# NousResearch/hermes-agent · TTS speed control and provider option expansion

## Open now

- 1 issue, 1 PR open on GitHub.
- #17789: Support ElevenLabs TTS speed configuration
- PR #39382: feat(tts): expose ElevenLabs generation options

These items add speed/rate configuration support across multiple TTS providers (ElevenLabs, Edge TTS, OpenAI, MiniMax, NeuTTS), using native parameters where available and ffmpeg fallback otherwise. Additional work covers exposing ElevenLabs generation options and unifying spoken-text preprocessing with provider-level tool parameters.

## TL;DR

- 4 member(s): 1 open issue(s), 1 closed issue(s), 1 open PR(s), 1 merged PR(s), 0 PR(s) closed without merging.
- A fix was merged to main in PR #73513. Verify it addresses your case.
- **Recommended:** read PR #73513 (and any competing PRs below) before filing. Confirm the merged change covers your symptom.

## Maintainer resolution verdict

- Internal-tracker verdict over this cluster's issue members: `unresolved`. This is distinct from the fix status above. Weigh it yourself.

## How this cluster was grouped

- Link evidence (`STRUCTURAL_PARTIAL`): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text.
- Members outside that structural core may belong to a different underlying problem.
- Pairwise link density `0.39`: the share of member pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36. `1.00` means every pair is linked.

## Open related issues

- #17789: Support ElevenLabs TTS speed configuration

## Closed / duplicate issues

- #6926: Feature: TTS Speed Control — Wire native rate params for Edge/OpenAI, add ffmpeg atempo fallback for NeuTTS/ElevenLabs

## Prior & competing PRs

- **#73513: feat(tts): unified spoken-text preprocessing + speed/instructions/provider tool params**. merged to main · fix tier `verified`
  - maintainer direction: category `merged`
  - files: `cli-config.yaml.example`, `cli.py`, `contributors/emails/[redacted:email]`, `contributors/emails/[redacted:email]`, `contributors/emails/[redacted:email]`, `contributors/emails/[redacted:email]`, `contributors/emails/[redacted:email]`, `gateway/platforms/base.py`, `hermes_cli/voice.py`, `tests/gateway/test_base_topic_sessions.py`, `tests/tools/test_tts_instructions.py`, `tests/tools/test_tts_max_text_length.py`, `tests/tools/test_tts_prepare_spoken.py`, `tests/tools/test_tts_speed.py`, `tests/tools/test_tts_text_normalize.py`, `tests/tools/test_tts_xai_speech_tags.py`, `tests/tools/test_voice_cli_integration.py`, `tools/tts_text_normalize.py`, `tools/tts_tool.py`, `website/docs/user-guide/features/tts.md` (+1 more)
- **#39382: feat(tts): expose ElevenLabs generation options**. open
  - maintainer direction: category `duplicate_of`; implication `duplicate`; refs `efd69c9a9`, `#69511`, `#73513`, `#43980`, `#39382`
  - files: `tests/tools/test_tts_elevenlabs_options.py`, `tools/tts_elevenlabs_options.py`, `tools/tts_streaming.py`, `tools/tts_tool_providers.py`, `website/docs/user-guide/configuration.md`, `website/docs/user-guide/features/tts.md`, `website/docs/user-guide/features/voice-mode.md`

## Fix status

- Merged to main in PR #73513 (cited above). No release data is tracked. Verify downstream.
- Fix last verified (merged) `2026-07-28`.
- Subsystem: `agent`