NativePort
← Catalog
Fish Audio logo

Fish Audio

TTS, transcription & voice design Voice & Audio fish.audio ↗

Four fixed routes reach Fish Audio's text-to-speech, transcription, and from-a-description voice-design models, each metered on the exact unit Fish Audio itself bills — bytes, audio-hours, or a flat per-call rate.

Where Fish Audio lands

Composite scores out of 10, from benchmark runs where every provider faces the identical task corpus. Rank is within that capability's field. Full method: how we measure.

Fish Audio sits outside the web-access benchmark — the search/scrape/crawl corpora don't exercise a voice & audio API, so this page carries catalog facts without a scorecard.

The honest pitch

Strongest case

Pick it for production text-to-speech with expressive, natural-sounding output, real speech-to-text, or building a new voice from a written description, all landing on the same key and balance as everything else here.

Known trade-off

Skip it for persistent voice-clone models or account-balance visibility: Fish Audio's model-management and wallet endpoints aren't mounted, since a shared gateway key would let one customer see or reuse another's saved models and balance. Per-request zero-shot cloning still works on a single `/v1/tts` call, and Fish Audio's WebSocket streaming endpoint isn't proxied either — its chunked, timestamped HTTP streaming route covers the same low-latency case instead.

About Fish Audio

Fish Audio builds expressive text-to-speech, speech recognition, and from-scratch voice design around its own model family, reached here through four fixed action endpoints rather than the platform’s full account-management surface. Text-to-speech bills on the literal UTF-8 byte count of the request text, transcription is metered from the real audio duration each response reports, and voice design is a flat rate per successful call — all read from Fish Audio’s own published prices rather than an estimate. Per-request zero-shot voice cloning rides along inline on a single call, while the platform’s persistent voice-model library and account-balance endpoints stay off-limits on the shared key every customer here uses.

Reaching it through NativePort

Identical paths, parameters and responses to Fish Audio's own documentation — the gateway holds the upstream credential and meters your balance at Fish Audio's real published usage price.

curl https://api.nativeport.ai/fishaudio/<native-path> \
  -H "Authorization: Bearer $NATIVEPORT_API_KEY"
Entry price $15/1M UTF-8 bytes TTS / $0.36/audio-hr ASR / $0.01/req voice-design Provider MCP community Route /fishaudio