;
## Overview
Generate speech with different language accents. The `language` parameter controls the accent/pronunciation style of the output — see [Language Support](/language-support) for the full per-model locale list.
The TTS API speaks the text you provide - it does **not** translate. To speak in a different language, provide input text in that language. For automatic translation + speech, use the [Translated TTS API](/api-reference/endpoint/create-translated-tts).
### Hear the Difference
Same text, different accents - all with the same voice:
### Prerequisites
Sign up at [CAMB.AI Studio](https://studio.camb.ai) if you haven't already.
Go to **Settings → API Keys** in Studio and copy your key. See [Authentication](/getting-started/authentication) for details.
```bash Python theme={null}
pip install camb-sdk
```
```bash TypeScript theme={null}
npm install @camb-ai/sdk
```
Skip this step if you're using the [direct API](/tutorials/direct-api).
```bash theme={null}
export CAMB_API_KEY="your_api_key_here"
```
***
## Code
```python Python theme={null}
import os
import asyncio
from camb.client import AsyncCambAI, save_async_stream_to_file
from camb.types import StreamTtsOutputConfiguration
client = AsyncCambAI(api_key=os.getenv("CAMB_API_KEY"))
# Languages to generate
LANGUAGES = [
("en-us", "English"),
("es-es", "Spanish"),
("fr-fr", "French"),
("pt-br", "Portuguese"),
]
async def generate_language(text, lang_code, lang_name):
"""Generate TTS for a single language"""
print(f"Generating {lang_name}...")
response = client.text_to_speech.tts(
text=text,
language=lang_code,
speech_model="mars-8.1-flash-beta",
voice_id=144300, # Replace with your voice ID
output_configuration=StreamTtsOutputConfiguration(format="wav")
)
filename = f"output_{lang_code}.wav"
await save_async_stream_to_file(response, filename)
print(f" Saved: {filename}")
return filename
async def main():
text = "Welcome to our service. We're glad to have you here."
print(f"Generating TTS in {len(LANGUAGES)} languages...\n")
# Generate all languages concurrently
tasks = [
generate_language(text, code, name)
for code, name in LANGUAGES
]
files = await asyncio.gather(*tasks)
print(f"\nDone! Generated {len(files)} audio files.")
asyncio.run(main())
```
```javascript TypeScript theme={null}
import { CambClient, saveStreamToFile } from '@camb-ai/sdk';
const client = new CambClient({
apiKey: process.env.CAMB_API_KEY
});
// Languages to generate
const LANGUAGES = [
{ code: 'en-us', name: 'English' },
{ code: 'es-es', name: 'Spanish' },
{ code: 'fr-fr', name: 'French' },
{ code: 'pt-br', name: 'Portuguese' },
];
async function generateLanguage(text, langCode, langName) {
console.log(`Generating ${langName}...`);
const response = await client.textToSpeech.tts({
text: text,
language: langCode,
speech_model: 'mars-8.1-flash-beta',
voice_id: 144300, // Replace with your voice ID
output_configuration: {
format: 'wav'
},
});
const filename = `output_${langCode}.wav`;
await saveStreamToFile(response, filename);
console.log(` Saved: ${filename}`);
return filename;
}
async function main() {
const text = "Welcome to our service. We're glad to have you here.";
console.log(`Generating TTS in ${LANGUAGES.length} languages...\n`);
// Generate all languages concurrently
const promises = LANGUAGES.map(lang =>
generateLanguage(text, lang.code, lang.name)
);
const files = await Promise.all(promises);
console.log(`\nDone! Generated ${files.length} audio files.`);
}
main();
```
***
## Supported Accents
Over 140 language accents are supported across CAMB.AI TTS. Common codes:
| Accent | Code |
| ------------------- | ------- |
| English (US) | `en-us` |
| English (UK) | `en-gb` |
| Spanish (Spain) | `es-es` |
| Spanish (Mexico) | `es-mx` |
| French | `fr-fr` |
| German | `de-de` |
| Italian | `it-it` |
| Portuguese (Brazil) | `pt-br` |
| Japanese | `ja-jp` |
| Korean | `ko-kr` |
| Chinese (Mandarin) | `zh-cn` |
| Hindi | `hi-in` |
| Arabic | `ar-sa` |
| Russian | `ru-ru` |
See [API Reference](/api-reference/endpoint/get-target-languages) for the broader TTS language list.
If you are using `POST /tts-stream`, check the streaming API reference for endpoint-specific support and model-specific constraints.
***
## Use Cases
***
## Next Steps
Add emotional expression and character to your speech with mars-instruct.
Translate text and generate speech in the target language.
Clone a voice from reference audio.
Generate sound effects and music from text.
Full TTS streaming API specification.