GET

/v1/schemas/elevenlabs/audio/v1/text-to-voice?kind=output

Accept:

kind outputactivity audiohash d628f0c9…extracted Nov 11, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `4fa3fc2e746d36f6c01d5db3e204140071b3f1b20a159ea56c21f7959c5a610f` { "fetchedAt": 1794374428, "extractorVersion": "2", "verifiedAt": null }

Response body

26 properties · 6 required · 15 $defs

property	type	description	constraints
voice_id*	string	The ID of the voice.
name*	string	The name of the voice.
category*	enum	The category of the voice.	generated \| cloned \| premade \| professional \| famous \| high_quality
labels*	object	Labels associated with the voice.
available_for_tiers*	string[]	The tiers the voice is available for.
high_quality_base_model_ids*	string[]	The base model IDs for high-quality voices.
samples	SampleResponseModel[]	List of samples associated with the voice.	nullable
fine_tuning	FineTuningResponseModel	Fine-tuning information for the voice.	nullable
description	string	The description of the voice.	nullable
preview_url	string	The preview URL of the voice.	nullable
settings	VoiceSettingsResponseModel	The settings of the voice.	nullable
sharing	VoiceSharingResponseModel	The sharing information of the voice.	nullable
verified_languages	VerifiedVoiceLanguageResponseModel[]	The verified languages of the voice.	nullable
collection_ids	string[]	The IDs of collections this voice belongs to.	nullable
safety_control	enum	The safety controls of the voice.	NONE \| BAN \| CAPTCHA \| ENTERPRISE_BAN \| ENTERPRISE_CAPTCHA · nullable
voice_verification	VoiceVerificationResponseModel	The voice verification of the voice.	nullable
permission_on_resource	string	The permission on the resource of the voice.	nullable
is_owner	boolean	Whether the voice is owned by the user.	nullable
is_legacy	boolean	Whether the voice is legacy.	default: false
is_mixed	boolean	Whether the voice is mixed.	default: false
favorited_at_unix	integer	Timestamp when the voice was marked as favorite in Unix time.	nullable
created_at_unix	integer	The creation time of the voice in Unix time.	nullable
is_bookmarked	boolean	Whether the voice is bookmarked by the current user. Only relevant for community (library-copied) voices.	nullable
recording_quality	enum	The recording quality of the voice as determined by the review pipeline.	studio \| good \| ok \| poor \| bad · nullable
labelling_status	enum	The review pipeline status of the voice.	in_review \| review_complete · nullable
recording_quality_reason	string	The reason for the recording quality assessment, as determined by the review pipeline.	nullable

Types

15 $defs

FineTuningResponseModelobject

is_allowed_to_fine_tune*	boolean	Whether the user is allowed to fine-tune the voice.
state*	object	The state of the fine-tuning process for each model.
verification_failures*	string[]	List of verification failures in the fine-tuning process.
verification_attempts_count*	integer	The number of verification attempts in the fine-tuning process.
manual_verification_requested*	boolean	Whether a manual verification was requested for the fine-tuning process.
language	string	The language of the fine-tuning process.	nullable
progress	object	The progress of the fine-tuning process.	nullable
message	object	The message of the fine-tuning process.	nullable
dataset_duration_seconds	number	The duration of the dataset in seconds.	nullable
verification_attempts	VerificationAttemptResponseModel[]	The number of verification attempts.	nullable
slice_ids	string[]	List of slice IDs.	nullable
manual_verification	ManualVerificationResponseModel	The manual verification of the fine-tuning process.	nullable
max_verification_attempts	integer	The maximum number of verification attempts.	nullable
next_max_verification_attempts_reset_unix_ms	integer	The next maximum verification attempts reset time in Unix milliseconds.	nullable

ManualVerificationFileResponseModelobject

file_id*	string	The ID of the file.
file_name*	string	The name of the file.
mime_type*	string	The MIME type of the file.
size_bytes*	integer	The size of the file in bytes.
upload_date_unix*	integer	The date of the file in Unix time.

ManualVerificationResponseModelobject

extra_text*	string	The extra text of the manual verification.
request_time_unix*	integer	The date of the manual verification in Unix time.
files*	ManualVerificationFileResponseModel[]	The files of the manual verification.

ReaderResourceResponseModelobject

resource_type*	enum	The type of resource.	read \| collection
resource_id*	string	The ID of the resource.

RecordingResponseModelobject

recording_id*	string	The ID of the recording.
mime_type*	string	The MIME type of the recording.
size_bytes*	integer	The size of the recording in bytes.
upload_date_unix*	integer	The date of the recording in Unix time.
transcription*	string	The transcription of the recording.

SampleResponseModelobject

sample_id*	string	The ID of the sample.
file_name*	string	The name of the sample file.
mime_type*	string	The MIME type of the sample file.
size_bytes*	integer	The size of the sample file in bytes.
hash*	string	The hash of the sample file.
duration_secs	number		nullable
remove_background_noise	boolean		nullable
has_isolated_audio	boolean		nullable
has_isolated_audio_preview	boolean		nullable
speaker_separation	SpeakerSeparationResponseModel		nullable
trim_start	integer		nullable
trim_end	integer		nullable

SpeakerResponseModelobject

speaker_id*	string	The ID of the speaker.
duration_secs*	number	The duration of the speaker segment in seconds.
utterances	UtteranceResponseModel[]	The utterances of the speaker.	nullable

SpeakerSeparationResponseModelobject

voice_id*	string	The ID of the voice.
sample_id*	string	The ID of the sample.
status*	enum	The status of the speaker separation.	not_started \| pending \| completed \| failed
speakers	object	The speakers of the sample.	nullable
selected_speaker_ids	string[]	The IDs of the selected speakers.	nullable

UtteranceResponseModelobject

start*	number	The start time of the utterance in seconds.
end*	number	The end time of the utterance in seconds.

VerificationAttemptResponseModelobject

text*	string	The text of the verification attempt.
date_unix*	integer	The date of the verification attempt in Unix time.
accepted*	boolean	Whether the verification attempt was accepted.
similarity*	number	The similarity of the verification attempt.
levenshtein_distance*	number	The Levenshtein distance of the verification attempt.
recording	RecordingResponseModel	The recording of the verification attempt.	nullable

VerifiedVoiceLanguageResponseModelobject

language*	string	The language of the voice.
model_id*	string	The voice's model ID.
accent	string	The voice's accent, if applicable.	nullable
locale	string	The voice's locale, if applicable.	nullable
preview_url	string	The voice's preview URL, if applicable.	nullable

VoiceSettingsResponseModelobject

stability	number	Determines how stable the voice is and the randomness between each generation. Lower values introduce broader emotional range for the voice. Higher values can result in a monotonous voice with limited emotion.	0 ≤ n ≤ 1 · nullable
use_speaker_boost	boolean	This setting boosts the similarity to the original speaker. Using this setting requires a slightly higher computational load, which in turn increases latency.	nullable
similarity_boost	number	Determines how closely the AI should adhere to the original voice when attempting to replicate it.	0 ≤ n ≤ 1 · nullable
style	number	Determines the style exaggeration of the voice. This setting attempts to amplify the style of the original speaker. It does consume additional computational resources and might increase latency if set to anything other than 0.	nullable
speed	number	Adjusts the speed of the voice. A value of 1.0 is the default speed, while values less than 1.0 slow down the speech, and values greater than 1.0 speed it up.	nullable
clone_strength	number	Controls how closely the output matches your professional voice clone samples (0–1). Lower values sound more versatile, while higher values preserve more of the original voice characteristics. We recommend 0 for most use cases, but if you do run into issues 0.5 could be a good fallback. Applies only to professional voice clones fine-tuned for the selected v4 model.	0 ≤ n ≤ 1 · nullable

VoiceSharingModerationCheckResponseModelobject

date_checked_unix	integer	The date the moderation check was made in Unix time.	nullable
name_value	string	The name value of the voice.	nullable
name_check	boolean	Whether the name check was successful.	nullable
description_value	string	The description value of the voice.	nullable
description_check	boolean	Whether the description check was successful.	nullable
sample_ids	string[]	A list of sample IDs.	nullable
sample_checks	number[]	A list of sample checks.	nullable
captcha_ids	string[]	A list of captcha IDs.	nullable
captcha_checks	number[]	A list of CAPTCHA check values.	nullable

VoiceSharingResponseModelobject

status*	enum	The status of the voice sharing.	enabled \| disabled \| copied \| copied_disabled
history_item_sample_id	string	The sample ID of the history item.	nullable
date_unix*	integer	The Unix time, in seconds, at which the voice was shared.
whitelisted_emails*	string[]	A list of whitelisted emails.
public_owner_id*	string	The ID of the public owner.
original_voice_id*	string	The ID of the original voice.
financial_rewards_enabled*	boolean	Whether financial rewards are enabled.
free_users_allowed*	boolean	Whether free users are allowed.
live_moderation_enabled*	boolean	Whether live moderation is enabled.
rate	number	The rate of the voice sharing.	nullable
fiat_rate	number	The rate of the voice sharing in USD per 1000 credits.	nullable
notice_period*	integer	The notice period of the voice sharing.
disable_at_unix	integer	The Unix time, in seconds, at which users who added the voice from the Voice Library lose access to it.	nullable
voice_mixing_allowed*	boolean	Whether voice mixing is allowed.
featured*	boolean	Whether the voice is featured.
category*	enum	The category of the voice.	generated \| cloned \| premade \| professional \| famous \| high_quality
reader_app_enabled	boolean	Whether the reader app is enabled.	nullable
image_url	string	The image URL of the voice.	nullable
ban_reason	string	The ban reason of the voice.	nullable
liked_by_count*	integer	The number of likes on the voice.
cloned_by_count*	integer	The number of clones on the voice.
name*	string	The name of the voice.
description	string	The description of the voice.	nullable
labels*	object	The labels of the voice.
review_status*	enum	The review status of the voice.	not_requested \| pending \| declined \| declined_resubmittable \| allowed \| allowed_with_changes
review_message	string	The review message of the voice.	nullable
enabled_in_library*	boolean	Whether the voice is enabled in the library.
instagram_username	string	The Instagram username of the voice.	nullable
twitter_username	string	The Twitter/X username of the voice.	nullable
youtube_username	string	The YouTube username of the voice.	nullable
tiktok_username	string	The TikTok username of the voice.	nullable
moderation_check	VoiceSharingModerationCheckResponseModel	The moderation check of the voice.	nullable
reader_restricted_on	ReaderResourceResponseModel[]	The reader restricted on of the voice.	nullable

VoiceVerificationResponseModelobject

requires_verification*	boolean	Whether the voice requires verification.
is_verified*	boolean	Whether the voice has been verified.
verification_failures*	string[]	List of verification failures.
verification_attempts_count*	integer	The number of verification attempts.
language	string	The language of the voice.	nullable
verification_attempts	VerificationAttemptResponseModel[]	Number of times a verification was attempted.	nullable

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"elevenlabs","endpointId":"v1/text-to-voice","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}