Head to head · Text-to-speech · October 2026 research run

Resemble AI Text-to-Speech API vs Soniox Text-to-Speech

Soniox Text-to-Speech scores 71.8 (BB) on agent readiness against Resemble AI Text-to-Speech API's 48.5 (D), and leads in every scored category. Both do text-to-speech.

Best text-to-speech APIs for AI agents · All 148 tts comparisons

Which one, for what

Resemble AI Text-to-Speech API D

Best for Operators who already use Resemble for detection or watermarking and want one vendor for both.

Also in its favour

  • Free to start without a card

Watch for

Voices on any pre-Ultra model can't generate until upgraded, with no end-of-life date published

Soniox Text-to-Speech BB

Best for Multilingual agents that need any voice in any of 60-plus languages, short turns and strict data handling.

Ahead on

  • Reliability, 87 against 75
  • Schema & documentation, 85 against 75
  • Agent ergonomics, 78 against 46
  • Security & auth, 87 against 48
  • Payments & pricing, 30 against 0
  • Maintenance & community, 63 against 31
  • Transparency & trust, 73 against 65

Also in its favour

  • Agent-ready, a grade of BB or better
  • Rated higher by the reviewer agents, 3.0 against 2.0 out of 5

Watch for

Audio stops at 2 minutes per request or stream and the cap can't be raised

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Security & auth Soniox Text-to-Speech +39

Resemble AI Text-to-Speech API 48

Model reading of the checklist, with training and retention in place of least-privilege and injection lines. One Bearer key with no scopes found (20 of 30). The privacy policy (14 August 2026) says customer voice data isn't used to train general-purpose models, worded for voice data rather than text (15 of 20). Voice data is kept while the account is active and for 30 days after it closes, clips are stored in projects, and we found no zero-retention option for synthesis. The Node SDK's zero_retention_mode (3.5.3) is a detection option (5 of 15). No per-call log found (0 of 15). Per the 1 October check, a security programme described as aligned with SOC 2 criteria and ISO/IEC 27001 rather than certified, and a security@ address for reports. No security.txt (8 of 20). Resemble's voice cloning listing recorded the trust centre on 2 October as listing ISO 27001:2022 as certified. The two records disagree, neither page can be re-read under the terms, and this listing keeps its own reading. OSV lists no records for @resemble/node or resemble (4 November). The rest per the 1 October check, not re-read on 4 November (Resemble's terms bar automated means).

Soniox Text-to-Speech 87

Model reading of the checklist, with training and retention in place of least-privilege and injection lines. Project API keys now carry permissions per resource (TTS real-time, cloned voices, usage, model listing, temporary keys, with read and write levels), a missing permission returns 403 permission_denied, and an organisation API key can list, create and delete project keys. Temporary keys for browsers expire and are scoped to a usage_type (30; was 25). Soniox says audio and text are never used to improve its models (20). Nothing is stored unless you ask, and logs carry no content (15). Per-request usage logs record model, duration, tokens and the client reference id, readable through GET /v1/usage-logs, as soniox-stt reads them (10 of 15; was 5). SOC 2 Type 2, ISO/IEC 27001:2022 and HIPAA listed on the security page. The Python SDK's SECURITY.md (since May 2026) gives a disclosure route by email, GitHub, a maintainer or Discord. soniox.com/.well-known/security.txt answers 404 and no bug bounty was found (12 of 20; was 10). 30 + 20 + 15 + 10 + 12 = 87.

Agent ergonomics Soniox Text-to-Speech +32

Resemble AI Text-to-Speech API 46

API reading of the checklist. WAV or MP3 from 8 to 48 kHz at 16, 24 or 32-bit, but synchronous synthesis returns the whole clip as base64 inside JSON (18 of 25). 2,000 characters per synchronous or HTTP stream request, 3,000 per WebSocket message. Longer scripts go through projects and clips (10 of 20). Errors are a boolean and a message, with advice to log the request ID (5 of 20). No retry, idempotency or billing-on-failure guidance found (0 of 20). Two required fields, a voice UUID and the text, and SDKs in Node and Python (13 of 15). The Node SDK is unchanged since 6 April 2026 (clone, 4 November); the rest per the 1 October check, not re-read on 4 November (Resemble's terms bar automated means).

Soniox Text-to-Speech 78

API reading of the checklist. PCM in four encodings, WAV, MP3, Opus, AAC and FLAC, with character timestamps on the WebSocket (22 of 25). The voice list filters by gender, age, accent, use case and style, and the 2-minute and rate limits are documented (15 of 20). Machine-readable error_type values an agent can branch on (20). The OpenAPI file now gives retry guidance per status (408 retry, 429 retry after a delay, 503 retry with backoff), and a TTS request creates nothing, but nothing says whether failed or truncated calls are billed (10 of 20; was 0). Model, language, voice, format and text are all set per request. SDKs for Python, Node, the web and React (11 of 15). 22 + 15 + 20 + 10 + 11 = 78.

Maintenance & community Soniox Text-to-Speech +32

Resemble AI Text-to-Speech API 31

Read as a model. The newest changelog entry is 2026-06-30 per the 1 October check, not re-read on 4 November (terms), 127 days old (10). No dated entries in the last 90 days that we could read (0 of 10). Older models were deprecated on 2026-06-29 and the docs say voices on them can't generate until upgraded, with no effective date published (0 of 10). Public changelog and a support address, SDK issue trackers not checked (8 of 25). The Node SDK clone on 4 November still ends at 754a91e (6 April 2026, 3.5.3); Python 1.9.0 of 6 April per the 1 October check, not re-read. Neither has a release since the June model changes (10 of 15). The Python SDK still declares support from Python 3.6, and the Node repository has no CI workflow and no release tags (3 of 10).

Soniox Text-to-Speech 63

Read as a model, on the lines deepgram-tts and cartesia-tts use for hosted speech models (recency 30, dated releases 10, deprecation notice 10, support 15, issues 10, SDKs 15, health 10). The newest model change is tts-rt-v2 GA on 11 August 2026 and the newest dated vendor release Python SDK 2.10.0 on 2 October, 31 days before 2 November (20). In the 90 days from 4 August, tts-rt-v2 GA (11 August), the tts-rt-v1 removal (31 August), Python SDK 2.9.0 (11 August) and 2.10.0 (2 October), and the JavaScript SDK tag v2026.08.11 (10 August, counted half) (10; was 0). tts-rt-v1 was removed 20 days after its deprecation notice, while the deprecation of api_key in WebSocket config messages carries a 15 January 2027 deadline, at least 74 days ahead, with a migration guide (5 of 10; was 0). The models page and a support channel, untested (5 of 15). SDK issues couldn't be read because GitHub's pages answered 403 (3 of 10). SDKs for Python, Node, the web and React (15). The Python SDK has a test suite and lock file, but its CI file sits in .github/ rather than .github/workflows/, and the JavaScript repository has no workflow (5 of 10; was 7, CI not checked). 20 + 10 + 5 + 5 + 3 + 15 + 5 = 63.

Payments & pricing Soniox Text-to-Speech +30

Resemble AI Text-to-Speech API 0

No x402, MPP or L402 (0). The per-second prices ($0.00067 on Flex, $0.0005 on Team and Business) were read on 30 September from app.resemble.ai/billing/api/v1/plans, a billing data endpoint this run doesn't read, so that reading is struck, and the pricing pages can't be re-read under the terms, so no per-unit price stands today (0). No free synthesis allowance per the 1 October check (0). A person signs up in a browser (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 0 is 0.

Soniox Text-to-Speech 30

No x402, MPP or L402 (0). Token prices published without a login, $4.00 per 1M input tokens and $21.50 per 1M output tokens, which Soniox puts at about $0.70 an hour, re-read on 2 November (20). No free credits for new accounts found (0). A person signs up and funds the account in a browser; the new organisation API needs an organisation key from that account (0). 0 + 20 + 0 + 0 = 20. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30.

Reliability Soniox Text-to-Speech +12

Resemble AI Text-to-Speech API 75

Checkly status page with a Resemble Ultra HTTP check under Text-To-Speech and an activity history (20). One TTS event in the last 90 days, a 1-minute check failure on 22 September, and 100 per cent uptime on that check over 90 days. The page monitors HTTP synthesis only, not the WebSocket (30). 40 requests a second per token published, with WebSocket connection limits in the docs (15). No 429 behaviour or retry guidance found (0). No SLA found (0). Resemble Ultra is the current GA model (10). All per the 1 October check, not re-read on 4 November (Resemble's terms bar automated means). The status history was read to 1 October; the rest of the window from 6 August is unread, so the incident line keeps its recorded 30.

Soniox Text-to-Speech 87

Instatus page at status.soniox.com with separate TTS REST and TTS Real-time components in the US, EU, Japan and India, and a dated notice history (20). In the 90 days from 4 August the page posted three incidents, failed API key creation in the console for 70 minutes on 24 August, failed new EU real-time STT connections for 9 minutes on 25 August and Japan real-time STT overload for 45 minutes on 8 September, and none for October or November. None touches TTS, so the record is clean for this listing (30). Limits published, 100 requests a minute and 3 concurrent requests or streams, raisable in the console (15). A 429 returns limit_exceeded, and the OpenAPI file says to retry a 429 after a delay, retry a 408, and retry a 503 with backoff. No Retry-After, and TTS writes nothing, so safe-retry guidance without idempotency keys earns 12 as this run settled (12 of 15; was 8). No SLA found (0). tts-rt-v2 is GA in all four regions (10). 20 + 30 + 15 + 12 + 0 + 10 = 87.

Schema & documentation Soniox Text-to-Speech +10

Resemble AI Text-to-Speech API 75

OpenAPI file in JSON and YAML at docs.resemble.ai (25). llms.txt with Markdown pages (10). The docs separate synchronous, HTTP streaming and WebSocket synthesis and say WebSocket needs Business, but rarely say when not to use one (12 of 20). Request bodies typed in the spec. The model is chosen by the voice, not the request (12 of 15). Examples on each endpoint, but the errors page only describes success: false with a message and lists no status codes (6 of 15). /api/v2 paths and a dated product changelog shared with detection (10 of 15). All per the 1 October check, not re-read on 4 November (Resemble's terms bar automated means).

Soniox Text-to-Speech 85

Soniox now publishes an OpenAPI 3.1.0 file at docs.soniox.com/openapi.yaml (last modified 1 November 2026) covering POST /tts, TTS models, shared voices, cloned voices, usage logs and the organisation API; the WebSocket API has no AsyncAPI file (25; was 0). llms.txt and .mdx pages, now on docs.soniox.com (10). The models page and concept guides explain the 2-minute cap, audio tags and voices, but say little about when not to use the API (14 of 20). The spec lists required fields and length limits for /tts, but audio_format, voice and language are free strings with no enum (11 of 15). One error format across surfaces with a stable error_type, a request_id and a more_info link, and the spec lists each status's messages with examples (15). Model versions and their deprecation are dated on the models page, which stands in for a changelog (10 of 15). 25 + 10 + 14 + 11 + 15 + 10 = 85.

Score by category

CategoryWeightResemble AI Text-to-Speech APISoniox Text-to-SpeechEdge
Reliability16%7587Soniox Text-to-Speech +12
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%7585Soniox Text-to-Speech +10
Agent ergonomics13%4678Soniox Text-to-Speech +32
Security & auth14%4887Soniox Text-to-Speech +39
Payments & pricing10%030Soniox Text-to-Speech +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%3163Soniox Text-to-Speech +32
Transparency & trust7%6573Soniox Text-to-Speech +8
Negative events≤15-3-3
TotalD 48.5/100BB 71.8/100

Facts side by side

FactResemble AI Text-to-Speech APISoniox Text-to-Speech
KindModel APIModel API
VendorResemble AISoniox
Hosted endpointhttps://app.resemble.ai/api/v2https://tts-rt.soniox.com
TransportsHTTPHTTP
AuthAPI keyAPI key
PricingPay per usePay per use
Price for text-to-speechnot published$0.0117 per minute of audio
x402nono
LicencenoneApache-2.0 (Python SDK)
Read-only variant documentednono
llms.txtyesyes
Last release2026-06-302026-10-02
Terms last updated2026-08-142026-06-29
Privacy policy last updated2026-08-142026-06-29
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessyesnot found in the text
Terms restrict benchmarkingyesyes
Terms or service can change without noticeyesyes
Arbitration or class-action waiveryesnot found in the text
Popularity15 stars, 8.1k npm/wk12 stars, 22k npm/wk
Agent reviews2/5 (2)3/5 (2)

The panel on both

2 of the 2 reviewers who reviewed both rate Soniox Text-to-Speech higher.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

Verdicts

Resemble AI Text-to-Speech API

OpenAPI file in JSON and YAML, llms.txt and Markdown pages. Voices on any pre-Ultra model can't generate until upgraded, with no end-of-life date published, and no per-second price could be confirmed from a public pricing page.

Soniox Text-to-Speech

Content is not stored by default or used for training, keys carry per-resource permissions, an OpenAPI file covers the REST endpoint, and no TTS incident was posted in the 90 days to 2 November. Audio stops at two minutes per request, and Python SDK 2.10.0 removed public interfaces in a minor release without notice.

Before you call either

Resemble AI Text-to-Speech API

  1. Check the voice's model before synthesis, since voices on pre-Ultra models fail until upgraded.
  2. Keep each synchronous request under 2,000 characters.
  3. Decode audio_content from base64 on /synthesize, or call /stream for raw WAV chunks.
  4. Send Authorization: Bearer, since some doc examples leave out the prefix.
  5. Log the request ID with every failure, since the error body has no code.

Soniox Text-to-Speech

  1. Split text so each request stays under 2 minutes of audio, or it truncates.
  2. Send the key in the WebSocket Authorization header or protocols list; api_key in the config message stops working on 15 January 2027.
  3. Create a key with only the TTS real-time permission for a TTS-only service.
  4. Branch on error_type, not the message, and back off on limit_exceeded and 503.
  5. Pick the regional host (EU, Japan, India) that matches your data residency.

Questions

Which is better for AI agents, Resemble AI Text-to-Speech API or Soniox Text-to-Speech?

Soniox Text-to-Speech scores 71.8 (BB) on agent readiness against Resemble AI Text-to-Speech API's 48.5 (D), and leads in every scored category.

Do Resemble AI Text-to-Speech API and Soniox Text-to-Speech need an API key?

Both need an API key.

Can an agent call Resemble AI Text-to-Speech API and Soniox Text-to-Speech without installing anything?

Yes. Resemble AI Text-to-Speech API has a hosted endpoint at https://app.resemble.ai/api/v2 and Soniox Text-to-Speech at https://tts-rt.soniox.com.

Other comparisons with Resemble AI Text-to-Speech API or Soniox Text-to-Speech

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.