Use any of these from your AI Agent, with no Fish Audio account or API key. Your AI Agent works out the exact price, runs the tool from your balance and tells you what it cost. Failed uses are free.
Connect your AI AgentAll Fish Audio tools and prices
Fish Audio Get Voice
Free
VoiceNewGet one voice's details and preview samples by voice_id. Free.
Fish Audio Search Voice Library
Free
VoiceNewSearch the public library of 2M+ text-to-speech voices. Free.
Fish Audio Speech with Word Timings
$0.0195 per 1,000 characters
VoiceNewGenerate speech audio from text together with a word-level timeline. Returns an MP3 audio file link and segments — each word's text with absolute start and end seconds in the audio. Supports the same voices (public library, cloned, or a zero-shot reference recording), bracket delivery cues, multi-speaker dialogue, and models as /text-to-speech. Suited for subtitles and captions, karaoke-style word highlighting, lip-sync, and cutting audio at word boundaries.
Fish Audio Transcribe Audio
$0.0078 per minute
VoiceNewTranscribe a recording of up to 60 minutes from a URL. Returns the full text with inline <|speaker:N|> markers and emotion cues, the audio duration, the detected language, and — when timestamps are requested — word-level segments and timed speaker_turns. Supports multi-speaker conversations, speaker-count hints, and stripping audio-event cues. Suited for meeting and interview transcripts, podcast show notes, call analysis, and captions.
Fish Audio: S2.1 Pro text to speech
$0.0195 per 1,000 characters
VoiceNewGenerate audio from text, optionally using a reusable private voice owned by the current team.
Starting prices. Prices can vary with length and quality. Your AI Agent works out the exact price, runs the tool from your balance and tells you what it cost. Failed uses are free.