October 27, 2026
Murf's List Voices endpoint now accepts a model parameter, with separate voice catalogs for Falcon 2.1 streaming and Gen2 synthesis.
Every Murf AI update in one feed — release notes, features and changes, straight from the source.
7 updates
Murf's List Voices endpoint now accepts a model parameter, with separate voice catalogs for Falcon 2.1 streaming and Gen2 synthesis.
Murf's beta WebSocket service covers 12 languages including Hindi and Tamil, supports 8 kHz telephony audio, and costs $0.24 per hour.
Existing falcon-2, falcon2 and FALCON identifiers now run Falcon 2.1 automatically, and the model adds IPA and dictionary pronunciation control.
Falcon 2 accepts inline IPA on Stream Speech and WebSockets, plus a pronunciation dictionary parameter that applies to every occurrence of a word.
Falcon 2 streaming now supports loudness adjustments from -50 to 50 through Stream Speech and WebSocket voice_config.
Falcon 2 returns per-word timing alongside streamed audio in every locale except Chinese, Japanese and Korean.
Murf decommissioned Gen2 for its Streaming API and recommends migrating to Falcon 2. Gen2 remains available for non-streaming text-to-speech.