Skip to content

Add TTS feature recipes: models, voices, formats, i18n, versioning, errors, watermark #8

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
1 commit merged into from
Sep 8, 2026
Merged

Add TTS feature recipes: models, voices, formats, i18n, versioning, errors, watermark #8

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,8 @@ __pycache__/
*.ogg
*.aac
*.flac
*.pcm
*.ulaw
*.vtt
*.srt
!**/fixtures/**
Expand All @@ -35,3 +37,9 @@ build/
.DS_Store
.idea/
.vscode/

# Agent scratch / worktrees (never commit these)
/.claude/
/.opencode/
/.overseer/
/.agents/
30 changes: 27 additions & 3 deletions COVERAGE.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,14 +11,38 @@ Recipes come in two flavors:

Each cell points at `recipes/audio/<language>/<flavor>/<recipe>/`.

## Audio (Text-to-Speech)
Legend also: — not applicable.

## Audio — synthesis

| | TypeScript<br>SDK | TypeScript<br>Native | Python<br>SDK | Python<br>Native | Bash<br>Native |
| -------------------------------------- | :---------------: | :------------------: | :-----------: | :--------------: | :------------: |
| quickstart (synthesize to file) | ✅ | ✅ | ✅ | ✅ | ✅ |
| streaming | ✅ | ✅ | ✅ | ✅ | ✅ |
| SSML controls (pitch / rate / emotion) | ✅ | ✅ | ✅ | ✅ | ✅ |
| word-level timestamps (caption sync) | ✅ | ✅ | ✅ | ✅ | ✅ |
| voice cloning | ✅ | ✅ | ✅ | ✅ | ✅ |
| multilingual (language param) | ✅ | ✅ | ✅ | ✅ | ✅ |
| output formats (telephony / bitrate) | ✅ | ✅ | ✅ | ✅ | ✅ |
| voice cloning (verified consent) | ✅ | ✅ | ✅ | ✅ | ✅ |

## Audio — voices & models

| | TypeScript<br>SDK | TypeScript<br>Native | Python<br>SDK | Python<br>Native | Bash<br>Native |
| ---------------------------- | :---------------: | :------------------: | :-----------: | :--------------: | :------------: |
| list models | ✅ | ✅ | ✅ | ✅ | ✅ |
| list voices (pagination) | ✅ | ✅ | ✅ | ✅ | ✅ |
| voice language/model support | ✅ | ✅ | ✅ | ✅ | ✅ |

## API essentials

| | TypeScript<br>SDK | TypeScript<br>Native | Python<br>SDK | Python<br>Native | Bash<br>Native |
| ------------------------------------ | :---------------: | :------------------: | :-----------: | :--------------: | :------------: |
| version pinning + idempotency | ✅ | ✅ | ✅ | ✅ | ✅ |
| error handling (codes / Retry-After) | ✅ | ✅ | ✅ | ✅ | ✅ |
| watermark detect / verify | — | ✅ | — | ✅ | ✅ |

Notes:

Bash has no SDK column — it's curl-only by design.
- Bash has no SDK column — it's curl-only by design.
- **Watermark** (`POST /v1/audio/watermark/{detect,verify}`) is not exposed in the SDKs, so it ships as native REST only.
- Multi-speaker **dialogue** (`POST /v1/audio/dialogue`, model `simba-dialogue-1.0`) is a known gap — not yet in the SDKs, so no recipe yet.
100 changes: 69 additions & 31 deletions README.md
View file
Open in desktop

Large diffs are not rendered by default.

261 changes: 261 additions & 0 deletions pnpm-lock.yaml
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 2 additions & 0 deletions recipes/audio/bash/native/error-handling/.env.example
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
# Get a key at https://platform.speechify.ai/api-keys
SPEECHIFY_API_KEY=
Loading
Loading