Transcription model
Universal 3.5 Pro
assemblyai/universal-3-5-pro
assemblyai/universal-3-5-pro is a speech-to-text model from Assemblyai you can call on the OceanToken API.
Price card, similar models and questions answered: Universal 3.5 Pro on oceantoken.ai.
At a glance
| Model ID | assemblyai/universal-3-5-pro |
|---|---|
| Type | Transcription |
| Publisher | Assemblyai |
| Price | On oceantoken.ai |
| Endpoint | /v1/audio/transcriptions |
| API shape | OpenAI-compatible |
| In the catalog since | 2026-09-22 |
API
POST /v1/audio/transcriptions, multipart/form-data. Base URL https://api.oceantoken.ai, your OceanToken key as the bearer token. The OpenAI SDKs work unchanged; see the Quickstart.
Download this spec (JSON) · llms.txt for AI assistants
Transcribe a file
- curl
- Python
- JavaScript
curl https://api.oceantoken.ai/v1/audio/transcriptions \
-H "Authorization: Bearer $OCEANTOKEN_API_KEY" \
-F model="assemblyai/universal-3-5-pro" -F file=@meeting.mp3
import os
from openai import OpenAI
client = OpenAI(base_url="https://api.oceantoken.ai/v1", api_key=os.environ["OCEANTOKEN_API_KEY"])
with open("meeting.mp3", "rb") as f:
result = client.audio.transcriptions.create(model="assemblyai/universal-3-5-pro", file=f)
print(result.text)
import fs from 'node:fs';
import OpenAI from 'openai';
const client = new OpenAI({baseURL: 'https://api.oceantoken.ai/v1', apiKey: process.env.OCEANTOKEN_API_KEY});
const result = await client.audio.transcriptions.create({model: 'assemblyai/universal-3-5-pro', file: fs.createReadStream('meeting.mp3')});
console.log(result.text);
Request parameters
Only what this model takes. Anything else in the request is left out before it reaches the model.
| Parameter | Type | Description |
|---|---|---|
filerequired | binary | The audio: mp3, m4a, wav, webm and other common formats. |
modelrequired | string | This model's ID. |
language | string | ISO-639-1 code such as en; improves accuracy. |
prompt | string | Names and spellings to expect. |
response_format | string json, text, verbose_json, srt, vtt default "json" | Models differ in which they offer. |
Response
| Field | Type | Description |
|---|---|---|
text | string | The transcript. |
Example response
{
"text": "Hello and welcome."
}
More examples and how errors and billing work: Speech and transcription.
Compared with similar models
Transcription models on OceanToken in the same price range as assemblyai/universal-3-5-pro. Compare their prices on oceantoken.ai.
| Model | Publisher | Context |
|---|---|---|
Universal 3.5 Proassemblyai/universal-3-5-pro | Assemblyai | — |
GPT Transcribeopenai/gpt-transcribe | OpenAI | — |
Nova 3deepgram/nova-3 | Deepgram | — |
Transcribe 1fish-audio/transcribe-1 | Fish Audio | — |
Use it
Create an account Price on oceantoken.ai
The facts on this page were read from the live OceanToken catalog on 2026-11-05 (UTC), when the documentation was built. Prices are published on oceantoken.ai.