feat: add multilingual-tts demo - #32
Open
luke-speechify wants to merge 1 commit into
Open
Conversation
Read text in any of 30+ languages with the Speechify TTS API, one native voice per locale. One-page Next.js playground: pick a language, hear it spoken by a voice native to that locale via POST /v1/audio/speech with the `language` parameter on simba-3.0. API key stays server-side; Turnstile fails open locally. Six languages wired up (en, de, es, fr, it, pt-BR), each with a native catalogue voice; 30+ more available. Registered as a hostable service in pnpm-workspace.yaml and vercel.json. Includes a Playwright e2e that hits the live API when SPEECHIFY_API_KEY is set.
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Pairs with the upcoming speechify.ai post "Text-to-speech in 30+ languages with the Speechify API" (DRG-376). Companion to the existing
multilingual-voiceoverdemo, from a different angle: an interactive language playground built around thelanguageparameter.What it does
A one-page Next.js playground. Pick a language, press Speak, and the text is synthesized in a voice native to that locale.
POST /api/speak(Node runtime) calls SpeechifyPOST /v1/audio/speechwithmodel: "simba-3.0",audio_format: "mp3", and thelanguageparameter, returning base64 audio. The whole feature is that one field.alfonso), German (amalia), Spanish (aitana), French (adeline), Italian (alessia), Portuguese-BR (adriana). 30+ more locales are available.TURNSTILE_SECRET_KEYis unset (local/fork).Notes
simba-3.2/simba-englishare English-only, so non-English usessimba-3.0.pnpm-workspace.yamlandvercel.json(service +/multilingual-tts/:path*rewrite).Tested
pnpm --filter multilingual-tts typecheckpasses.fr-FRandde-DEreturned real MP3 audio (200), an unsupported language returned 400.e2e/multilingual-tts.spec.ts) drives the picker and asserts a 200 + base64 audio; skips whenSPEECHIFY_API_KEYis unset.