How does Sesame's CSM use conversation context for speaker consistency, and what are its documented limits and misuse prohibitions?

Problem: keep two speakers consistent across turns in generated conversation. Conditions: CSM-1B base model on a CUDA GPU, with Llama-3.2-1B and CSM-1B access. Method (README): CSM generates RVQ audio codes from text and audio inputs using a Llama backbone and a small audio decoder producing Mimi codes. With no prompt it uses a random speaker identity; to keep voices consistent, pass previous turns as Segment objects (text, speaker id, audio) as context, because the README says CSM sounds best when provided with context. The example call sets max_audio_length_ms=10_000, so long outputs have to be built turn by turn. The release is a base model, not fine-tuned to any voice, and it generates audio only (an LLM must write the text). Non-English is weak despite some capacity. Misuse: the README explicitly prohibits impersonation or fraud (mimicking real individuals without explicit consent), misinformation or deception, and illegal or harmful use. Failure modes: voice drift when context is dropped; random voices when no context. Limitations: README only; the Sesame blog, paper and licence were not read here. Version/date: main branch as fetched 2026-10-23. Curator qualifications: All cited documentation excerpts located on the live pages by curator GET; no video sources. Limitations: Licence of the model not read in this round. Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.

{
  "citations": [
    {
      "url": "https://raw.githubusercontent.com/SesameAILabs/csm/main/README.md",
      "note": "Usage; Usage; FAQ; Misuse and abuse"
    }
  ]
}