> ## Documentation Index
> Fetch the complete documentation index at: https://docs.audiopod.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenAI Compatibility

> Point your existing OpenAI audio code at AudioPod by changing only the base URL and API key. Drop-in /v1/audio/speech, /v1/audio/transcriptions and /v1/audio/translations.

## Overview

AudioPod exposes **OpenAI-compatible audio endpoints**, so code written for the
OpenAI audio API runs against AudioPod with **two changes only**: the base URL
and the API key. Use the official OpenAI SDKs — no AudioPod-specific client
required.

| Endpoint                        | Purpose                               |
| ------------------------------- | ------------------------------------- |
| `POST /v1/audio/speech`         | Text to speech — returns audio bytes  |
| `POST /v1/audio/transcriptions` | Speech to text (source language)      |
| `POST /v1/audio/translations`   | Speech to text, translated to English |

<Note>
  These three are the only audio shapes the OpenAI API defines. AudioPod's other
  capabilities — stem separation, music generation, speaker separation, voice
  cloning, noise reduction, media conversion — are available through the native
  [REST API](/api-reference/text-to-speech), [SDKs](/sdks/overview) and
  [MCP server](/sdks/mcp).
</Note>

## Configuration

Set the base URL to `https://api.audiopod.ai/api/v1` and use your AudioPod API
key (starts with `ap_`). Create one in your
[dashboard](https://audiopod.ai/dashboard/account/api-keys).

<CodeGroup>
  ```python Python theme={null}
  from openai import OpenAI

  client = OpenAI(
      base_url="https://api.audiopod.ai/api/v1",
      api_key="ap_your_api_key",
  )
  ```

  ```javascript Node.js theme={null}
  import OpenAI from "openai";

  const client = new OpenAI({
    baseURL: "https://api.audiopod.ai/api/v1",
    apiKey: "ap_your_api_key",
  });
  ```
</CodeGroup>

Calls are billed to your [API wallet](/account/api-wallet) (prepaid, in USD).
Nothing is charged for a request that fails — you're only billed once audio or
a transcript is produced.

## Text to speech

`POST /v1/audio/speech` synthesizes `input` with the requested `voice` and
returns the audio bytes.

<CodeGroup>
  ```python Python theme={null}
  response = client.audio.speech.create(
      model="tts-1",
      voice="nova",
      input="Hello from AudioPod.",
      response_format="mp3",  # mp3 | opus | aac | flac | wav | pcm
  )
  response.stream_to_file("speech.mp3")
  ```

  ```bash cURL theme={null}
  curl https://api.audiopod.ai/api/v1/audio/speech \
    -H "Authorization: Bearer ap_your_api_key" \
    -H "Content-Type: application/json" \
    -d '{"model":"tts-1","voice":"nova","input":"Hello from AudioPod."}' \
    --output speech.mp3
  ```
</CodeGroup>

| Field             | Notes                                                                                                 |
| ----------------- | ----------------------------------------------------------------------------------------------------- |
| `input`           | The text to synthesize (required).                                                                    |
| `voice`           | A voice name (e.g. `nova`, `onyx`) or a voice ID. List options at `GET /api/v1/voice/voice-profiles`. |
| `response_format` | `mp3` (default), `opus`, `aac`, `flac`, `wav`, `pcm`.                                                 |
| `speed`           | `0.25`–`4.0` (default `1.0`).                                                                         |

## Transcription

`POST /v1/audio/transcriptions` converts speech to text in the source language.

<CodeGroup>
  ```python Python theme={null}
  with open("audio.mp3", "rb") as f:
      transcript = client.audio.transcriptions.create(
          model="whisper-1",
          file=f,
          response_format="json",  # json | text | verbose_json | srt | vtt
      )
  print(transcript.text)
  ```

  ```bash cURL theme={null}
  curl https://api.audiopod.ai/api/v1/audio/transcriptions \
    -H "Authorization: Bearer ap_your_api_key" \
    -F file="@audio.mp3" \
    -F model="whisper-1"
  ```
</CodeGroup>

| Field             | Notes                                                            |
| ----------------- | ---------------------------------------------------------------- |
| `file`            | The audio file to transcribe (required).                         |
| `language`        | Optional ISO-639-1 hint (e.g. `en`); auto-detected when omitted. |
| `prompt`          | Optional text to guide the transcription.                        |
| `response_format` | `json` (default), `text`, `verbose_json`, `srt`, `vtt`.          |

`verbose_json` includes the detected `language`, `duration`, and segment-level
timestamps.

## Translation

`POST /v1/audio/translations` converts speech in any language to **English**
text. The request shape matches transcription (the `language` field is not used
— output is always English).

<CodeGroup>
  ```python Python theme={null}
  with open("spanish.mp3", "rb") as f:
      translation = client.audio.translations.create(
          model="whisper-1",
          file=f,
      )
  print(translation.text)  # English
  ```

  ```bash cURL theme={null}
  curl https://api.audiopod.ai/api/v1/audio/translations \
    -H "Authorization: Bearer ap_your_api_key" \
    -F file="@spanish.mp3" \
    -F model="whisper-1"
  ```
</CodeGroup>

## Notes & differences

* **Auth**: pass your AudioPod API key as a Bearer token (the scheme the OpenAI
  SDKs use). `X-API-Key` is also accepted.
* **Models**: the `model` field is accepted for compatibility. AudioPod selects
  the appropriate engine for each request; you don't need to change `model`
  strings when migrating.
* **Voices**: common OpenAI voice names map to AudioPod voices. Browse the full
  catalog — including custom voice clones — at `GET /api/v1/voice/voice-profiles`
  and pass any voice name or ID as `voice`.
* **Errors** follow the OpenAI shape (`{ "error": { "message", "type", "param" } }`),
  so existing OpenAI error handling works unchanged.

## Beyond OpenAI

Already migrated? AudioPod does more than the OpenAI audio API. Explore
[stem separation](/api-reference/stem-splitter),
[music generation](/api-reference/music/overview),
[speaker separation](/api-reference/speaker-separation), and
[voice cloning](/api-reference/voice-management) through the native API and SDKs.