Implementation:Elevenlabs Elevenlabs python ForcedAlignmentCharacterResponseModel

Attribute	Value
Sources	src/elevenlabs/types/forced_alignment_character_response_model.py
Domains	Forced Alignment, Audio Timing, Transcription
Last Updated	2026-02-15

Overview

Description

The ForcedAlignmentCharacterResponseModel represents a single character with its precise timing information from the ElevenLabs forced aligner. Forced alignment is the process of mapping each character in a transcript to its exact time position in the corresponding audio. This model provides the transcribed character along with its start and end times in seconds, enabling character-level precision for synchronization tasks.

Usage

This model is returned as part of forced alignment results, typically within word-level alignment data (see ForcedAlignmentWordResponseModel). It is used in scenarios requiring fine-grained audio-text synchronization, such as precise subtitle timing, animation lip-sync, or phonetic analysis. Each instance represents exactly one character's temporal position in the audio stream.

Code Reference

Source Location

src/elevenlabs/types/forced_alignment_character_response_model.py

Class Signature

class ForcedAlignmentCharacterResponseModel(UncheckedBaseModel):
    """
    Model representing a single character with its timing information from the aligner.
    """
    ...

Import Statement

from elevenlabs.types import ForcedAlignmentCharacterResponseModel

Base Class

UncheckedBaseModel (from elevenlabs.core.unchecked_base_model)

I/O Contract

Field	Type	Required	Description
text	str	Yes	The character that was transcribed.
start	float	Yes	The start time of the character in seconds.
end	float	Yes	The end time of the character in seconds.

Usage Examples

from elevenlabs import ElevenLabs

client = ElevenLabs(api_key="your_api_key")

# Obtain forced alignment results (from a dubbing or alignment endpoint)
# Each character in the aligned text has precise timing
alignment_result = client.audio_native.get_alignment(
    audio_id="audio_abc123"
)

# Iterate through character-level alignment data
for char_alignment in alignment_result.characters:
    duration = char_alignment.end - char_alignment.start
    print(
        f"Character '{char_alignment.text}': "
        f"{char_alignment.start:.3f}s - {char_alignment.end:.3f}s "
        f"(duration: {duration:.3f}s)"
    )

Related Pages

• ForcedAlignmentWordResponseModel - Word-level forced alignment timing (composed of characters)
• Alignment - Chunk-level audio-text alignment data