--- title: "ElevenLabs Scribe" type: "AI Tool" url: "https://aidemos.com/tools/elevenlabs-scribe" description: "ElevenLabs Scribe nailed jargon-heavy audio with timestamps, confidence, and speaker labels, but crosstalk, code-switching, and a 401 broke." category: "audio-speech" website: "https://elevenlabs.io/docs/api-reference/speech-to-text" published: "2026-08-13T09:18:22.530033+00:00" updated: "2026-08-20T12:46:21.519687+00:00" --- # ElevenLabs Scribe Fast batch transcription with rich metadata, strongest on jargon and weaker on overlap and code-switching. ## TL;DR Verdict **Strong batch STT API with rich metadata and clear caveats** **Where it wins:** - You need batch speech-to-text with word timestamps, confidence values, and speaker labels in the payload. - You need strong accuracy on jargon-heavy English narration. - You need fast batch turnaround on long recordings and can work with about $0.2202/audio-hour. **Main limitation:** You need validated speaker attribution correctness in overlapping conversations. **Pricing:** Free / Pay-as-you-go $0.22/hr · Starter — $6/month $0.22/hr · Creator — $22/month (first month $11) $0.22/hr · Pro — $99/month $0.22/hr `Word timestamps` · `Speaker labels` · `3 scored inputs` · `Code-switching tested` **Website:** [Visit ElevenLabs Scribe](https://elevenlabs.io/docs/api-reference/speech-to-text) > **Strong batch STT API with rich metadata and clear caveats** > > ElevenLabs Scribe is a strong batch speech-to-text API for developers: every scored run returned word-level timestamps, confidence values, and speaker labels, and it was outstanding on the jargon-heavy sample. The tradeoff is that crosstalk produced heavy insertions and over-segmentation, while the bilingual run lost Spanish tokens and the trace recorded an HTTP 401, so it reads as a fast English-first transcription backend with clear limits on overlap and code-switching. ## Demo Recording [Video: ElevenLabs Scribe demo recording](https://cdn.futuresmart.ai/public/aidemos/86a430d970e943d4bec81d7aa92e8984.mov?v=1) *Video — Task-level tutorial recording for ElevenLabs Scribe.* ## Feature-by-Feature Breakdown ### Batch Speech-to-Text Transcription **Verdict:** Mixed The API transcribes longer or batch audio in a single request, including the medical narration, crosstalk, bilingual sample, and 18–36 minute recordings. The sampled cards use those runs as evidence for overall transcription throughput and quality across hard-audio variants. **Input:** > **Audio** **Output:** > **Image** **Input:** > **Audio** **Output:** > **Image** **Input:** > **Audio** **Output:** > **Image** **Input:** > **Audio** **Output:** **Input:** > **Audio** **Output:** **Input:** > **Audio** **Output:** **Input:** > **Audio** **Output:** RESULT > **Json** — RESULT **Input:** > **Audio** **Output:** RESULT > **Json** — RESULT **Input:** > **Audio** **Output:** RESULT > **Json** — RESULT **Input:** ``` INPUT-1: Overlapping Speech / Crosstalk — long-form batch run on a 35:43 recording. ``` **Output:** RESULT > **Image** — RESULT **Input:** ``` INPUT-2: Medical Jargon — long-form batch run on an 18:44 recording. ``` **Output:** RESULT > **Image** — RESULT **Input:** ``` INPUT-3: Bilingual Code-Switching — long-form batch run on a 32:18 recording. ``` **Output:** RESULT > **Image** — RESULT **Bottom line:** Best on the medical jargon sample, middling on crosstalk, and weaker on bilingual spans, so it is useful but not evenly strong across the hard-audio set. ### Transcript Metadata The API returns structured transcript payloads with word-level timestamps, confidence values, speaker labels, and other annotation fields. The evidence is drawn from raw JSON transcript output and per-token metadata that was consistently present across the sampled runs. **Input:** > **Audio** **Output:** **Input:** > **Audio** **Output:** **Input:** > **Audio** **Output:** **Bottom line:** This metadata is consistently present and usable downstream on every scored run. ### Speaker Diarization The API assigns speaker labels in transcript output and reports distinct-speaker counts for audio such as crosstalk, narration, and bilingual conversation. The sampled cards emphasize label presence in the transcript payload and downstream use for analytics or captions. **Input:** Test input > **Audio** — Test input **Output:** Raw API response > **Image** — Raw API response **Input:** > **Audio** **Output:** RESULT > **Image** — RESULT **Input:** > **Audio** **Output:** RESULT > **Image** — RESULT **Input:** > **Audio** **Output:** RESULT > **Image** — RESULT **Bottom line:** The labels exist, but the benchmark only measured label presence and count, not attribution correctness. ### Code-Switching / Multilingual Transcription The API transcribes mixed-language audio without special configuration, as shown on the Spanish-English sample. The evidence shows successful mixed-language transcription with weaker Spanish recall than clean-English narration. **Input:** > **Audio** **Output:** RESULT > **Image** — RESULT **Bottom line:** It can transcribe mixed-language audio, but Spanish quality is materially weaker than the clean-English medical sample. ## Developer API pricing Scribe v2 pricing from the vendor page; the per-hour rate stays flat across paid tiers. | Plan | Price | Notes | | --- | --- | --- | | Free / Pay-as-you-go ★ | $0.22/hr | 4 h 30 min included; Scribe v2 Realtime $0.39/hr, 2 h 30 min included. | | Starter — $6/month | $0.22/hr | 27 h included; Realtime 15 h included. | | Creator — $22/month (first month $11) | $0.22/hr | 100 h included; Realtime 56 h included. | | Pro — $99/month | $0.22/hr | 450 h included; Realtime 254 h included. | | Scale — $299/month | $0.22/hr | 1,359 h included; Realtime 767 h included. | | Business — $990/month | $0.22/hr | 4,500 h included; Realtime 2,538 h included. | | Enterprise | Custom | Requires sales contact; custom DPA/SLA, SSO, HIPAA BAA. | | Startup Grants Program | Free for 12 months | 33,000,000 characters; application required. | *Per-hour Scribe rate does not change across plans: paid tiers buy included hours, not a lower unit rate. Add-ons listed in the report were entity detection (+$0.070/hr) and keyterm prompting (+$0.050/hr).* ## Is It Right For You? **Use it if** - You need batch speech-to-text with word timestamps, confidence values, and speaker labels in the payload. - You need strong accuracy on jargon-heavy English narration. - You need fast batch turnaround on long recordings and can work with about $0.2202/audio-hour. - You need some code-switching support and can tolerate imperfect Spanish recall. **Skip it if** - You need validated speaker attribution correctness in overlapping conversations. - You need overlap-heavy audio to stay faithful without insertions. - You need bilingual spans to stay near clean-English accuracy. - You need streaming latency evidence from this benchmark. - You need a repeatability rerun on the same input. ## Classification - **Category:** audio-speech - **Subcategory:** audio-to-text - **Type:** speech - **Built for:** Other ## Frequently Asked Questions **Q: How accurate was ElevenLabs Scribe on overlapping speech?** On the crosstalk sample, it scored WER 26.67%, returned 7,180 words against 7,579 reference words, and produced 383 insertions. The transcript detail also showed over-segmentation, with 5 speaker labels for a 4-participant recording. **Q: How did it perform on medical jargon?** It was strongest on the medical sample, scoring WER 3.01% and 100.0% jargon recall. The run returned 2,743 words against 2,728 reference words. **Q: How well did it handle Spanish-English code-switching?** It was usable but clearly weaker than the English medical sample: WER was 28.57%, Spanish token recall was 57.5% (46 of 80 types), and the transcript detail showed the engine dropping the Spanish token 'ahora' and rewriting it as 'oh now'. **Q: Does ElevenLabs Scribe return timestamps, confidence, and speaker labels?** Yes. All three scored runs reported word-level timestamps, confidence via logprob, and speaker labels via speaker_id, with payload depth reported as 3/3. **Q: Was speaker attribution correctness measured?** No. The benchmark confirmed that speaker labels exist and counted them, but it did not compute a diarization error rate or otherwise score whether each label was assigned to the right person. **Q: What was the benchmark cost and speed?** The report's normalized rate was $0.2202 per audio-hour ($0.00367/min). Measured runs ranged from 6.07s to 41.76s wall clock, with real-time factor from 0.00313 to 0.01949. **Q: Was repeatability tested with a rerun on the same audio?** No. This report includes one scored run per input, but it does not include a rerun of a prior input, so repeatability was not tested here. ## Similar Tools AI tools similar to ElevenLabs Scribe: - [Deepgram Nova-3](https://aidemos.com/tools/deepgram-nova-3) — Batch speech-to-text with rich metadata, but weak on crosstalk and code-switching. - [Rev AI](https://aidemos.com/tools/rev-ai) — Low-cost batch speech-to-text with structured JSON, word timestamps, and speaker labels, but mixed accuracy on hard audio and weak multilingual recall. - [Gladia](https://aidemos.com/tools/gladia) — Batch STT with rich JSON metadata and strong jargon recall, but weak overlap handling and a channel-duplication caveat on bilingual audio. - [Speechmatics](https://aidemos.com/tools/speechmatics) — Strong batch STT for hard English audio, but weak on code-switching as configured. ## Need a custom AI solution for this use case? If you are looking to build a custom audio transcription, batch transcription, or transcription workflow for your business or internal workflow, email us at [contact@futuresmart.ai](mailto:contact@futuresmart.ai). ### Found something inaccurate or missing? We try to keep our AI research accurate and useful. If you found outdated information, an issue, or have a suggestion, email us at [collaborate@aidemos.com](mailto:collaborate@aidemos.com).