> ## 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.

# Bland TTS

> A focused TTS and voice toolkit for Bland AI — CLI, Node library, and MCP server in one lightweight package.

`bland-tts` is a focused text-to-speech and voice toolkit for Bland AI. Three modes ship in one package: a CLI, a Node library (`BlandTtsClient`), and an MCP server.

## bland-tts vs. bland-cli

[`bland-cli`](/sdks/cli) is the full kitchen sink — calls, pathways, scenarios, knowledge bases, personas, batch campaigns. Big install, broad surface.

`bland-tts` is for projects that just need speech: a podcast generator, a voice notification system, an experimentation harness for prompt phrasing. Tiny dependency footprint (`chalk`, `commander`, `ora`). Library-first design means you can drop the MCP server and import `BlandTtsClient` directly.

If you need the full Bland API surface, use `bland-cli`. If you only need speech synthesis and voice management, use `bland-tts`.

## Install

```bash theme={null}
# Install globally for CLI use
npm install -g bland-tts

# Or install per-project as a library
npm install bland-tts

# Or run without installing
npx bland-tts speak "hello world"
```

**Requirements:** Node.js 20+

## Authentication

Set your Bland API key in the environment:

```bash theme={null}
export BLAND_API_KEY=org_your_key_here
```

You can also pass `apiKey` directly to the `BlandTtsClient` constructor when using the library.

## Default voices

When you call `speak()` without specifying a voice, one is picked at random from:

* **Karen**
* **Valentine Experimental**
* **Willow**

To lock a single default for a process, pass `defaultVoice` to the client constructor. To opt out and let the server choose, pass `defaultVoice: null`. The CLI surfaces which voice was actually used (`voice_used` in `--json`, dimmed line otherwise).

## CLI

```bash theme={null}
# Speak some text — voice picked from the rotation
bland-tts speak "Hey, thanks for calling Maple Vet"
# → "voice: Karen" (or Valentine Experimental, or Willow)

# Pin a specific voice
bland-tts speak "Hello world" --voice maya -o hello.mp3
bland-tts speak "Hola" --language es --json

# Voices
bland-tts voices                       # list
bland-tts voices --custom              # only voices you've cloned
bland-tts voice maya                   # full details for one voice

# Voice cloning (BTTS v2)
bland-tts clone "MyVoice" sample1.wav sample2.wav
bland-tts rename <voice_id> "NewName"
bland-tts delete <voice_id>

# Browse stored TTS generations (auto-stored from `speak`)
bland-tts samples list
bland-tts samples list --voice <voice_id> --limit 10
bland-tts samples get <sample_id> -o sample.mp3
```

Every command supports `--json` for scripting.

## Library

```ts theme={null}
import { BlandTtsClient } from "bland-tts";
import fs from "node:fs/promises";

const tts = new BlandTtsClient(); // reads BLAND_API_KEY from env

// One-shot synthesis to a file
const { audio } = await tts.speakToBuffer({
  text: "Hello world",
  voice: "maya",
});
await fs.writeFile("out.mp3", audio);

// Just get the URL
const res = await tts.speak({ text: "Hi", voice: "nat", language: "en" });
console.log(res.url);

// Voices
const voices = await tts.listVoices();
const maya = await tts.getVoice("maya");

// Clone
await tts.cloneVoice({
  name: "MyVoice",
  samples: [
    { filename: "a.wav", content: await fs.readFile("a.wav") },
  ],
});

// Manage
await tts.renameVoice(voiceId, "NewName");
await tts.deleteVoice(voiceId);

// Stored samples
const recent = await tts.listSamples({ limit: 10 });
const sample = await tts.getSample(recent[0].id);
```

### Library API

| Method                                     | Endpoint                    | Notes                                              |
| ------------------------------------------ | --------------------------- | -------------------------------------------------- |
| `speak({text, voice?, language?})`         | `POST /v1/speak`            | Returns `{url, sample_id}`. Auto-stores.           |
| `speakToBuffer({...})`                     | (same) + download           | One-call synth-and-download. Returns `Uint8Array`. |
| `listVoices()`                             | `GET /v1/voices`            | All voices on your account.                        |
| `getVoice(idOrName)`                       | `GET /v1/voices/:id`        | Accepts UUID or name.                              |
| `cloneVoice({name, samples})`              | `POST /v1/voices/clone`     | Multipart. `name` ≤ 30 chars.                      |
| `renameVoice(id, name)`                    | `PATCH /v1/voices/:id`      |                                                    |
| `deleteVoice(id)`                          | `DELETE /v1/voices/:id`     | Permanent.                                         |
| `listSamples({voiceId?, limit?, offset?})` | `GET /v1/speak/samples`     | Past `speak()` outputs.                            |
| `getSample(id)`                            | `GET /v1/speak/samples/:id` | One sample by ID.                                  |

All methods throw `BlandApiError` (with `.status` and `.body`) on API failures.

## MCP server

Hook into Claude Code, Cursor, Claude Desktop, Windsurf, and other MCP-compatible clients.

Add to `~/.config/claude-code/mcp.json` (or your client's equivalent):

```json theme={null}
{
  "mcpServers": {
    "bland-tts": {
      "command": "npx",
      "args": ["-y", "bland-tts", "mcp"],
      "env": { "BLAND_API_KEY": "org_your_key_here" }
    }
  }
}
```

### Tools exposed

| Tool               | Does what                                  |
| ------------------ | ------------------------------------------ |
| `tts_speak`        | Convert text to speech with a chosen voice |
| `tts_voices_list`  | List voices on your account                |
| `tts_voice_get`    | Details for one voice (by ID or name)      |
| `tts_voice_rename` | Rename a cloned voice                      |
| `tts_voice_delete` | Delete a cloned voice                      |
| `tts_samples_list` | Browse past TTS generations                |
| `tts_sample_get`   | Fetch one stored generation                |

<Note>
  Voice cloning is intentionally CLI-only since multipart file uploads aren't well-suited to stdio JSON-RPC. Use `bland-tts clone <name> <files...>` for that.
</Note>

## Environment Variables

| Variable        | Purpose            |
| --------------- | ------------------ |
| `BLAND_API_KEY` | Your Bland API key |

***

Docs for agents: [llms.txt](/llms.txt)