Independent review. IonBin has no partnership with Fish Audio and was not paid for this page. Our evaluation is our own, based on public documentation and our research. Product names are trademarks of their owners and are used for identification only. How disclosure works.
Text to speech and voice cloning, plus a voice-agent platform (public beta) that can answer calls on a phone number, call your webhooks mid-call and warm-transfer to a person with a private briefing.
Managed local numbers are offered for the US and Canada through Twilio, with each number bound to an agent. Existing numbers can be imported over SIP. Carrier configuration determines available transfer behavior. source ↗
A warm transfer can place the caller on hold while the agent privately briefs a person; confirm mode waits for acceptance before merging. The full call remains recorded after merge, while the transcript covers the agent segment. SIP transfers require appropriate carrier configuration. source ↗
Webhook tools call your HTTP endpoint and can use caller information from session variables. Fish Audio sends the request and processes the response; tool-call history can record results. Hosting your database yourself does not mean data never reaches Fish Audio. Limit returned fields and review recording/retention settings. source ↗
USD prices: Free includes 8,000 credits/month; Plus is $15 monthly or $132/year; Pro is $100 monthly or $900/year; Max is $999 monthly or $8,988/year. Agent API use is billed separately. Confirm checkout terms and commercial rights. Checked 2026-10-18. source ↗
The base conversation rate is $0.06/minute, plus model-token charges where applicable. Managed phone calls normally add $0.01/minute, with higher rates for some outbound destinations. Managed numbers cost $1.20/month; cold and warm post-handoff calls have separate rates. Imported SIP numbers have no Fish phone surcharge or transfer fee, but your carrier can charge. Checked 2026-10-18. source ↗
The terms prohibit rights infringement and deceptive uses. Use voices and content you have rights and consent to use, and identify AI callers. The plan page limits free generated content to personal, non-commercial projects; review paid-plan rights before commercial use. source ↗
How Fish Audio connects to each AI platform: native connector or MCP, API through code the agent writes, browser control, or file upload.
| Platform | MCP / connector | API (agent-written code) | Browser | Upload / export |
|---|---|---|---|---|
| Claude (incl. Claude Code) | Not documented https://docs.fish.audio/llms.txt — no official MCP server confirmed in the reviewed documentation index; this is not proof that none exists. | Not documented Claude (incl. Claude Code): Claude Code edits files and runs commands Fish Audio publishes an API, but this pairing still needs network, authentication and execution-scope checks. Fish Audio API ↗Claude (incl. Claude Code) docs ↗ | Inferred Claude Code with the Claude in Chrome extension (Chrome, Edge and other Chromium browsers). Fish Audio is a web app; the pairing itself is not documented. Claude (incl. Claude Code) browser docs ↗ | Not documented Verify which side exports and which imports, supported formats and permissions. Fish Audio's recorded upload/import status is yes; Claude (incl. Claude Code)'s file status is yes. These flags do not establish a file-transfer route. Fish Audio file docs ↗Claude (incl. Claude Code) file docs ↗ |
| OpenAI Codex | Not documented https://docs.fish.audio/llms.txt — no official MCP server confirmed in the reviewed documentation index; this is not proof that none exists. | Not documented OpenAI Codex: Edits files and runs commands locally; cloud tasks run in isolated workspaces Fish Audio publishes an API, but this pairing still needs network, authentication and execution-scope checks. Fish Audio API ↗OpenAI Codex docs ↗ | Inferred Only in the ChatGPT desktop app; not in the Codex CLI or IDE extension. Fish Audio is a web app; the pairing itself is not documented. OpenAI Codex browser docs ↗ | Not documented Verify which side exports and which imports, supported formats and permissions. Fish Audio's recorded upload/import status is yes; OpenAI Codex's file status is yes. These flags do not establish a file-transfer route. Fish Audio file docs ↗OpenAI Codex file docs ↗ |
| Google Antigravity | Not documented https://docs.fish.audio/llms.txt — no official MCP server confirmed in the reviewed documentation index; this is not proof that none exists. | Not documented Google Antigravity: Agents edit code and run tasks Fish Audio publishes an API, but this pairing still needs network, authentication and execution-scope checks. Fish Audio API ↗Google Antigravity docs ↗ | Inferred The /browser guide documents App and CLI support through Chrome DevTools MCP; the overview comparison conflicts on CLI availability. IDE browser features are separate. Fish Audio is a web app; the pairing itself is not documented. Google Antigravity browser docs ↗ | Not documented Verify which side exports and which imports, supported formats and permissions. Fish Audio's recorded upload/import status is yes; Google Antigravity's file status is yes. These flags do not establish a file-transfer route. Fish Audio file docs ↗Google Antigravity file docs ↗ |
Confirmed is reserved for evidence of the specific connection route. The current named integrations include plugins, skills and CLIs, so a named platform alone does not confirm MCP or a native connector. Inferred means each side documents a relevant capability, but no document describes the pairing. Code execution still needs network and credential access; file handling still needs a compatible format and transfer direction. Not documented means the records do not establish the route. IonBin has not tested these pairings. Recorded Oct 18, 2026.
To verify Official MCP server availability is unconfirmed; API and SDK access are documented.
| Level | Status | Detail / source |
|---|---|---|
| Native connector / MCP | To verify | Official docs ↗ — no official MCP server confirmed in the reviewed documentation index; this is not proof that none exists. |
| API / CLI | Yes | Official docs ↗ — REST API and SDKs for hosted voice agents; speech and cloning have separate API documentation. |
| Browser / manual | No | Browser access is recorded alongside a documented programmatic route. |
| File upload / import | Yes | Official docs ↗ — upload one or multiple reference audio samples to create a reusable voice model. |
Recorded Oct 18, 2026. Setup and plan limits vary; check the vendor's docs. How levels are assigned.
No confirmed MCP server yet.
Automation hubs to assess for a custom API connection: Gumloop, Make, n8n, Zapier. Verify credentials, supported requests, limits and error handling; no configured integration is implied.
No long-form review yet. Verdict is based on research, not hands-on testing.
AI speech generation and dubbing for narration, translations and audio versions of content. Its hosted MCP server lets assistants manage voice agents and generate speech within granted workspace permissions.
Speech recognition and voice-agent APIs. Flux adds model-integrated end-of-turn detection for voice agents; Nova covers conventional streaming and batch transcription.
ElevenLabs is a trademark of its owner. IonBin is an independent publisher and is not affiliated with, sponsored by, or endorsed by ElevenLabs. Product names are used for identification and review purposes only.
With your permission, Google Analytics uses cookies to measure page visits and help us improve IonBin. It stays off until you choose. We do not enable advertising tracking.
You can change this choice anytime below. Turning analytics off reloads open IonBin tabs where analytics is running. Save unfinished form text first. Privacy details.