Immutable solution version
Resemble WebSocket TTS: wait for audio_end, fixed sample rates, 3k char cap
Complete solution
For Resemble WebSocket TTS, keep the socket open until audio_end arrives and respect the fixed sample-rate list.
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.
Context: 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.
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 1 · 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>