Transcribe audio
Supply base64 audio in input_audio.data and its actual format.
On this page
https://api.shareai.now/api/v1/audio/transcriptionsTranscribe audio
- Base URL
https://api.shareai.now- Authentication
- Bearer API key or approved OAuth access token
- Required scope
inferenceormonetization_gateway
Supply base64 audio in input_audio.data and its actual format. Supported languages, prompts, response formats and timestamp options depend on the model. This JSON endpoint does not accept multipart file uploads. The response contains the transcription and reported usage.
Before you start#
Set SHAREAI_API_KEY on your server and replace the model placeholder with a currently enabled model. Never expose the API key in browser code. The model, account, credential and provider must all permit this operation. Optional settings below require model support; the API safety bounds are not a promise that every model supports every value.
Send a request#
cURL
curl --fail-with-body --request POST "https://api.shareai.now/api/v1/audio/transcriptions" \
-H "Authorization: Bearer $SHAREAI_API_KEY" \
-H "Content-Type: application/json" \
--data '{
"model": "YOUR_ENABLED_TRANSCRIPTION_MODEL",
"input_audio": {
"data": "UklGRsQAAABXQVZFZm10IBAAAAABAAEAQB8AAIA+AAACABAAZGF0YaAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA",
"format": "wav"
}
}'Python
import json
import os
import urllib.request
payload = {'model': 'YOUR_ENABLED_TRANSCRIPTION_MODEL',
'input_audio': {'data': 'UklGRsQAAABXQVZFZm10IBAAAAABAAEAQB8AAIA+AAACABAAZGF0YaAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA',
'format': 'wav'}}
headers = {'Content-Type': 'application/json'}
headers["Authorization"] = "Bearer " + os.environ["SHAREAI_API_KEY"]
request = urllib.request.Request('https://api.shareai.now/api/v1/audio/transcriptions', data=json.dumps(payload).encode(), headers=headers, method="POST")
with urllib.request.urlopen(request, timeout=180) as response:
result = json.load(response)
print(result)TypeScript
const response = await fetch("https://api.shareai.now/api/v1/audio/transcriptions", {
method: "POST",
headers: { Authorization: `Bearer ${process.env.SHAREAI_API_KEY}`, ...{"Content-Type": "application/json"} },
body: JSON.stringify({
"model": "YOUR_ENABLED_TRANSCRIPTION_MODEL",
"input_audio": {
"data": "UklGRsQAAABXQVZFZm10IBAAAAABAAEAQB8AAIA+AAACABAAZGF0YaAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA",
"format": "wav"
}
}),
});
if (!response.ok) throw new Error(await response.text());
const result = await response.json();
console.log(result);The example contains a tiny silent WAV solely to show valid base64 transport. Replace input_audio.data with standard base64 of your own audio file; for Python use base64.b64encode(Path(“audio.wav”).read_bytes()).decode(“ascii”). Do not paste an audio URL into this field.
Request fields#
| Field | Type | Meaning and limits |
|---|---|---|
model required | string | Exact enabled public model identifier. Must declare this operation and be allowed by your credential. |
input_audio required | object | Required data and format fields. data is standard base64 of the actual audio bytes; format must match. JSON only; multipart is unsupported. Duration tariffs require WAV, MP3 or FLAC with a known timebase, at most 600 seconds combined. |
language | string | Optional model-supported language code. |
prompt | string | Optional model-supported transcription context; not an audio-generation prompt. |
response_format | string | Model-supported response format, at most 100 characters. The operation determines whether the result is JSON or binary. |
timestamp_granularities | array | Optional model-supported timestamp granularity values. Availability depends on the response format and model. |
provider | object | Optional provider routing preferences. Use provider.only for accepted provider tags, not a prefix in the model ID. Account and credential restrictions still apply. |
Read the result#
Success returns HTTP 200 with JSON. Supply base64 audio in input_audio.data and its actual format. Supported languages, prompts, response formats and timestamp options depend on the model. This JSON endpoint does not accept multipart file uploads. The response contains the transcription and reported usage.
Billing units#
Transcription uses the model’s published duration and/or token tariff. Provider-reported seconds and tokens remain separate measurements. Base64 length is not an audio duration or token count. Input-duration tariffs require self-describing WAV, MP3 or FLAC with a combined duration of at most 600 seconds; unknown or raw PCM timebases are not admitted for duration pricing.
Choose the exact enabled model identifier from Console. Its declared operation and input/output capabilities must match this endpoint; a text chat model cannot be substituted for another operation. Your credential, provider and account restrictions still apply.
Pricing and usage#
Rates are published in EUR AI credits for the selected model, provider, units and variants. Only the dimensions in its active tariff are charged. An estimate reserves credits before execution; final charges use measured usage. Prices can depend on resolution, output format or a usage band. Check Console Usage for the final ShareAI debit. Upstream cost fields and media bytes are not converted into invented token counts.
Access and errors#
Use inference for approved network-cost inference or monetization_gateway for an approved Builder markup and accepted billing terms. Identity-only access does not authorize spending. Validation, model authorization, insufficient credits, rate limits and execution failures return a structured error. After a timeout or uncertain submission, inspect Usage or the video job before creating another potentially paid request.
Last updated November 3, 2026