Fast, low-cost speech-to-text of a single audio clip (multilingual, auto-detected unless a language hint is passed). Sub-second on short clips, suited to turn-based voice chat as well as recordings; caller must chunk audio longer than the provider file-size limit (~25MB) into clips.
Pass species_name to pin this model; omit it and Fire uses the default for the
endpoint. Every response carries meta.price.usd and meta.call_id.
In: audio · Out: text
Family openai · genus whisper · served by edenai
Free to sign up. Pay only when you top up.