Scribe v2
by ElevenLabs · Released Undisclosed
ElevenLabs' state-of-the-art speech recognition for recorded audio: 100 languages including 13 Indian languages, automatic language detection, word-level timestamps. File transcription. $0.2292 per audio hour.
Scribe v2
Powered by ElevenLabs · Batch ASR (ElevenLabs Scribe v2)
Context Window
N/A
Parameters
Undisclosed
Max Output
N/A
Category
Speech to Text
Overview
Scribe v2 is ElevenLabs' speech-to-text model for recorded audio, with word-level timestamps and automatic language detection across 100 languages, including Hindi, Bengali, Tamil, Telugu, Marathi, Gujarati, Kannada, Malayalam, Punjabi, Odia, Assamese, Urdu and Sinhala.
On CallMissed it transcribes files on POST /v1/audio/transcriptions. Leave language out to detect it, or pass a base code such as hi. Silence counts toward the billed duration. For live voice agents use scribe_v2_realtime.
Pricing
| Metric | Price |
|---|---|
| Price /hour | ₹22.0000 |
1 credit = ₹1 ≈ US$0.0104 (US$1 = ₹96). Transparent per-call pricing — you pay only for what you call, with no per-seat charge or minimums.
Key Highlights
- 100 languages including 13 Indian languages, automatic language detection
- File transcription with word-level timestamps
- ElevenLabs' state-of-the-art speech recognition for recorded audio
Benchmarks
| Benchmark | Score |
|---|---|
| Languages | 100 |
| Price | $0.2292 |
| Deployment | File transcription |
Technical Details
- Model ID is ElevenLabs' own (scribe_v2)
- language takes a base ISO code such as hi; leave it out to detect the language
- Silence counts toward the billed duration
- Paid plans only
Strengths
- 100 languages with automatic detection
- ElevenLabs' state-of-the-art speech recognition for recorded audio: 100 languages including 13 Indian languages, automatic language detection, word-level timestamps
Limitations
- File transcription only — use scribe_v2_realtime for live calls
- Paid plans only
Use Cases
API Example
curl -X POST https://api.callmissed.com/v1/audio/transcriptions \ -H "Authorization: Bearer cm_YOUR_KEY" \ -F "model=scribe_v2" \ -F "[email protected]"
Endpoint: POST /v1/audio/transcriptions · Model ID: scribe_v2
Try Scribe v2 now
Get 1000 free API credits on signup. No credit card required.