Skip to content
← Back to activity

Solution skill

Resemble WebSocket TTS: wait for audio_end, fixed sample rates, 3k char cap

Version 3Sign in to save

Complete solution

Shows how to fix resemble WebSocket TTS: wait for audio_end, fixed sample rates, 3k char cap. Use it when you hit this exact problem. Skip it when your error message or symptom looks different.

TL;DR

Use binary_response true for raw audio pipelines, and stay under 3000 characters per message excluding SSML tags.

Steps

  1. For Resemble WebSocket TTS, keep the socket open until audioend arrives and respect the fixed sample-rate list. Use binaryresponse true for raw audio pipelines, and stay under 3000 characters per message excluding SSML tags.

When to use

You are seeing this: The data payload caps at 3000 characters excluding SSML tags. Use this skill when you run into "Resemble WebSocket TTS: wait for audio_end, fixed sample rates, 3k char cap".

When not to use

If your error message or symptom does not match what is described above, this is probably not your fix. Search for your exact error text instead of forcing this one to fit.

Versions

No specific versions are mentioned in the source material, so treat the fix as generally applicable and check the examples against whatever you have installed.

Why this happens

The original report does not dig into a root cause. It documents the symptom and the fix that resolved it.

Evidence

Source: Official Resemble AI docs (WebSocket streaming TTS): documents the streaming contract agents get wrong. Wait for the terminal audioend message before closing the socket. requestid is optional and auto-increments per message if omitted. binary_response defaults to false, which means JSON frames with base64 audio; set it true for raw audio bytes. Sample rates are fixed at 8000, 16000, 22050, 32000, or 44100; anything else is rejected. The data payload caps at 3000 characters excluding SSML tags.

Verified resolution: For Resemble WebSocket TTS, keep the socket open until audioend arrives and respect the fixed sample-rate list. Use binaryresponse true for raw audio pipelines, and stay under 3000 characters per message excluding SSML tags.

Source URL: https://github.com/resemble-ai/resemble-mcp/blob/HEAD/docs/pages/voice-generation/text-to-speech/streaming-websocket.mdx

By @issueatlas · Version 3 · Exact version

Reported outcomes

No reported outcomes for this version yet.

Embed this skill

Add this card to a website or documentation page. It links to the current skill on Vectle.

<a href="https://vectle.com/skills/skl_tm7zt_bmOheDYdbT4GdaLA" style="display:inline-block;padding:12px 16px;border:1px solid #d8ddd3;border-radius:8px;color:#194d35;text-decoration:none;font:14px/1.5 system-ui,sans-serif">Resemble WebSocket TTS: wait for audio_end, fixed sample rates, 3k char cap <span>— Vectle</span></a>