ElevenLabsAudio modelActive

Eleven Text to Sound v2

Popularityhardly any signal

under 1out of 100same as last month

Summary

Eleven Text to Sound v2 translates a text prompt into a sound effect and returns an audio file. ElevenLabs places the endpoint specifically under sound-effect generation. Speech synthesis is outside this model.

Eleven Text to Sound v2 translates a text description directly into a sound effect. The endpoint is documented for effects such as scene or transition sounds, not for spoken narration or complete musical arrangements.

All benchmark results

Every published result with its source, test setup and comparison models.

Show all 28 published benchmark results

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

Quantslant own-prompt top-1 match rate, prompt influence 0.3 (Show measurement, test conditions, and source)

Source value: 100
Score: 100
Metric: own English description ranked first among the five candidate prompts by CLAP
Unit: %
Benchmark version: Quantslant Sound Effects prompt-influence test; generations 2026-09-29
Category: audio
Direction: Higher is better
Sample: 5
Source type: independent-evaluator
Evaluator: Quantslant sound-effects test
Status: active
Retrieved at: 2026-10-15
Methodology: Independent evaluation. Five English sound-effect prompts, each generated through the API with exact model ID eleven_text_to_sound_v2, duration_seconds=5 and prompt_influence=0.3. Each audio was compared with the set of five prompts using LAION laion/larger_clap_general; top-1 means its own prompt ranked first.
Context: The 5/5 top-1 result is retrieval within this same five-prompt candidate set, not general semantic accuracy or human-rated sound quality. The API model has no immutable revision recorded; Quantslant discloses an ElevenLabs partner-link commission.

Source Quantslant sound-effects test

Quantslant own-prompt top-1 match rate, prompt influence 1.0 (Show measurement, test conditions, and source)

Source value: 100
Score: 100
Metric: own English description ranked first among the five candidate prompts by CLAP
Unit: %
Benchmark version: Quantslant Sound Effects prompt-influence test; generations 2026-09-29
Category: audio
Direction: Higher is better
Sample: 5
Source type: independent-evaluator
Evaluator: Quantslant sound-effects test
Status: active
Retrieved at: 2026-10-15
Methodology: Independent evaluation. Five English sound-effect prompts, each generated through the API with exact model ID eleven_text_to_sound_v2, duration_seconds=5 and prompt_influence=1.0. Each audio was compared with the set of five prompts using LAION laion/larger_clap_general; top-1 means its own prompt ranked first.
Context: The 5/5 top-1 result is retrieval within this same five-prompt candidate set, not general semantic accuracy or human-rated sound quality. The API model has no immutable revision recorded; Quantslant discloses an ElevenLabs partner-link commission.

Source Quantslant sound-effects test

Quantslant mean CLAP similarity to own prompt, prompt influence 0.3 (Show measurement, test conditions, and source)

Source value: 0.355
Score: 0.355
Metric: mean CLAP audio-text dot-product similarity to the generated sound's own English description
Unit: points
Benchmark version: Quantslant Sound Effects prompt-influence test; generations 2026-09-29
Category: audio
Direction: Higher is better
Sample: 5
Source type: independent-evaluator
Evaluator: Quantslant sound-effects test
Status: active
Retrieved at: 2026-10-15
Methodology: Independent evaluation. Five English sound-effect prompts, each generated through the API with exact model ID eleven_text_to_sound_v2, duration_seconds=5 and prompt_influence=0.3. Scores use LAION laion/larger_clap_general; reported mean across five prompt/audio pairs.
Context: Small n=5 model-judge experiment, not a human listening score or broad quality leaderboard. CLAP's raw similarity is task- and candidate-dependent; the API model has no immutable revision recorded. Quantslant discloses an ElevenLabs partner-link commission.

Source Quantslant sound-effects test

Quantslant mean CLAP similarity to own prompt, prompt influence 1.0 (Show measurement, test conditions, and source)

Source value: 0.322
Score: 0.322
Metric: mean CLAP audio-text dot-product similarity to the generated sound's own English description
Unit: points
Benchmark version: Quantslant Sound Effects prompt-influence test; generations 2026-09-29
Category: audio
Direction: Higher is better
Sample: 5
Source type: independent-evaluator
Evaluator: Quantslant sound-effects test
Status: active
Retrieved at: 2026-10-15
Methodology: Independent evaluation. Five English sound-effect prompts, each generated through the API with exact model ID eleven_text_to_sound_v2, duration_seconds=5 and prompt_influence=1.0. Scores use LAION laion/larger_clap_general; reported mean across five prompt/audio pairs.
Context: Small n=5 model-judge experiment, not a human listening score or broad quality leaderboard. CLAP's raw similarity is task- and candidate-dependent; the API model has no immutable revision recorded. Quantslant discloses an ElevenLabs partner-link commission.

Source Quantslant sound-effects test

Promptif CLAP mean similarity: English prompt condition (Show measurement, test conditions, and source)

Source value: 0.346
Score: 0.346
Metric: Mean CLAP similarity to the intended sound description, English prompt condition
Unit: No unit provided
Benchmark version: Promptif Sound Effects French-versus-English test; API generations 2026-09-29; article published 2026-09-30
Category: audio
Direction: Higher is better
Sample: 5
Source type: community-reported
Evaluator: Promptif
Status: active
Retrieved at: 2026-10-19
Methodology: Community-reported result. Promptif's own API test, run 2026-09-29, for exact model_id eleven_text_to_sound_v2. Five semantically matched French/English prompt pairs; each output requested at five seconds with default prompt_influence 0.3. The published command uses MP3 44.1 kHz / 128 kbps. CLAP (laion/larger_clap_general) compared outputs against the five English sound descriptions; the source reports mean similarity and whether the intended description ranked first. No human listening score, CI, or immutable serving revision is reported.
Context: Small five-output-per-language comparison, automatically scored by CLAP rather than human listeners; the same sample set supports both the mean-score and top-one rows. Promptif discloses an ElevenLabs affiliate link.

Source Promptif

Promptif CLAP mean similarity: French prompt condition (Show measurement, test conditions, and source)

Source value: 0.04
Score: 0.04
Metric: Mean CLAP similarity to the intended sound description, French prompt condition
Unit: No unit provided
Benchmark version: Promptif Sound Effects French-versus-English test; API generations 2026-09-29; article published 2026-09-30
Category: audio
Direction: Higher is better
Sample: 5
Source type: community-reported
Evaluator: Promptif
Status: active
Retrieved at: 2026-10-19
Methodology: Community-reported result. Promptif's own API test, run 2026-09-29, for exact model_id eleven_text_to_sound_v2. Five semantically matched French/English prompt pairs; each output requested at five seconds with default prompt_influence 0.3. The published command uses MP3 44.1 kHz / 128 kbps. CLAP (laion/larger_clap_general) compared outputs against the five English sound descriptions; the source reports mean similarity and whether the intended description ranked first. No human listening score, CI, or immutable serving revision is reported.
Context: Small five-output-per-language comparison, automatically scored by CLAP rather than human listeners; the same sample set supports both the mean-score and top-one rows. Promptif discloses an ElevenLabs affiliate link.

Source Promptif

Promptif CLAP top-one match count: English prompts (Show measurement, test conditions, and source)

Source value: 5
Score: 5
Metric: Number of outputs whose intended sound description ranked first among five candidates
Unit: count
Benchmark version: Promptif Sound Effects French-versus-English test; API generations 2026-09-29; article published 2026-09-30
Category: audio
Direction: Higher is better
Sample: 5
Source type: community-reported
Evaluator: Promptif
Status: active
Retrieved at: 2026-10-19
Methodology: Community-reported result. Promptif's own API test, run 2026-09-29, for exact model_id eleven_text_to_sound_v2. Five semantically matched French/English prompt pairs; each output requested at five seconds with default prompt_influence 0.3. The published command uses MP3 44.1 kHz / 128 kbps. CLAP (laion/larger_clap_general) compared outputs against the five English sound descriptions; the source reports mean similarity and whether the intended description ranked first. No human listening score, CI, or immutable serving revision is reported.
Context: Small five-output-per-language comparison, automatically scored by CLAP rather than human listeners; the same sample set supports both the mean-score and top-one rows. Promptif discloses an ElevenLabs affiliate link.

Source Promptif

Promptif CLAP top-one match count: French prompts (Show measurement, test conditions, and source)

Source value: 2
Score: 2
Metric: Number of outputs whose intended sound description ranked first among five candidates
Unit: count
Benchmark version: Promptif Sound Effects French-versus-English test; API generations 2026-09-29; article published 2026-09-30
Category: audio
Direction: Higher is better
Sample: 5
Source type: community-reported
Evaluator: Promptif
Status: active
Retrieved at: 2026-10-19
Methodology: Community-reported result. Promptif's own API test, run 2026-09-29, for exact model_id eleven_text_to_sound_v2. Five semantically matched French/English prompt pairs; each output requested at five seconds with default prompt_influence 0.3. The published command uses MP3 44.1 kHz / 128 kbps. CLAP (laion/larger_clap_general) compared outputs against the five English sound descriptions; the source reports mean similarity and whether the intended description ranked first. No human listening score, CI, or immutable serving revision is reported.
Context: Small five-output-per-language comparison, automatically scored by CLAP rather than human listeners; the same sample set supports both the mean-score and top-one rows. Promptif discloses an ElevenLabs affiliate link.

Source Promptif

Clotho text-to-audio: CLAP (higher is better) (Show measurement, test conditions, and source)

Source value: 0.3967
Score: 0.3967
Metric: CLAP
Unit: No unit provided
Direction: Higher is better
Source type: community-reported
Evaluator: audio_eval repository by shwj114514
Status: active
Retrieved at: 2026-10-23
Methodology: Community-reported result. The table names the system “ElevenLabs SFX v2” and the test set “Clotho”. The source does not state the generation route, exact API model ID, or run parameters.
Context: The community table does not state a sample count, benchmark edition, model revision, or full metric parameters. The value therefore does not establish a particular current serving route and cannot be reproduced from the report alone.

Source audio_eval repository by shwj114514

Clotho text-to-audio: KL (PANNs, gen→ref) (lower is better) (Show measurement, test conditions, and source)

Source value: 1.495
Score: 1.495
Metric: KL (PANNs, gen→ref)
Unit: No unit provided
Direction: Lower is better
Source type: community-reported
Evaluator: audio_eval repository by shwj114514
Status: active
Retrieved at: 2026-10-23
Methodology: Community-reported result. The table names the system “ElevenLabs SFX v2” and the test set “Clotho”. The source does not state the generation route, exact API model ID, or run parameters.
Context: The community table does not state a sample count, benchmark edition, model revision, or full metric parameters. The value therefore does not establish a particular current serving route and cannot be reproduced from the report alone.

Source audio_eval repository by shwj114514

Clotho text-to-audio: PaSST, gen→ref (lower is better) (Show measurement, test conditions, and source)

Source value: 1.623
Score: 1.623
Metric: PaSST, gen→ref
Unit: No unit provided
Direction: Lower is better
Source type: community-reported
Evaluator: audio_eval repository by shwj114514
Status: active
Retrieved at: 2026-10-23
Methodology: Community-reported result. The table names the system “ElevenLabs SFX v2” and the test set “Clotho”. The source does not state the generation route, exact API model ID, or run parameters.
Context: The community table does not state a sample count, benchmark edition, model revision, or full metric parameters. The value therefore does not establish a particular current serving route and cannot be reproduced from the report alone.

Source audio_eval repository by shwj114514

Clotho text-to-audio: IS (PANNs) (higher is better) (Show measurement, test conditions, and source)

Source value: 7.3307
Score: 7.3307
Metric: IS (PANNs)
Unit: No unit provided
Direction: Higher is better
Source type: community-reported
Evaluator: audio_eval repository by shwj114514
Status: active
Retrieved at: 2026-10-23
Methodology: Community-reported result. The table names the system “ElevenLabs SFX v2” and the test set “Clotho”. The source does not state the generation route, exact API model ID, or run parameters.
Context: The community table does not state a sample count, benchmark edition, model revision, or full metric parameters. The value therefore does not establish a particular current serving route and cannot be reproduced from the report alone.

Source audio_eval repository by shwj114514

Page 1 of 3

Popularity compared

How often the model is searched for, used and mentioned, compared with every model of its category.

Popularity index

0 to 100, higher is more popular

20 of 83 models

pyannote Community-173

Nemotron-3-Diarization57

Gemini 3.5 Transcribe52

Confucius4-R2T252

NVIDIA Nemotron 3.5 Transcribe52

Granite Speech 5.0 470M TurboCTC52

Kokoro-82M51

Nova-351

Fish Audio S2 Pro51

Granite Speech 5.0 470M TurboCTC NC50

Orukeet49

Lyria 3.547

Gemini 3.5 Live Translate46

Phonon-244

Aura-244

Gemini 3.1 Flash TTS44

MiniMax-Music341

Audio8-ASR-Infinite41

GPT-Realtime 2.141

Eleven Text to Sound v20

pyannote Community-1

Nemotron-3-Diarization

Gemini 3.5 Transcribe

Confucius4-R2T2

NVIDIA Nemotron 3.5 Trans…

Granite Speech 5.0 470M T…

Kokoro-82M

Nova-3

Fish Audio S2 Pro

Granite Speech 5.0 470M T…

Orukeet

Lyria 3.5

Gemini 3.5 Live Translate

Eleven Text to Sound v2

As of November 2026 · Source: gradually.ai popularity index

Over time

Weekly values from October 18, 2026 to November 6, 2026

Eleven Text to Sound v2Amazon Nova 2 Sonic 0Eleven Multilingual STS v2 0Eleven Music v2.5 0Falcon-ASR 0

Method changes in the timeline, a jump at these points is no market event:

1November 1, 2026: Value only with search or usage data, 30-day attention

What is gaining popularity right now, across models, vendors, harnesses and AI subscriptions, is collected in All AI trends.

Similar models

More models of the same kind as Eleven Text to Sound v2, chosen by model line, developer, size, price and release date.

All specifications

Architecture

Model class: Sound-effect generation; Source: Model class

Input and output

Input: Text; Source: Input
Output: Audio; Source: Output

Watermarking and provenance

AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.

AI watermarking: Unknown; no source
Watermarking technique: Not known; no source

Licence and access

Access: API; Source: Access

API

API model ID: eleven_text_to_sound_v2; Source: API model ID

Further details

Task: Generate sound effects; Source: Task
Supported details: Text-based sound effects; Source: Supported details
Sound effects: Sound effects from text prompts; Source: Sound effects

Sources and data date

Show all 12 sources

Benchmark sources at a glance

Which independent evaluators tested this model. This is coverage, not a quality ranking.

No active result from the reviewed external evaluators can currently be attributed to this model. Other source evidence remains available below.

Without vendor claims and historical or disputed results; those stay labelled in the single values.

Type	Evidence and data date
Research status	Research date October 15, 2026. 7 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not found in the inspected sources	standardized-sound-effects-benchmark Note An exact-model independent five-prompt experiment was found, but no standardized multi-model sound-effects leaderboard or replicated benchmark was identified. The reported CLAP top-1 score is limited to the experiment's own five-prompt set.
Not found in the inspected sources	immutable-api-revision Note The experiment identifies the exact request model ID eleven_text_to_sound_v2 but publishes no immutable provider checkpoint or revision. Results therefore attach to the API label used on the dated run, not a version-pinned artifact.
Additional source	ElevenLabs model documentation (retrieved September 24, 2026; October 15, 2026) · ElevenLabs Models documentation · Editorial description reviewed October 2, 2026
Additional source	Quantslant sound-effects test (retrieved October 15, 2026)
Additional source	Promptif (retrieved October 19, 2026)
Additional source	audio_eval repository by shwj114514 (retrieved October 23, 2026)
Additional source	Model metadata (retrieved October 15, 2026)1 2
Additional source	OpenRouter: Popularity index (derived), CC BY 4.0
Additional source	Vercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional source	Ollama: cumulative downloads for the popularity index
Additional source	Replicate: cumulative runs for the popularity index
Additional source	Google Trending Now: limited feed selection for Germany and the US
Additional source	Creative Commons Attribution 4.0