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

# Audio API: Speech-to-Text and Text-to-Speech via NexLLM

> Transcribe audio files to text with POST /v1/audio/transcriptions, or generate speech with POST /v1/audio/speech — fully OpenAI-compatible.

NexLLM's audio endpoints give you access to speech-to-text transcription and text-to-speech synthesis through a single, OpenAI-compatible interface. Use the transcriptions endpoint to convert audio recordings into text, and the speech endpoint to turn written content into natural-sounding audio — all with the same API key you use for chat and embeddings.

## Endpoints

| Endpoint       | Path                            | Description                      |
| -------------- | ------------------------------- | -------------------------------- |
| Speech-to-Text | `POST /v1/audio/transcriptions` | Transcribe an audio file to text |
| Text-to-Speech | `POST /v1/audio/speech`         | Convert text to spoken audio     |

***

## Speech-to-Text: Transcriptions

### Parameters

<ParamField body="model" type="string" required>
  The transcription model to use. Use `whisper-1` for Whisper-compatible transcription.
</ParamField>

<ParamField body="file" type="file" required>
  The audio file to transcribe. Accepted formats include `mp3`, `mp4`, `mpeg`, `mpga`, `m4a`, `wav`, and `webm`. The file must be under 25 MB.
</ParamField>

<ParamField body="language" type="string">
  The [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) language code of the audio (e.g. `en`, `es`, `fr`). Providing this improves accuracy and speed. If omitted, the model detects the language automatically.
</ParamField>

<ParamField body="prompt" type="string">
  Optional text to guide the model's transcription style or provide context about the audio content.
</ParamField>

***

## Text-to-Speech

### Parameters

<ParamField body="model" type="string" required>
  The text-to-speech model to use. Use `tts-1` for standard quality or `tts-1-hd` for higher quality audio.
</ParamField>

<ParamField body="input" type="string" required>
  The text to convert to speech. Maximum length is 4,096 characters.
</ParamField>

<ParamField body="voice" type="string" required>
  The voice to use for synthesis. Available options: `alloy`, `echo`, `fable`, `onyx`, `nova`, `shimmer`.
</ParamField>

<ParamField body="response_format" type="string">
  The audio format of the output. Supported values: `mp3`, `opus`, `aac`, `flac`. Defaults to `mp3`.
</ParamField>

***

## Code Examples

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

  client = OpenAI(
      api_key="sk-xxxxxxxxxxxxxxxx",
      base_url="https://www.nexllm.ai/v1"
  )

  with open("audio.mp3", "rb") as audio_file:
      transcript = client.audio.transcriptions.create(
          model="whisper-1",
          file=audio_file
      )

  print(transcript.text)
  ```

  ```python Text-to-Speech theme={null}
  from openai import OpenAI
  from pathlib import Path

  client = OpenAI(
      api_key="sk-xxxxxxxxxxxxxxxx",
      base_url="https://www.nexllm.ai/v1"
  )

  response = client.audio.speech.create(
      model="tts-1",
      voice="alloy",
      input="Hello! Welcome to NexLLM."
  )

  Path("output.mp3").write_bytes(response.content)
  ```
</CodeGroup>

<Tip>
  For long-form content like articles or podcasts, consider splitting the text into smaller segments before calling the speech endpoint. This lets you process segments in parallel and combine the output files, reducing overall latency.
</Tip>