Laying out the streets…STEP 1 OF 3

Fish Audio Realtime STT · Office #57,145

Realtime speech-to-text for voice agents, $0.36 an hour

In the Transcription and dictation neighborhood (Work and office). In town since 31 Oct 2026.

Nobody has claimed this office yet. Tablif records every new product and gives it an office; when its owner claims it, the lights go on.

Is this yours? Claim it

What Tablif read on Fish Audio Realtime STT's site

Fish Audio Realtime STT describes itself as: “Realtime Speech to Text - Fish Audio”

What it is

Calls itself “speech-to-text”.

  • Calls itself: speech-to-text
“Realtime speech-to-text for voice agents”

Where it puts itself

Rules out “Compressed formats such as Opus or MP3 are not accepted on this endpoint.”.

  • Says it will not: Compressed formats such as Opus or MP3 are not accepted on this endpoint.
“…transcribe-stream-1 does more than transcribe: it decides when the user has finished their turn, usually tells the user talking to your app apart from background sound, and notices when a “mm-hm” is only an acknowledgement.”
“Compressed formats such as Opus or MP3 are not accepted on this endpoint.”

What it costs

Prices quoted: $0.36 an hour.

  • Price: $0.36 an hour
“…transcribe-stream-1 costs $0.36 per hour, billed per second of session duration as its own line item, Realtime ASR.”
“Pricing & Rate Limits -> https://docs.fish.audio/developer-guide/models-pricing/pricing-and-rate-limits”

Who it sells to

Sells to developers. Made for Voice agents. In 29 language codes.

  • Sells to: developers
  • Made for: Voice agents
  • Languages: 29 language codes
“Documentation for Fish Audio APIs, SDKs, models, voice cloning, real-time streaming, and self-hosting.”
“Voice agents Know when the user has finished, start replies early, and handle interruptions.”

How it runs

A API. Hosted in the cloud. Offers an API. Open source. AI is the core of the product.

  • Kind: api
  • Runs where: cloud / hosted
  • API: yes
  • Open source: yes
  • AI role: core to the product
“Open wss://api.fish.audio/v1/asr/realtime from your server with the header”
“Documentation for Fish Audio APIs, SDKs, models, voice cloning, real-time streaming, and self-hosting.”

What it works with

Built on Mintlify. Names transcribe-1-pro and transcribe-stream-1 on its pages.

  • Built on: Mintlify
  • Names: transcribe-1-pro · transcribe-stream-1
“Fish Audio Realtime STT”
“Powered by This documentation is built and hosted on Mintlify, a developer documentation platform”

What it offers as proof

In beta. Instant signup. Publishes docs and a blog.

  • Stage: beta
  • Instant signup: yes
“Fish Audio Realtime Speech to Text (transcribe-stream-1, in preview) streams audio over a WebSocket and returns transcripts turn by turn.”
“Sign Up Sign Up”

Sources

Tablif read these pages, last on 31 Oct 2026. Everything above is what the product says about itself; Tablif does not verify every claim.

Similar products in Tablif Town

Explore Tablif Town