ElevenLabsAudio modelActive
Eleven Music v2.5
PopularityRank 670 of 875
0out of 100same as last month
Summary
Eleven Music v2.5 generates music from natural-language instructions. The current ElevenLabs documentation highlights better prompt adherence, richer melodies, deeper arrangements, and more layered instruments. You can choose vocals or an instrumental result while specifying genre, style, and structure.
Eleven Music v2.5 combines composition plans, audio references, and inpainting in one music model. It can revise selected sections of a piece, while an individual sound effect belongs to the narrower Text to Sound model.
All benchmark results
Every published result with its source, test setup and comparison models.
Show all 18 published benchmark results
Page 1 of 2
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.
Genflick median written-lyrics recovery by Scribe v2 (Show measurement, test conditions, and source)
- Source value
- 99
- Score
- 99
- Metric
- median share of written lyrics recovered in order by Scribe v2 speech-to-text
- Unit
- %
- Benchmark version
- Genflick test published 2026-10-02; current model music_v2_5
- Category
- audio generation / lyric recovery
- Direction
- Higher is better
- Sample
- 26
- Source type
- independent-evaluator
- Evaluator
- Genflick observed music-generation benchmark
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Independent evaluation. Genflick reports the median share of the written lyrics recovered in order by ElevenLabs Scribe v2 across the 26 generated songs in its music_v2_5 test. The page lists 8 languages and 26 minutes of audio. The model serving revision is not pinned.
- Context
- This is an ASR-based lyric-recovery proxy, not a human lyric-fidelity or acoustic-quality score. It evaluates the interaction of generated audio and Scribe v2 transcription.
Artificial Analysis AA-Music-Instrumental Elo (Show measurement, test conditions, and source)
- Source value
- 1001
- Score
- 1001
- Metric
- blind pairwise same-prompt music preference Elo
- Unit
- elo
- Benchmark version
- AA-Music-Instrumental v1.1
- Category
- audio
- Direction
- Higher is better
- Sample
- 2236
- Confidence interval
- 21
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Independent evaluation. Blind pairwise comparisons generated from the same prompts, judged by validated evaluators; instrumental generation cohort; 2,236 appearances.
- Context
- Appearances are not unique listeners; vocal and instrumental cohorts measure separate tasks.
Artificial Analysis AA-Music-Vocal Elo (Show measurement, test conditions, and source)
- Source value
- 1012
- Score
- 1012
- Metric
- blind pairwise same-prompt music preference Elo
- Unit
- elo
- Benchmark version
- AA-Music-Vocal v1.1
- Category
- audio
- Direction
- Higher is better
- Sample
- 2656
- Confidence interval
- 19
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Independent evaluation. Blind pairwise comparisons generated from the same prompts, judged by validated evaluators; vocal generation cohort; 2,656 appearances.
- Context
- Appearances are not unique listeners; vocal and instrumental cohorts measure separate tasks.
Genflick median generation time for a 60-second song (Show measurement, test conditions, and source)
- Source value
- 8
- Score
- 8
- Metric
- median generation latency for a 60-second song
- Unit
- seconds
- Benchmark version
- Genflick test published 2026-10-02; current model music_v2_5
- Category
- audio generation
- Direction
- Lower is better
- Sample
- 17
- Source type
- independent-evaluator
- Evaluator
- Genflick observed music-generation benchmark
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Independent evaluation. Genflick reports testing the current ElevenLabs Compose Music API model_id music_v2_5. The page reports 26 songs across 8 languages and a median time for a 60-second song across 17 one-at-a-time runs; the range was 7.0 to 10.4 seconds. Serving revision is not pinned.
- Context
- This is an external observation of the serving API, not a pinned model-weight evaluation. Genflick does not report a confidence interval.
Genflick Music v2.5 generated songs with 100% written-lyrics recovery (Show measurement, test conditions, and source)
- Source value
- 12
- Score
- 12
- Metric
- Count of generated songs for which Scribe v2 recovered 100% of the written lyrics
- Unit
- count
- Category
- audio
- Direction
- Higher is better
- Sample
- 26
- Source type
- independent-evaluator
- Evaluator
- Genflick GenBench music research
- Status
- active
- Retrieved at
- 2026-10-19
- Methodology
- Independent evaluation. Genflick identifies its tested generation model as current ElevenLabs Compose Music model_id music_v2_5 and reports 26 songs, 8 languages, and 26 minutes of audio. This row is the source-reported count of songs with full written-lyrics recovery by Scribe v2; the source says 12 of 26 songs returned at 100%.
- Context
- This is a source-reported count within the same 26-song experiment as the already-recorded median lyric-recovery cell; it is not an independent second sample. Generation API revision is not pinned.
Promptif CLAP genre similarity: 30-second lo-fi instrumental, English description (Show measurement, test conditions, and source)
- Source value
- 0.555
- Score
- 0.555
- Metric
- CLAP similarity to the requested genre description among six genre candidates
- Unit
- No unit provided
- Benchmark version
- Promptif four-track Eleven Music v2.5 test; verified 2026-09-29; article published 2026-09-30
- Category
- audio
- Direction
- Higher is better
- Sample
- 1
- Source type
- community-reported
- Evaluator
- Promptif
- Status
- active
- Retrieved at
- 2026-10-19
- Methodology
- Community-reported result. Promptif's own four-output API test of exact model_id music_v2_5, verified 2026-09-29. Two 30-second instrumental lo-fi tracks used English and French style prompts; two 45-second indie-pop songs used the same supplied 54-word French lyrics with English and French style descriptions, one generation per condition. CLAP compared each track against six genre descriptions; Scribe transcription was compared with the supplied lyrics. The source gives no CI, repeated-run distribution, or immutable serving revision.
- Context
- Community-reported four-output test with one generation per condition, automatic CLAP/Scribe measurements and no blinded human listening. Promptif discloses an ElevenLabs affiliate link; the rows are not a cross-model comparison or repeated-run estimate.
Promptif CLAP genre similarity: 30-second lo-fi instrumental, French description (Show measurement, test conditions, and source)
- Source value
- 0.545
- Score
- 0.545
- Metric
- CLAP similarity to the requested genre description among six genre candidates
- Unit
- No unit provided
- Benchmark version
- Promptif four-track Eleven Music v2.5 test; verified 2026-09-29; article published 2026-09-30
- Category
- audio
- Direction
- Higher is better
- Sample
- 1
- Source type
- community-reported
- Evaluator
- Promptif
- Status
- active
- Retrieved at
- 2026-10-19
- Methodology
- Community-reported result. Promptif's own four-output API test of exact model_id music_v2_5, verified 2026-09-29. Two 30-second instrumental lo-fi tracks used English and French style prompts; two 45-second indie-pop songs used the same supplied 54-word French lyrics with English and French style descriptions, one generation per condition. CLAP compared each track against six genre descriptions; Scribe transcription was compared with the supplied lyrics. The source gives no CI, repeated-run distribution, or immutable serving revision.
- Context
- Community-reported four-output test with one generation per condition, automatic CLAP/Scribe measurements and no blinded human listening. Promptif discloses an ElevenLabs affiliate link; the rows are not a cross-model comparison or repeated-run estimate.
Promptif CLAP genre similarity: 45-second indie-pop song, English style description (Show measurement, test conditions, and source)
- Source value
- 0.407
- Score
- 0.407
- Metric
- CLAP similarity to the requested genre description among six genre candidates
- Unit
- No unit provided
- Benchmark version
- Promptif four-track Eleven Music v2.5 test; verified 2026-09-29; article published 2026-09-30
- Category
- audio
- Direction
- Higher is better
- Sample
- 1
- Source type
- community-reported
- Evaluator
- Promptif
- Status
- active
- Retrieved at
- 2026-10-19
- Methodology
- Community-reported result. Promptif's own four-output API test of exact model_id music_v2_5, verified 2026-09-29. Two 30-second instrumental lo-fi tracks used English and French style prompts; two 45-second indie-pop songs used the same supplied 54-word French lyrics with English and French style descriptions, one generation per condition. CLAP compared each track against six genre descriptions; Scribe transcription was compared with the supplied lyrics. The source gives no CI, repeated-run distribution, or immutable serving revision.
- Context
- Community-reported four-output test with one generation per condition, automatic CLAP/Scribe measurements and no blinded human listening. Promptif discloses an ElevenLabs affiliate link; the rows are not a cross-model comparison or repeated-run estimate.
Promptif CLAP genre similarity: 45-second indie-pop song, French style description (Show measurement, test conditions, and source)
- Source value
- 0.354
- Score
- 0.354
- Metric
- CLAP similarity to the requested genre description among six genre candidates
- Unit
- No unit provided
- Benchmark version
- Promptif four-track Eleven Music v2.5 test; verified 2026-09-29; article published 2026-09-30
- Category
- audio
- Direction
- Higher is better
- Sample
- 1
- Source type
- community-reported
- Evaluator
- Promptif
- Status
- active
- Retrieved at
- 2026-10-19
- Methodology
- Community-reported result. Promptif's own four-output API test of exact model_id music_v2_5, verified 2026-09-29. Two 30-second instrumental lo-fi tracks used English and French style prompts; two 45-second indie-pop songs used the same supplied 54-word French lyrics with English and French style descriptions, one generation per condition. CLAP compared each track against six genre descriptions; Scribe transcription was compared with the supplied lyrics. The source gives no CI, repeated-run distribution, or immutable serving revision.
- Context
- Community-reported four-output test with one generation per condition, automatic CLAP/Scribe measurements and no blinded human listening. Promptif discloses an ElevenLabs affiliate link; the rows are not a cross-model comparison or repeated-run estimate.
Promptif Scribe lyric-transcript word differences: English style description (Show measurement, test conditions, and source)
- Source value
- 4
- Score
- 4
- Metric
- Word differences from the supplied 54-word French lyric, one generated song
- Unit
- count
- Benchmark version
- Promptif four-track Eleven Music v2.5 test; verified 2026-09-29; article published 2026-09-30
- Category
- audio
- Direction
- Lower is better
- Sample
- 1
- Source type
- community-reported
- Evaluator
- Promptif
- Status
- active
- Retrieved at
- 2026-10-19
- Methodology
- Community-reported result. Promptif's own four-output API test of exact model_id music_v2_5, verified 2026-09-29. Two 30-second instrumental lo-fi tracks used English and French style prompts; two 45-second indie-pop songs used the same supplied 54-word French lyrics with English and French style descriptions, one generation per condition. CLAP compared each track against six genre descriptions; Scribe transcription was compared with the supplied lyrics. The source gives no CI, repeated-run distribution, or immutable serving revision.
- Context
- Community-reported four-output test with one generation per condition, automatic CLAP/Scribe measurements and no blinded human listening. Promptif discloses an ElevenLabs affiliate link; the rows are not a cross-model comparison or repeated-run estimate.
Promptif Scribe lyric-transcript word differences: French style description (Show measurement, test conditions, and source)
- Source value
- 2
- Score
- 2
- Metric
- Word differences from the supplied 54-word French lyric, one generated song
- Unit
- count
- Benchmark version
- Promptif four-track Eleven Music v2.5 test; verified 2026-09-29; article published 2026-09-30
- Category
- audio
- Direction
- Lower is better
- Sample
- 1
- Source type
- community-reported
- Evaluator
- Promptif
- Status
- active
- Retrieved at
- 2026-10-19
- Methodology
- Community-reported result. Promptif's own four-output API test of exact model_id music_v2_5, verified 2026-09-29. Two 30-second instrumental lo-fi tracks used English and French style prompts; two 45-second indie-pop songs used the same supplied 54-word French lyrics with English and French style descriptions, one generation per condition. CLAP compared each track against six genre descriptions; Scribe transcription was compared with the supplied lyrics. The source gives no CI, repeated-run distribution, or immutable serving revision.
- Context
- Community-reported four-output test with one generation per condition, automatic CLAP/Scribe measurements and no blinded human listening. Promptif discloses an ElevenLabs affiliate link; the rows are not a cross-model comparison or repeated-run estimate.
Promptif single-generation time: 30-second lo-fi instrumental, English description (Show measurement, test conditions, and source)
- Source value
- 6.2
- Score
- 6.2
- Metric
- Observed single-request generation time
- Unit
- seconds
- Benchmark version
- Promptif four-track Eleven Music v2.5 test; verified 2026-09-29; article published 2026-09-30
- Category
- audio
- Direction
- Lower is better
- Sample
- 1
- Source type
- community-reported
- Evaluator
- Promptif
- Status
- active
- Retrieved at
- 2026-10-19
- Methodology
- Community-reported result. Promptif's own four-output API test of exact model_id music_v2_5, verified 2026-09-29. Two 30-second instrumental lo-fi tracks used English and French style prompts; two 45-second indie-pop songs used the same supplied 54-word French lyrics with English and French style descriptions, one generation per condition. CLAP compared each track against six genre descriptions; Scribe transcription was compared with the supplied lyrics. The source gives no CI, repeated-run distribution, or immutable serving revision.
- Context
- Community-reported four-output test with one generation per condition, automatic CLAP/Scribe measurements and no blinded human listening. Promptif discloses an ElevenLabs affiliate link; the rows are not a cross-model comparison or repeated-run estimate.
Page 1 of 2
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-1, pyannote: 73
Nemotron-3-Diarization, NVIDIA: 57
Gemini 3.5 Transcribe, Google: 52
Confucius4-R2T2, NetEase Youdao: 52
Granite Speech 5.0 470M TurboCTC, IBM: 52
Kokoro-82M, hexgrad: 51
Nova-3, Deepgram: 51
Fish Audio S2 Pro, Fish Audio: 51
NVIDIA Nemotron 3.5 Transcribe, NVIDIA: 50
Granite Speech 5.0 470M TurboCTC NC, IBM: 50
Orukeet, Oruk: 49
Lyria 3.5, Google: 47
Gemini 3.5 Live Translate, Google: 46
Phonon-2, Fermion Research: 44
Aura-2, Deepgram: 44
Gemini 3.1 Flash TTS, Google: 44
MiniMax-Music3, MiniMax: 41
Audio8-ASR-Infinite, Edge0 AI: 41
GPT-Realtime 2.1, OpenAI: 41
Eleven Music v2.5, ElevenLabs: 0
Eleven Music v2.5
As of November 2026 · Source: gradually.ai popularity index
Over time
Weekly values from October 18, 2026 to November 5, 2026
Eleven Music v2.5Amazon Nova 2 SonicEleven Multilingual STS v2Eleven Text to Sound v2Falcon-ASR
All specifications
Architecture
Input and 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
API
Further details
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 published | pinned-serving-revision-and-confidence-interval Note Genflick does not report a pinned serving revision or confidence intervals. |
| Unresolved | generation API revision Note Genflick identifies model_id music_v2_5 but does not pin the served generation API revision. The 12-of-26 count is a breakdown from the same experiment, not a separate test. |
| Additional source | ElevenLabs model documentation (retrieved September 24, 2026; October 15, 2026) · ElevenLabs Models documentation · Editorial description reviewed October 2, 2026 |
| Additional source | Artificial Analysis (retrieved October 15, 2026; October 23, 2026)12 |
| Additional source | Genflick observed music-generation benchmark (retrieved October 17, 2026; October 19, 2026; October 21, 2026) |
| Additional source | Promptif (retrieved October 19, 2026) |
| Additional source | Model metadata (retrieved October 17, 2026) |
| 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 |