Speech-to-Text & Text-to-Speech for Astro: what 12 makers' products chose
Among 12 makers' products built with Astro that we know the Speech-to-Text & Text-to-Speech of, ElevenLabs leads: 7 of them (58%). Next come Cartesia (2) and Deepgram (2).
Real-time or batch, and which direction. Streaming voice features need low latency above everything, while transcribing recordings is about accuracy and price per hour. Most providers lead in one direction — speech-to-text or text-to-speech — so many apps end up using two.
What makers on Astro chose
| Option | Astro products | All makers |
|---|---|---|
| 7 (58%) | 56% | |
| 2 (17%) | 12% | |
| 2 (17%) | 27% | |
| 2 (17%) | 11% |
Live makers' products with a source for both: that they're built with Astro, and what they use for Speech-to-Text & Text-to-Speech. A product using two options counts in both; not market share. "All makers" is the option's share among every maker's product that made this decision.
Which to pick, by situation
- How the voice sounds is part of the product — narration, characters, content
ElevenLabs 7 here - You're building live conversation where every millisecond of delay shows
Cartesia 2 here
Deepgram 2 here - Users upload recordings to be transcribed and analysed
AssemblyAI 2 here
Deepgram 2 here
ElevenLabs
Voice generation7 Astro products here (58%).
In Lovable, ReplitBest forNatural, expressive voices and voice cloning for narration, content and characters.
Trade-offCredits run out fast on long audio, and cloning needs consent from the voice owner.
“We finally gave our video editing assistant access to Eleven Labs capabilities and it instantly improved the overall feeling of the videos created with tellers.ai !”
“We've used ElebenLabs voices on our platform and it has been the smoothest experience – thank you!”
Speech-to-Text & Text-to-SpeechMaker says so · source ↗“We finally gave our video editing assistant access to Eleven Labs capabilities and it instantly improved the overall feeling of the videos created with tellers.ai !”
Speech-to-Text & Text-to-SpeechMaker says so · source ↗“They are too good. We tried other vendors, but no one is even close to their quality”
Speech-to-Text & Text-to-SpeechMaker says so · source ↗“ElevenLabs helped us create natural voiceovers and bring Banger’s launch story to life across languages.”
Speech-to-Text & Text-to-SpeechMaker says so · source ↗“We use ElevenLabs for audio interviews with employees. It helps us replace traditional surveys with a natural conversation.”
Speech-to-Text & Text-to-SpeechMaker says so · source ↗“When developing our Voice Agents, we needed voices that wouldn’t immediately scream “robot” to customers. ElevenLabs delivered exactly what we needed.”
Speech-to-Text & Text-to-SpeechMaker says so · source ↗“Range of voices I could choose from an ability to create pesonalised audio on the fly!”
Speech-to-Text & Text-to-SpeechMaker says so · source ↗
Cartesia
Voice generation2 Astro products here (17%).
Best forText-to-speech with very low time to first audio, for live conversation.
Trade-offBuilt for real-time use, with fewer creator tools such as dubbing and sound effects.
“We love Cartesia for their super-fast and hyper-realistic voices!”
“Pretty natural-sounding voice :)”
Speech-to-Text & Text-to-SpeechMaker says so · source ↗“We love Cartesia for their super-fast and hyper-realistic voices!”
Speech-to-Text & Text-to-SpeechMaker says so · source ↗
Deepgram
Transcription2 Astro products here (17%).
Best forStreaming speech-to-text with low latency, for live calls and voice interfaces.
Trade-offIts text-to-speech is built for voice agents, with a set of prebuilt voices and no voice cloning.
“We use Deepgram to transcribe live AI-driven training calls, where SDRs and sales reps practice conversations with an AI agent impersonating real prospects. The fast, accurate transcription is essential — it enables our coaching system to deliver instant feedback and correction right after each mock call. This real-time loop helps reps improve faster, and we’re thankful to the Deepgram team for enabling it.”
“We use Deepgram to transcribe live AI-driven training calls, where SDRs and sales reps practice conversations with an AI agent impersonating real prospects. The fast, accurate transcription is essential — it enables our coaching system to deliver instant feedback and correction right after each mock call. This real-time loop helps reps improve faster, and we’re thankful to the Deepgram team for enabling it.”
Speech-to-Text & Text-to-SpeechMaker says so · source ↗“Super fast, very accurate dictation”
Speech-to-Text & Text-to-SpeechMaker says so · source ↗
AssemblyAI
Transcription2 Astro products here (17%).
Best forAccurate transcription of recordings with speaker labels and extras like summaries and topic detection.
Trade-offFocused on speech-to-text; you need another vendor for speech output.
“Nugget is built on real-time interview transcription, so latency and accuracy on conversational audio were non-negotiable. AssemblyAI's Universal-Streaming plus speaker diarization out-performed Deepgram in my testing on actual customer calls — fewer dropped words, cleaner speaker separation. The API was also the cleanest to integrate; I had a production pipeline running in a day. LeMUR was the bonus that sealed it.”
“Nugget is built on real-time interview transcription, so latency and accuracy on conversational audio were non-negotiable. AssemblyAI's Universal-Streaming plus speaker diarization out-performed Deepgram in my testing on actual customer calls — fewer dropped words, cleaner speaker separation. The API was also the cleanest to integrate; I had a production pipeline running in a day. LeMUR was the bonus that sealed it.”
Speech-to-Text & Text-to-SpeechMaker says so · source ↗“Converting clinician-patient conversations into highly accurate transcripts.”
Speech-to-Text & Text-to-SpeechMaker says so · source ↗Also chosen, and not seen yet
Real options for Speech-to-Text & Text-to-Speech not seen among these Astro products yet: OpenAI API, Whisper, Kokoro, Fish Audio, Recall.ai.
Getting Speech-to-Text & Text-to-Speech right
Decide whether audio is live (calls, voice UI) or recorded (uploads, meetings); the right provider differs. Test with your own audio — accents, background noise and domain terms change accuracy more than benchmarks show. For TTS, listen to full paragraphs, not single sentences, before choosing a voice.
- Choosing a speech-to-text provider on clean benchmark audio, then discovering it struggles with your users' accents, jargon and background noise.
- Cloning a voice without the speaker's documented consent, which breaks provider terms and, in many places, the law.
- Sending whole recordings to a streaming API or live audio to a batch one, paying for latency you don't need or waiting on latency you can't accept.
The rest of the Astro stack
What makers' Astro products chose for their other decisions, the most common pick for each:
- Hosting: Vercel 49 of 112
- Transactional Email: Resend 44 of 84
- Web Analytics: Cloudflare Web Analytics 18 of 47
- Payments: Stripe 22 of 34
- Database: Supabase 7 of 27
- LLM API: OpenAI API 17 of 27
- Product Analytics: PostHog 13 of 14
- Authentication: Clerk 8 of 12
Questions
What do most Astro apps use for Speech-to-Text & Text-to-Speech?
Among 12 makers' products built with Astro that we know the Speech-to-Text & Text-to-Speech of, ElevenLabs leads: 7 of them (58%). Next come Cartesia (2) and Deepgram (2).
How this is counted: a product is on Astro when a live-product source says so (the maker, its website, a customer story or a subprocessor list), and the same for its Speech-to-Text & Text-to-Speech. How evidence is collected.