On November 12 (01:00 SGT on November 13) Fish Audio launched Fish Agent, a no-code platform for voice agents: describe the assistant you want in text and it is generated, with a company-reported median deploy time of 32 seconds. Agents can rent a phone number or bring their own to make and take calls, use a platform model or your own OpenAI-compatible endpoint, and extend through webhooks, knowledge bases and a REST API. Conversations run on Live 3, the full-duplex model Fish Audio released earlier. The docs label the platform a public beta. Pricing is $0.035 per minute (normally $0.07, discounted until December 31), plus $0.01 per minute for phone calls and $1.20 per month per number, with $5 of free credit for new users.
Key Takeaways
- ✓No-code generation: describe a voice agent in text to create it, with a company-reported median deploy time of 32 seconds
- ✓Phone calls: rent a number or bring your own carrier via BYO SIP to make and take calls; managed numbers are US and Canada local only, with warm and cold transfers to humans
- ✓Swappable brain: a platform model by default, or your own OpenAI-compatible chat completions endpoint, while Fish Audio still handles speech recognition, synthesis and interruptions
- ✓Pricing: $0.035 per minute (normally $0.07, discounted until December 31, 2026), plus $0.01 per minute for phone calls and $1.20 per month per number; new users get $5 of credit with no card required
- ✓Testing and monitoring: single-turn, multi-turn and tool-call tests, versioned publishing and rollback, call recordings, transcripts and automatic post-call analysis; the platform is still in public beta
Key Decision Metrics at a Glance
Turn your technical choice into a development budget
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Background and the problem
Voice agents are moving from demos into real work such as front desks, bookings, customer support and outbound follow-ups. But building one that can actually take phone calls usually means wiring together speech recognition, an LLM, speech synthesis, phone lines and interruption handling yourself. Fish Audio started in text-to-speech and released its full-duplex Live 3 voice model on November 10. Fish Agent packages the whole chain as a hosted platform so that people who do not write code can put a phone assistant live in minutes.
How it works
There are three ways in: a visual console, a REST API under /v1/agent/*, and the @fishaudio/agent-client and @fishaudio/agent-react web SDKs. Each agent is a system prompt, a first message, a voice and language, a knowledge base and tools. Edits autosave to a draft, and publishing freezes it into an immutable numbered version. Tools come in webhook, client and system types, and endpoints can be imported from cURL. The LLM is swappable: point it at your own OpenAI-compatible endpoint and the platform sends the full context and tool definitions, while Fish Audio keeps handling recognition, synthesis, interruptions and billing. Conversations run on Live 3 by default, which listens while it speaks and tells backchannels apart from real interruptions.
Benchmarks
All published numbers are company-reported: a 32-second median deploy time and more than 2 million voices in 30+ languages. Fish Audio earlier said Live 3 can decide to respond in as little as 186 ms and currently supports English only. No task-completion rates, end-to-end latency distributions or standardized benchmarks against other voice agent platforms have been published.
Getting started
- In the Agents console at fish.audio, describe what you need to generate an agent; new accounts get $5 of credit, about 140 minutes at the promotional rate before phone surcharges. 2. Upload PDFs, Markdown or URLs as knowledge and set up order lookup or booking endpoints as webhook tools. 3. Validate with single-turn, multi-turn and tool-call tests, then publish. 4. Rent a US or Canada local number for $1.20 per month, or bring your own via BYO SIP; to keep your own dialogue logic, connect through Custom LLM.
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.