3, mp4, mpeg, mpga, m4a, wav, and webm.

Common STT fields:

mode: batch, async, or realtime
language
diarization
speaker_count_hint
timestamps: word, segment, or both
custom_vocabulary / keyterms
smart_formatting
detect_language
profanity_filter
redaction
multichannel

Required features are checked before provider selection. If a fallback route would drop a required feature such as diarization, timestamps, redaction, realtime mode, or keyterms, routing fails closed instead of silently degrading the transcript.

OpenAI Transcribe Models

OpenAI-compatible transcription routes are first-class audio_input routes in LatentKit.

Model	Typical use	Notes
`gpt-4o-transcribe`	Higher-quality batch transcription	Supports prompt context and JSON or text responses
`gpt-4o-mini-transcribe`	Lower-cost batch transcription	Supports prompt context and JSON or text responses
`gpt-4o-transcribe-diarize`	Speaker-aware transcripts	Use with `diarization` and `response_format: "diarized_json"` when configured on the route
`whisper-1`	Compatibility, translations, and timestamp-heavy workflows	Supports verbose timestamp formats where the upstream model allows them

LatentKit decides the exact provider/model from the route assigned to the API key. Do not send provider or model in application requests; transcription route-control fields are rejected, including nested audio.provider and audio.model.

SDK Examples

import { LatentKit } from '@latentkit/sdk';

const client = new LatentKit({
  apiKey: process.env.LATENTKIT_API_KEY!,
});

const transcript = await client.transcription.create({
  audio: {
    base64: '<base64-audio>',
    media_type: 'audio/mpeg',
    filename: 'meeting.mp3',
  },
  language: 'en',
  prompt: 'Meeting about product roadmap and LatentKit routing.',
  response_format: 'json',
});

console.log(transcript.content);

import os
from latentkit import LatentKit

with LatentKit(api_key=os.environ["LATENTKIT_API_KEY"]) as client:
    transcript = client.transcription.create(
        audio={
            "base64": "<base64-audio>",
            "media_type": "audio/mpeg",
            "filename": "meeting.mp3",
        },
        language="en",
        prompt="Meeting about product roadmap and LatentKit routing.",
        response_format="json",
    )

print(transcript["content"])

Response Shape

STT responses use the same routed response envelope as chat responses and may include:

text in content
status
language
language_confidence
duration_seconds
segments
words
warnings
usage.audio_seconds
usage.billable_audio_seconds

Available providers

The live provider and model list depends on your workspace connections and plan. Open Connections and Routes in the console to see which audio_input models can be assigned to your key.

Audio URL Safety

Remote audio.url input may be disabled for your workspace. When it is available, the URL must use HTTPS, match an approved host, return a supported audio type and declared size, and remain within the service limits. Use a multipart upload or base64 input when remote URLs are unavailable.

Managed Billing

Platform Access audio availability depends on the selected model, plan, and supported usage metering. BYOK uses your provider account. Check the route and estimated cost in the console before sending production audio workloads.

On this page