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

# Create Speech

> Convert text to natural-sounding audio. Choose from 6 voices and 5 audio formats.

<ParamField body="model" type="string" required>
  TTS model. `tts-1` (faster, lower quality) or `tts-1-hd` (slower, higher fidelity).
</ParamField>

<ParamField body="input" type="string" required>
  Text to convert to speech. Maximum 4096 characters.
</ParamField>

<ParamField body="voice" type="string" required>
  Voice preset. Options: `alloy`, `echo`, `fable`, `onyx`, `nova`, `shimmer`.

  * `alloy` — neutral, versatile
  * `echo` — male, authoritative
  * `fable` — British accent, storytelling
  * `onyx` — deep, powerful
  * `nova` — female, friendly
  * `shimmer` — female, soft
</ParamField>

<ParamField body="response_format" type="string" default="mp3">
  Audio format. Options: `mp3`, `opus`, `aac`, `flac`, `wav`. Use `opus` for lowest latency.
</ParamField>

<ParamField body="speed" type="number" default="1.0">
  Playback speed. Range: `0.25` to `4.0`. `1.0` = normal speed.
</ParamField>

<RequestExample>
  ```bash cURL theme={null}
  curl https://www.samuraiapi.in/v1/audio/speech \
    -H "Authorization: Bearer $SAMURAI_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "tts-1-hd",
      "voice": "nova",
      "input": "The way of the samurai is found in death.",
      "speed": 0.9
    }' \
    --output speech.mp3
  ```

  ```python Python theme={null}
  from pathlib import Path

  response = client.audio.speech.create(
      model="tts-1-hd",
      voice="nova",
      input="The way of the samurai is found in death.",
      speed=0.9
  )
  response.stream_to_file(Path("speech.mp3"))
  ```
</RequestExample>

<ResponseExample>
  ```
  Binary audio file (MP3)
  Content-Type: audio/mpeg
  ```
</ResponseExample>