Create transcriptions

The OpenAI-compatible STT endpoint (POST /v1/audio/transcriptions, multipart: file + model [+ language + response_format]).

POST /v1/audio/transcriptions

AI → · All API references → · Get started →

Address	`https://api.hanzo.ai/v1/audio/transcriptions`
Method	`POST`
Operation	`post_audio_transcriptions`
Auth	`Authorization: Bearer $HANZO_API_KEY`

The OpenAI-compatible STT endpoint (POST /v1/audio/transcriptions, multipart: file + model [+ language + response_format]). It mirrors AudioSpeech exactly: authenticate the caller, resolve model to its STT provider through the SAME model-route resolution (so the in-cluster speech service — or any BYO node registered as an STT provider — works transparently), transcribe, and return the OpenAI body. This is the ONE way to transcribe: OpenAI-shaped, with no store coupling, so a caller needs no chat to be heard.

Request

The document declares no body for POST /v1/audio/transcriptions. The handler is typed in cloud but its shape is not yet emitted, so the fields are not listed here — ask MCP's describe for post_audio_transcriptions, which answers from the running route.

Response

Status	Body	Meaning
`200`	openai.AudioResponse	Success.
`401`	—	No credential, or one this service does not accept.
`403`	—	A valid credential that may not do this.

200 body — 20 fields.

Field	In	Type	Always
`duration`	body	number	—
`language`	body	string	—
`segments`	body	object[]	—
`segments[].avg_logprob`	body	number	—
`segments[].compression_ratio`	body	number	—
`segments[].end`	body	number	—
`segments[].id`	body	integer	—
`segments[].no_speech_prob`	body	number	—
`segments[].seek`	body	integer	—
`segments[].start`	body	number	—
`segments[].temperature`	body	number	—
`segments[].text`	body	string	—
`segments[].tokens`	body	integer[]	—
`segments[].transient`	body	boolean	—
`task`	body	string	—
`text`	body	string	—
`words`	body	object[]	—
`words[].end`	body	number	—
`words[].start`	body	number	—
`words[].word`	body	string	—

Failure carries the platform error shape — see Errors.

Examples

CLI

SDK

HTTP

MCP

hanzo audio transcriptions

.ts

.py

.go

.rs

.java

import { Configuration, AiApi } from 'hanzoai';

const api = new AiApi(new Configuration({ accessToken: process.env.HANZO_API_KEY }));
const { data } = await api.postAudioTranscriptions();

from hanzoai.cloud import ApiClient, Configuration
from hanzoai.cloud.api import AiApi

client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"]))
result = AiApi(client).post_audio_transcriptions()

cfg := hanzoai.NewConfiguration()
cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY"))
client := hanzoai.NewAPIClient(cfg)

resp, _, err := client.AiAPI.PostAudioTranscriptions(context.Background()).Execute()
if err != nil {
	return err
}

use hanzo_client::apis::{configuration::Configuration, ai_api};

let mut cfg = Configuration::new();
cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok();

let result = ai_api::post_audio_transcriptions(&cfg, Default::default()).await?;

import ai.hanzo.cloud.ApiClient;
import ai.hanzo.cloud.api.AiApi;

ApiClient client = new ApiClient();
client.setBearerToken(System.getenv("HANZO_API_KEY"));

var result = new AiApi(client).postAudioTranscriptions();

curl -X POST https://api.hanzo.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $HANZO_API_KEY"

MCP declares no tool for ai — tools/list on https://api.hanzo.ai/v1/mcp names the products it does reach. Use HTTP or an SDK.

AI API · All Hanzo APIs · Interactive reference

Was this page useful?

PreviousCreate public — POST /v1/audio/transcriptions/public NextCreate voice