Scribe v2
Very accurate transcription with speaker labels and a free plan. Heavy API users pay less with MAI-Transcribe-2.
Should you use it?
Pick it if
Podcasters, journalists and teams who want accurate transcripts with speaker labels in an app, or a free way to start.
Best for: Podcasters and journalists who want speaker labels, with a free way to start (Speech to text Top 20)
Skip it if
You transcribe large volumes through an API and can accept a preview; MAI-Transcribe-2 is cheaper and more accurate.
You give up: Over twice MAI-Transcribe-2's hourly price; trains on your audio unless you opt out
The short version
- What this is
- ElevenLabs' speech to text model. It turns recordings into text with speaker labels and timestamps in 90+ languages, in the ElevenLabs app or API.
- Why it matters
- It is one of the most accurate transcription models and you can start on a free plan.
- 2.2% word error rate, 4th of 55 models on Artificial Analysis; no score yet, as its terms stop us publishing one.
- $0.22 per audio hour on the API; free plan to start.
- Opt out of training in settings if your audio is private.
Good at
Our take
Scribe v2 is a strong, mature choice. Only three models beat its 2.2% error rate on Artificial Analysis s1, and it comes with the extras people need for real transcripts: speaker labels, timestamps and custom key terms s6.
For high-volume API work, MAI-Transcribe-2 is more accurate and less than half the price per hour, but it is a preview without an SLA s1 s2. If you want something that is not a preview, or a free way to start in an app, Scribe v2 is the pick.
Score
A score from 0 to 100 per job, against everything available today.
New to this? What the scores and labels mean
- 0 to 100
- Our score for one job, like writing or coding, compared with everything else out today. 100 is the best available today. For AI models we build it from public data, such as Arena's blind votes and Epoch AI's independent tests; apps and tools are scored on our own checklist. The same tool can score differently for different jobs, and where two likely ranges overlap, we call it a tie.
- Our verdict
- Use it: a top choice for most people. Worth trying: good, and worth a go. Depends: good for some people or one kind of job. Wait: too early to tell, or not out for everyone yet. Skip: something else does the job better.
- First look
- Just released. We say what it is and whether to bother, and give it a score once public results exist.
- No score yet
- None of the public sources we use covers it yet, or the only evidence is from a source whose numbers we can't use, so we describe it in words instead.
- Best buy
- Nothing cheaper scores as well for that job.
- Best free
- The best score for that job that costs nothing, through a free plan or by running on your own computer.
- Pay as you go
- No monthly plan: you pay for each use, usually through a developer account.
- Checked
- The day we last confirmed the score and the price against the sources. Prices change often, so check the date.
- AI model
- The engine underneath, like GPT or Claude. You use it through an app or, if you code, directly.
- Open source
- Free to download and run on your own computer, so nothing leaves your machine.
Voice and audio
No score yet. The leaderboard this rests on does not let us publish numbers from it, so we describe the evidence instead.
1 source so far
Independent testArtificial Analysis speech to text: word error rate 2.2%, rank 4 of 55 distinct models (59 rows, some the same model from different hosts) when sorted by error rate, lower is better s1.
Alternatives
Nothing we have scored beats it for voice on score or on price.
- MAI-Transcribe-2Voice model–Pay as you goLower error rate at $0.10 an hour, but still a preview. Side by side
- Grok Voice Transcribe 2.0Voice modelNot reviewed yetError rate 2.3% on Artificial Analysis, almost level, at $1.67 per 1,000 minutes against $3.67 s1.
Evidence
Everything behind the call and the scores, folded so the page stays short. Spotted a wrong price, score or link? Report a mistake.
How we scored this
Voice has no score yet, because none of the public sources we use covers it.
Independent test
Reviews are drafted with help from AI models, including Anthropic's Claude. Model scores come only from outside leaderboards and independent evaluations, by a written rule.
No one paid for this review or gave us free access, and we earn nothing if you sign up. How we score
Sources 6
- s1Artificial Analysis speech to text leaderboard
- s2ElevenLabs API pricing
- s3ElevenLabs pricing
- s4ElevenLabs privacy policy
- s5ElevenLabs blog: Introducing Scribe v2
- s6ElevenLabs docs: models
Something here out of date or wrong? Report a mistake and we will check it against the source.
History 2 changes
Every change to a rating, the price or our call, with the reason. Scores are against what exists on the day, so they drift down as better things ship. Older entries come from before we moved to scores.
- New: Voice ratedReviewed: voice.
- Audit: re-opened Artificial Analysis speech to text; 2.2% rank 4 confirmed. Replaced Gemini 3.5 Transcribe (2.6%, pricier) with Grok Voice Transcribe 2.0 (2.3%, under half the price) as an alternative. Rating unchanged.
Use it well 4 guides on this site
Pages on this site that help with the jobs above.