Implementation:Elevenlabs Elevenlabs python AudioOutputMulti
| Field | Value |
|---|---|
| source | Elevenlabs_Elevenlabs_python |
| domains | Audio, Streaming, Text-to-Speech |
| last_updated | 2026-02-15 |
Overview
Description
AudioOutputMulti is a Pydantic model representing a server payload containing an audio chunk for a specific context. It carries base64-encoded audio data along with optional alignment information (both raw and normalized) and a context identifier. This model supports multi-context audio streaming where different audio chunks may belong to different conversational contexts. This model is auto-generated by Fern from the ElevenLabs API definition and extends UncheckedBaseModel.
Usage
This model is received as part of streaming audio responses when using multi-context audio generation in the ElevenLabs API. Each instance represents a single audio chunk that can be decoded and played back, with optional alignment data for synchronization purposes.
Code Reference
Source Location
src/elevenlabs/types/audio_output_multi.py
Class Signature
class AudioOutputMulti(UncheckedBaseModel):
"""
Server payload containing an audio chunk for a specific context.
"""
...
Import Statement
from elevenlabs.types import AudioOutputMulti
I/O Contract
| Field | Type | Required | Description |
|---|---|---|---|
| audio | str |
Yes | Base64 encoded audio chunk. |
| normalized_alignment | Optional[NormalizedAlignment] |
No | Normalized alignment data for the audio chunk. Serialized with alias normalizedAlignment.
|
| alignment | Optional[Alignment] |
No | Alignment data for the audio chunk. |
| context_id | Optional[str] |
No | The contextId for which this audio is. Serialized with alias contextId.
|
Usage Examples
from elevenlabs.types import AudioOutputMulti
import base64
# Typically received as part of a streaming response
audio_chunk = AudioOutputMulti(
audio="SGVsbG8gV29ybGQ=", # base64 encoded audio data
context_id="ctx_12345",
)
# Decode the audio data
raw_audio = base64.b64decode(audio_chunk.audio)