audio model comparison
Gemini 3.8 Live vs Scribe v2 Realtime
Gemini 3.8 Live and Scribe v2 Realtime are both current audio models, from Google and ElevenLabs. Gemini 3.8 Live is 23% cheaper per audio minute (audio input) than Scribe v2 Realtime, $0.005 vs $0.0065.
Data verified October 13, 2026 · Dataset 2026-10-13
Side by side
Prices in effect today, compared at the same tier wherever both list one. The better value in each row is highlighted.
| Fact | Gemini 3.8 Live | Scribe v2 Realtime |
|---|---|---|
| Price per audio minute (audio input) | $0.005 (better) | $0.0065 |
| Price per audio minute (audio output) | $0.018 | Not listed |
| Artificial Analysis AA-WER Streaming | Not measured | 3.59 % WER (#2 of 2) |
| Provider | ElevenLabs | |
| Release date | September 15, 2026 | November 11, 2025 |
| Access | API only | API only |
| Context window | Not reported | Not reported |
| Max output | Not reported | Not reported |
| Input | text, audio | audio |
| Output | text, audio | text |
No independent benchmark has scored both models yet. Each rank counts the current models scored on that benchmark.
What each costs
Example workloads at each provider's listed rates, then every other rate either one lists. The cheaper figure in each row is highlighted.
| Workload or rate | Gemini 3.8 Live | Scribe v2 Realtime |
|---|---|---|
| 100 hours of audio input | $30 (better) | $39 |
| 100 hours of audio output | $108 | Not listed |
| Other listed rates | ||
| 1M input tokens, audio | $3 | Not listed |
| 1M output tokens, audio | $12 | Not listed |
| 1M input tokens, text | $0.75 | Not listed |
| 1M output tokens, text | $4.50 | Not listed |
When to choose each
Gemini 3.8 Live
Where it leads
- Lower price per audio minute (audio input), $0.005 vs $0.0065
- Accepts text input
- Also outputs audio
- Supports text-to-speech and reasoning
Best for
- Customer-facing voice agents that need natural turn-taking
Watch out for
- Audio is billed per token; the per-minute figures are Google's equivalents ($0.005 input, $0.018 output)
- No independent voice benchmark is recorded here
Scribe v2 Realtime
Where it leads
- Supports speech-to-text
Best for
- Live transcription
Watch out for
- $0.39 per hour of audio, about 1.8 times batch Scribe v2
Gemini 3.8 Live vs Scribe v2 Realtime FAQ
Which is cheaper, Gemini 3.8 Live or Scribe v2 Realtime?
Gemini 3.8 Live is 23% cheaper per audio minute (audio input) than Scribe v2 Realtime, $0.005 vs $0.0065.
How much would 100 hours of audio input cost with Gemini 3.8 Live or Scribe v2 Realtime?
100 hours of audio input comes to $30 with Gemini 3.8 Live and $39 with Scribe v2 Realtime at their listed rates.
How do Gemini 3.8 Live and Scribe v2 Realtime differ in features?
Gemini 3.8 Live takes text and audio input; Scribe v2 Realtime takes audio. Gemini 3.8 Live produces text and audio; Scribe v2 Realtime produces text. Only Gemini 3.8 Live supports text-to-speech and reasoning. Only Scribe v2 Realtime supports speech-to-text.
Related comparisons
- Gemini 3.8 Flash-Lite TTS vs Gemini 3.8 Live
- Grok Voice Transcribe 2.0 vs Scribe v2 Realtime
- Gemini 3.8 Flash TTS vs Gemini 3.8 Live
- Gemini 3.5 Transcribe vs Scribe v2 Realtime
- Gemini 3.1 Flash Live Preview vs Gemini 3.8 Live
- GPT Transcribe vs Scribe v2 Realtime
- Gemini 3.5 Live Translate Preview vs Gemini 3.8 Live
- Gemini 3.1 Flash Live Preview vs Scribe v2 Realtime
- Scribe v2 vs Scribe v2 Realtime
- Gemini 3.5 Live Translate Preview vs Scribe v2 Realtime
- GPT-4o Transcribe vs Scribe v2 Realtime
Production evaluation
Choosing between Gemini 3.8 Live and Scribe v2 Realtime?
Public benchmarks narrow the shortlist. We run both on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- A head-to-head evaluation on your real workload
- Routing between models by cost and difficulty