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

# Welcome to Bland Speech

> A humanlike text-to-speech model built for real conversations.

Bland Speech is a text-to-speech model built for live conversation. It captures the breath, pacing, hesitation, and emotional movement that make speech feel real, so a synthetic voice reads like a person rather than a narrator.

Most TTS is built around clean studio reads: audiobooks, voiceover, promo. Bland Speech is built for the moments where synthetic speech usually breaks: pauses, names, numbers, emotion, mid-sentence changes, and everything else a phone call throws at a voice.

## What makes it different

<CardGroup cols={2}>
  <Card title="Human-like realism" icon="user-large">
    Breath, pacing, hesitation, cadence, emotional movement. Not a polished studio read, a voice that sounds like a person.
  </Card>

  <Card title="Built for real conversations" icon="phone">
    Timing, interruptions, mid-thought changes. Tuned for live speech, not narration.
  </Card>

  <Card title="Audio realism as the goal" icon="waveform">
    Judged on how real the audio sounds against the same text and the same voice, not on a checklist of features.
  </Card>

  <Card title="Direct in plain language" icon="wand-magic-sparkles">
    Say `warmer`, `more tired`, or `slower at the end`. No prompt tags, no sliders, no grammar to memorize.
  </Card>
</CardGroup>

## Start here

<CardGroup cols={2}>
  <Card title="Bland TTS SDK" icon="terminal" href="/sdks/bland-tts">
    Focused CLI, Node library, and MCP server. The fastest path from install to first audio.
  </Card>

  <Card title="Synthesize Speech" icon="code" href="/api-v2/post/tts">
    `POST /v2/tts`. Turn text into audio in one request, stream the frames back as they render.
  </Card>

  <Card title="Clone a voice" icon="microphone" href="/api-v1/post/clone">
    Bring your own voice with a short reference audio and use it in any synthesis.
  </Card>

  <Card title="Browse voices" icon="list" href="/api-v1/get/voices">
    Bland's curated library plus every voice your org has cloned.
  </Card>
</CardGroup>

## Try it

Create an account at [studio.bland.ai/signup](https://studio.bland.ai/signup), grab an API key, then:

```bash theme={null}
curl -X POST https://api.bland.ai/v2/tts \
  -H "authorization: YOUR_API_KEY" \
  -H "content-type: application/json" \
  -d '{"text": "Hey, this actually sounds like a person.", "voice": "maya"}' \
  --output hello.wav
```

That returns a `wav` you can play. Swap `voice` for any UUID from [List Voices](/api-v1/get/voices).