fish.audio TTS Requires in (create one at https://fish.audio/go-api/api-keys/). Create voice models in the fish.audio playground and pass their id as to reuse a cloned voice. Current API Single synchronous call returning raw audio bytes: The backend model is chosen with the HTTP header , not a body field. In OpenMontage this maps to the tool's input. Backend models is required — there is no default . Pass one of: - — latest generation. Best quality: inline emotion tags, 80+ languages, multi-speaker. Hero narration. - — promotional free access to s2.1-pro. Drafts, samples, and validation runs…