Hacktoberfest 2026: the issues maintainers tagged for October, open and beginner-friendly. Browse Hacktoberfest issues

Feature: Long-text TTS – sentence chunking, no input length limit, and crossfaded streaming

Open
  • Is something wrong?
#1,195 0 comments 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 1 day

Nobody has claimed this yet.

Assessment

Difficulty
5/5
Estimated time
Over a week
Newbie friendliness
22/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Active
Tech stack
go
Domain
api, backend

Research direction

The payload names only the /v1/audio/speech endpoint and no source files, so start by finding that route and how it forwards requests to TTS backends. Decide the design first: chunk sizing per backend, how audio streams back as one response, and whether crossfading is in scope. Done means a long input is split at sentence boundaries, sent in order, and returned as a single audio stream, which needs maintainer agreement on the design.

Written by the indexing model from the issue text.

Description

Summary

A user wants GoModel's text-to-speech (/v1/audio/speech) to read whole articles or books aloud. Backends like Pocket TTS have low character limits or get worse on long inputs, so clients have to split the text themselves. The archived project open-unified-tts did this as a proxy.

Proposal

Add optional gateway-side long-text handling for speech requests:

  • split the input at sentence boundaries, sized to each backend's limits
  • send the chunks in sequence and stream the audio back as one response
  • optionally crossfade or smooth the joins between chunks

Source

Reported on the GoModel Discord (#general), 2026-09-30 / 2026-10-01 UTC:

here's another niche gomodel could fill ... I have a use-case for making our TTS backend read out whole articles and I would have to handle chunking myself if not for a proxy like open-unified-tts, but it's unmaintained now

so having sentence chunking and removing the character limit, having crossfading, etc would make it a very nice streaming API for reading full pages, books, etc

https://discord.com/channels/1470354066524868676/1470354067875303426/1554721036094800002
https://discord.com/channels/1470354066524868676/1470354067875303426/1555319672163803147

Dominant language
Go
Stars
1.2k
Forks
111
Avg merge
17h 1m
Merged PRs (30d)
95

Getting set up

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from ENTERPILOT/GoModel

All issues in ENTERPILOT/GoModel

Similar issues

More Go issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.