Skip to main content

​
Overview

The text_to_sound_effects client provides methods to generate realistic sound effects from text descriptions using advanced AI models.

​
convert()

Generate sound effects from a text description.

​
Method Signature

client.text_to_sound_effects.convert(
    text: str,
    output_format: Optional[AllowedOutputFormats] = None,
    loop: Optional[bool] = None,
    duration_seconds: Optional[float] = None,
    prompt_influence: Optional[float] = None,
    model_id: Optional[str] = None,
    request_options: Optional[RequestOptions] = None
) -> Iterator[bytes]

​
Parameters

​
text
str
required
The text description of the sound effect you want to generate.
​
output_format
AllowedOutputFormats
Output format of the generated audio. Formatted as codec_sample_rate_bitrate.Examples:
  • mp3_22050_32 - MP3 with 22.05kHz sample rate at 32kbps
  • mp3_44100_192 - MP3 with 44.1kHz at 192kbps (requires Creator tier+)
  • pcm_44100 - PCM with 44.1kHz (requires Pro tier+)
  • ulaw_8000 - μ-law format commonly used for Twilio
​
loop
bool
Whether the sound effect should be designed to loop seamlessly.
​
duration_seconds
float
Target duration of the generated sound effect in seconds.
​
prompt_influence
float
How closely the generation should follow the text prompt. Range: 0.0 to 1.0.
​
model_id
str
The ID of the sound effects model to use.
​
request_options
RequestOptions
Request-specific configuration.

​
Returns

Iterator[bytes] - Streaming audio data in the specified format.

​
Example

from elevenlabs import ElevenLabs

client = ElevenLabs(api_key="YOUR_API_KEY")

# Generate a sound effect
audio = client.text_to_sound_effects.convert(
    text="thunder crashing in the distance",
    duration_seconds=3.0,
    loop=True
)

# Save to file
with open("thunder.mp3", "wb") as f:
    for chunk in audio:
        f.write(chunk)

​
Use Cases

  • Video Production: Add realistic sound effects to videos
  • Voice-overs: Enhance narration with ambient sounds
  • Game Development: Generate dynamic sound effects for games
  • Podcasts: Create custom audio branding and transitions

​
Async Usage

from elevenlabs import AsyncElevenLabs
import asyncio

async def generate_sound():
    client = AsyncElevenLabs(api_key="YOUR_API_KEY")
    
    audio = await client.text_to_sound_effects.convert(
        text="rain falling on a tin roof",
        duration_seconds=5.0
    )
    
    chunks = []
    async for chunk in audio:
        chunks.append(chunk)
    
    return b"".join(chunks)

audio_data = asyncio.run(generate_sound())

Build docs developers (and LLMs) love

Get started for freeTalk to us