Free speech APIs — transcription and text-to-speech

Free speech-to-text and text-to-speech APIs, from free monthly minutes to hundreds in credit.

Audio APIs — transcription (STT) and synthesis (TTS) — often ship a real free tier or a sizeable one-time credit. The providers below offer free audio/speech access, from a few free hours a month to hundreds of dollars in starting balance.

Check the "catch" on each provider's page: some free speech tiers forbid commercial use or watermark the output.

Top pick — Groq

Lowest-latency inference for open-weight models Details →

17 verified providers

ProviderFree tierRate limitsGotchas
Google Gemini API (AI Studio)Gemini 2.5 Flash, 2.5 Flash-Lite, 2.5 Pro (limited), embeddings, TTS modelsVaries by model, roughly 5-30 req/min and 20-500 req/day depending on modelno cardno phonecommercial OKOpenAI-compatible
GroqOpen-weight models (Llama, Qwen, GPT-OSS) plus Whisper, no credit card requirede.g. llama-3.1-8b-instant: 30 RPM/14.4K RPD/6K TPM/500K TPD; llama-3.3-70b-versatile: 30 RPM/1K RPD/12K TPM/100K TPD; qwen3-32b: 60 RPM/1K RPD/6K TPM/500K TPD; similar for GPT-OSS and Whisper modelsno cardphone requiredcommercial OKOpenAI-compatible
Cloudflare Workers AI10,000 Neurons/day, all account plans30+ models: LLMs (Llama, Mistral, DeepSeek, Qwen...), embeddings, image, audiono cardno phonecommercial OKOpenAI-compatible
HuggingFaceFree CPU Basic + ZeroGPU for Spaces; Inference Providers has a monthly credit ($0.10/mo on Free plan, $2.00/mo on PRO/Team/Enterprise)No RPM/TPM published, only credit amountsno cardOpenAI-compatible
Scaleway Generative APIs1,000,000 tokens free + 60 min Whisper transcription; billing starts at token 1,000,001Gemma, Llama, Mistral, QwenOpenAI-compatible
Deepgram$200 free credit on signup (no card, no expiration) — Nova speech-to-text and Aura text-to-speech at pay-as-you-go ratesSTT pre-recorded up to 50 concurrent; STT streaming up to 150; TTS REST up to 15; TTS streaming up to 45no cardno phonecommercial OK
AssemblyAI$50 free credit on signup (no card) — pre-recorded & streaming speech-to-text, Speech Understanding, and an OpenAI-compatible LLM Gateway (25+ models)Free tier: 5 parallel transcriptions; streaming 5 new streams/min; global 20k requests / 5 minno cardno phonecommercial OKOpenAI-compatible
Pollinations.aiFree hosted image models (Flux, Turbo, Stable Diffusion) via a simple GET URL; also text and audio. No signup required to startAnonymous ~1 request / 15s; free registration (Seed tier) ~1 request / 5sno cardno phone
Twelve Labs (Marengo Embed)Free plan: the Marengo Embed API for all input types (video, audio, image, text) at no cost, plus ~600 min indexingEmbed video/audio: 3,000 RPD, 25 RPM; embed text/image: 3,000 RPD, 600 RPMno card
Speechmatics3,000 minutes (50 hours)/month speech-to-text + 1,000,000 characters (~20 hrs)/month text-to-speech2 concurrent real-time sessions on the free planno card
Speechify API50,000 characters/month TTS (hard cap) + 60 min/month voice agents3 concurrent calls; hard cap pauses at the limit (no overages)no cardno phonecommercial OK
Hume AI (Octave TTS)10,000 characters/month TTS (~10 minutes) on the Free plan15 requests per minuteno cardcommercial OK
Unreal Speech250,000 characters/month TTS (~6 hours of audio)Tiered endpoints for different text lengths; specific caps not documentedcommercial OK
ElevenLabs10,000 credits/month shared across Text-to-Speech, Speech-to-Text and more (~10 min TTS/month)Concurrency tied to the Free plan (not numerically published)no cardno phoneeval only
Sarvam AI₹100 in free credits on signup, usable across all APIs including the Sarvam-M chat/LLM API and speech (STT/TTS)Not published; bounded by the ₹100 creditOpenAI-compatible
Gladia€50 in free credits on signup for speech-to-text (~80+ hrs pre-recorded or 60+ hrs real-time at current rates)Not published; bounded by the €50 credit
Rime3,000 free TTS minutes for every new account (Starter plan)Starter: 20 concurrent TTS generations

FAQ

Is there a free speech-to-text API?

Yes — Groq (Whisper), Cloudflare Workers AI and others offer free STT; several dedicated speech providers also grant a sizeable one-time credit.

Which free speech API is best for production?

Check each provider’s rate limits and whether commercial use is allowed — some free speech tiers are evaluation-only or watermark their output.

More guides

← All guides