# Crossing the uncanny valley of conversational voice

*Source* · `src-sesame-2025-csm` · status: **n/a**

| field | value |
|---|---|
| kind | Technical report / blog |
| authors | Sesame |
| venue | Sesame research |
| date | 2025-02-27 |
| url | https://www.sesame.com/research/crossing_the_uncanny_valley_of_voice |
| accessed | 2026-10-24 |

## Notes

Conversational Speech Model: Llama-variant backbone (1B, 3B, 8B) plus small decoder over Mimi split-RVQ tokens at 12.5 Hz; about one million hours of mostly English audio. CMOS: no preference vs human without context; human recordings preferred with 90 s of context. No turn-taking modeling; Apache 2.0 release announced.

## Backlinks (computed)

**cited by:** [Realtime speech-to-speech and expressive TTS for characters](../technique/realtime-voice-models.md)

## Citation

Sesame (2025-02-27). *Crossing the uncanny valley of conversational voice*. Sesame research https://www.sesame.com/research/crossing_the_uncanny_valley_of_voice

---
Provenance: created in run `2026-10-24-techniques-llm-agents`.