Skip to content

docs(tts): document per-provider max_text_length caps from #13743 - #13825

Closed
r266-tech wants to merge 1 commit into
NousResearch:mainfrom
r266-tech:docs-tts-max-text-length-13743
Closed

docs(tts): document per-provider max_text_length caps from #13743#13825
r266-tech wants to merge 1 commit into
NousResearch:mainfrom
r266-tech:docs-tts-max-text-length-13743

Conversation

@r266-tech

Copy link
Copy Markdown
Contributor

Summary

PR #13743 replaced the global MAX_TEXT_LENGTH = 4000 with a per-provider table and a user-override max_text_length: key, but website/docs/user-guide/features/tts.md documented no length behaviour at all. Users hitting truncation (or wondering why xAI can take 15k chars while Mistral can't) have no way to discover the new caps or the override from the docs.

This PR adds an Input length limits subsection to the Voice & TTS page, right after the existing ### Configuration YAML block. It documents:

  • Provider default caps as defined in tools/tts_tool.py PROVIDER_MAX_TEXT_LENGTH (Edge 5000, OpenAI 4096, xAI 15000, MiniMax 10000, Mistral 4000, Gemini 5000, NeuTTS/KittenTTS 2000)
  • ElevenLabs model-aware table from ELEVENLABS_MODEL_MAX_TEXT_LENGTH (flash_v2_5 40k, flash_v2 30k, multilingual_v2 10k default, v3 5k)
  • Override syntax: tts.<provider>.max_text_length: <int> with a YAML example
  • Validation rules from _resolve_max_text_length() (non-positive, non-integer, or boolean values fall through to the provider default so a broken config can't accidentally disable truncation)

All values verified against tools/tts_tool.py on main (commit 7b79e0f).

Test plan

  • Values cross-checked against PROVIDER_MAX_TEXT_LENGTH and ELEVENLABS_MODEL_MAX_TEXT_LENGTH dicts in tools/tts_tool.py
  • Validation rules cross-checked against _resolve_max_text_length() and tests/tools/test_tts_max_text_length.py
  • Docs-only: website/docs/user-guide/features/tts.md +37 / -0

PR NousResearch#13743 replaced the global MAX_TEXT_LENGTH=4000 with a per-provider
table and a user-override 'max_text_length:' key, but the user-guide
TTS page documented no length behaviour at all. Users hitting truncation
had no way to discover the new caps or the override.

Add an 'Input length limits' subsection after the existing Configuration
YAML block: provider default caps (Edge 5000 / OpenAI 4096 / xAI 15000 /
MiniMax 10000 / Mistral 4000 / Gemini 5000 / ElevenLabs model-aware /
NeuTTS,KittenTTS 2000), ElevenLabs model_id -> cap table (5k-40k), an
override example, and the validation rules (non-positive / non-integer /
boolean values fall through to the provider default).
@alt-glitch alt-glitch added type/docs Documentation improvements P3 Low — cosmetic, nice to have tool/tts Text-to-speech and transcription labels Apr 22, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

P3 Low — cosmetic, nice to have tool/tts Text-to-speech and transcription type/docs Documentation improvements

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants