Fish Agent launches no-code voice agents

// 5h agoPRODUCT LAUNCH

Fish Agent launches no-code voice agents

Fish Audio’s new Fish Agent platform lets users describe voice agents in plain English, attach knowledge and API tools, choose a voice, and deploy to websites, apps, or inbound and outbound calls. The public beta includes Live 3 full-duplex speech, human handoff, call testing, and $5 trial credit.

// ANALYSIS

Fish Agent is a credible move from expressive text-to-speech into the higher-value action layer, but production reliability will matter more than how quickly users create a demo.

–No-code setup lowers the barrier while web widgets, phone numbers, WebRTC, and SDKs provide developer escape hatches.
–Knowledge bases, webhooks, calendar and CRM actions, and call transfers make it more than a conversational receptionist.
–Live 3’s interruption handling and turn-taking could improve naturalness beyond conventional cascaded voice stacks.
–Promotional pricing starts at $0.035 per minute, with additional phone, number, and premium-LLM costs.
–The public beta still needs validation on noisy calls, complex workflows, latency, and failure recovery.

// TAGS

fish-agentvoice-agentagentspeechno-codeautomationapihosted-service

DISCOVERED

5h ago

2026-11-12

PUBLISHED

7h ago

2026-11-12

RELEVANCE

8/ 10

AUTHOR

FishAudio

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE37m ago

Framer Agent Generates Images, Shaders

Framer’s AI Agent can now turn natural-language prompts into generated imagery and interactive shader effects, including pointer-driven smudges, halftones, CRT visuals, bokeh, and pencil styles. The workflow aims to produce polished web interactions without manual code or After Effects.

OPEN SOURCE44m ago

Perplexity Decider v1.3 Adds Locate Extraction

Perplexity open-sourced its latest decision models under Apache licensing, adding Locate for extracting exact text spans and character positions. Both models are free on OpenRouter for one week and support classification, routing, moderation, reranking, and structured evaluation.

LAUNCH49m ago

Daybreak Red Team automates continuous pen tests

OpenAI’s Daybreak Red Team puts coordinated AI agents to work testing web applications, validating vulnerabilities, and checking whether patches actually stop exploits. The early-access service targets organizations that need continuous offensive security coverage without maintaining a dedicated red team.