ElevenLabs Flash v2.5
Audio Available elevenlabs/flash-v2-5 · by ElevenLabs · neural-tts
Pricing — 1 offering(s)
Text characters
- $60.00 / 1M characters Historical 2024-06-01 → 2026-07-29
- $50.00 / 1M characters Current 2026-07-30 → present
Showing the active price and any recorded history. Full pricing history is available via the paid API — see API docs.
Capability profile
voice naturalness moderate
language support strong
voice variety strong
streaming latency strong
cloning support strong
Benchmarks
| Benchmark | Score | Config | Source |
|---|---|---|---|
| First-byte latency (vendor-reported) | 75 ms | Streaming endpoint, ElevenLabs infrastructure. Vendor-reported, not independently verified. | source ↗ |
| MOS (naturalness) | — | No formally published MOS score. Community comparisons rate it below Multilingual v2 but above commodity TTS APIs. | — |
Operator guidance
The default ElevenLabs choice for interactive and real-time applications. At ~$50/1M chars (half the cost of Multilingual v2), it covers most use cases. Upgrade to Multilingual v2 only when audio quality is the primary differentiator (e.g. final production narration).
Use cases
- Conversational AI and real-time voice agents
- Interactive applications requiring sub-100ms TTS response
- Cost-optimised ElevenLabs use cases (0.5 credits/char vs 1 credit/char for v2)
Limitations
- Credit-based pricing; effective rate is plan-dependent
- Slightly lower audio quality than Multilingual v2
- Directly published per-character API rate (not plan-estimated)
Citations
Compare models
ComparingElevenLabs Flash v2.5with
Pick a model above to see the comparison.