Models Model Description Languages Coda Rime’s flagship model (May 2026). LLM backbone + speech engine, sub-100ms latency, 184 voices, top-rated quality. en, es, fr, pt, de, ja ArcanaV3 Previous flagship. Expressive, multilingual codeswitching. ar, en, fr, de, he, hi, ja, pt, es, ta
Rime.Coda.<VoiceId> Rime.ArcanaV3.<VoiceId>
Coda is Rime’s recommended model for new integrations. It surpasses ArcanaV3 in naturalness, prosody, and artifact-free output.
Voice Samples Voice Language Gender Sample Rime.ArcanaV3.albionen-US Male Rime.ArcanaV3.arcadeen-US Male
WebSocket Query Parameters Parameter Type Default Description audio_formatstring mp3mp3, linear16.sample_rateinteger 240008000, 16000, 22050, 24000, 44100, 48000, 96000.
Voice Settings Field Type Default Description voice_speedfloat 1.0Speech rate multiplier.
{ "text" : " " , "voice_settings" : { "voice_speed" : 0.9 } }
REST API Fields Field Type Default Description voice_speedfloat 1.0Speech rate multiplier. output_typestring binary_outputbinary_output, base64_output, or audio_id.
Response Default (binary_output): chunked audio bytes.
With output_type: "base64_output": JSON with base64-encoded audio.
With output_type: "audio_id": JSON with an audio_url for deferred retrieval. 
